Thoughts on Epistemology
Many of my thoughts on epistemology come from Wittgenstein's last work called On Certainty. They were developed from my understanding of On Certainty, in particular Wittgenstein's bedrock propositions. However, I don't want to give the impression that what I'm putting forth in this thread is necessarily what Wittgenstein was communicating in On Certainty. I developed my own theory based on some of his thinking, and how I interpreted some of his thinking. So much of my own thinking on this subject is going beyond what's presented in On Certainty. It's my expansion of some of the ideas in On Certainty, for better or worse.
First, it seems that there are beliefs that arise apart from language, and a belief, whether linguistic or not, is simply a state-of-mind. These mind states are clearly seen in our actions. This is not to say that all actions by living organisms reflect beliefs, but simply to say that all beliefs are reflections of mind states, which in turn are shown by the things we do.
Second, not only are there beliefs that arise non-linguistically, but our thoughts are also not dependent upon linguistics. This it seems, has to be case if one is to make sense of the development of linguistics. For if there are no beliefs and no thoughts prior to the formation of linguistics (language), what would be the springboard of language? How does one get from a mind of no thoughts and no beliefs, to a mind that is able to express one's thoughts linguistically? It also seems to be the case that language is simply a tool to communicate our thoughts to one another, which also seems to lend support for the idea that thinking is prior to language.
Third, the basis for beliefs in prelinguistic man is causal in nature, not based on reasoning, reasoning is a linguistic endeavor, at least as how it is defined here. How are beliefs causally formed? It seems to be the case that beliefs arise causally within the mind based on the interactions between our sensory experiences and the world around us. The interaction between our sensory experiences and the world do not necessitate the belief, but are simply sufficient to cause the belief. One acts upon the information given through sensory impressions, which in turn has a causal relationship with the belief.
Fourth, these three previous ideas form what is bedrock to all of epistemology. For epistemology arises out of language, it is a way of expressing what we know, or what we believe we know by using propositions. Justification come to an end with beliefs that are quite apart from those that arise through any method of linguistic justification. These bedrock beliefs are outside the purview of epistemology.
Fifth, bedrock beliefs can be expressed in language, as all beliefs can, but they are not dependent on language. For example, "I have hands," is such a belief, and it is expressed using linguistic concepts. However, the belief that we have hands is also shown by our actions, i.e., it is a state-of-mind that expresses itself in actions using our hands. Wittgenstein shows in On Certainty, as he reflects on Moore's claim that he has knowledge of his hands, that it is not a matter of knowing at all. There is something fundamental, something bedrock about this belief, and it is with such beliefs that justification ends. Thus, the idea or the conclusion that knowledge rests on beliefs outside the scope of epistemological concerns, something more fundamental, as expressed in the first three ideas of this thread.
Finally, the ideas expressed here solve two problems that have plagued some epistemological theories. First, the infinite regress problem, viz., that there is no end to justification, and the problem of circularity.
First, it seems that there are beliefs that arise apart from language, and a belief, whether linguistic or not, is simply a state-of-mind. These mind states are clearly seen in our actions. This is not to say that all actions by living organisms reflect beliefs, but simply to say that all beliefs are reflections of mind states, which in turn are shown by the things we do.
Second, not only are there beliefs that arise non-linguistically, but our thoughts are also not dependent upon linguistics. This it seems, has to be case if one is to make sense of the development of linguistics. For if there are no beliefs and no thoughts prior to the formation of linguistics (language), what would be the springboard of language? How does one get from a mind of no thoughts and no beliefs, to a mind that is able to express one's thoughts linguistically? It also seems to be the case that language is simply a tool to communicate our thoughts to one another, which also seems to lend support for the idea that thinking is prior to language.
Third, the basis for beliefs in prelinguistic man is causal in nature, not based on reasoning, reasoning is a linguistic endeavor, at least as how it is defined here. How are beliefs causally formed? It seems to be the case that beliefs arise causally within the mind based on the interactions between our sensory experiences and the world around us. The interaction between our sensory experiences and the world do not necessitate the belief, but are simply sufficient to cause the belief. One acts upon the information given through sensory impressions, which in turn has a causal relationship with the belief.
Fourth, these three previous ideas form what is bedrock to all of epistemology. For epistemology arises out of language, it is a way of expressing what we know, or what we believe we know by using propositions. Justification come to an end with beliefs that are quite apart from those that arise through any method of linguistic justification. These bedrock beliefs are outside the purview of epistemology.
Fifth, bedrock beliefs can be expressed in language, as all beliefs can, but they are not dependent on language. For example, "I have hands," is such a belief, and it is expressed using linguistic concepts. However, the belief that we have hands is also shown by our actions, i.e., it is a state-of-mind that expresses itself in actions using our hands. Wittgenstein shows in On Certainty, as he reflects on Moore's claim that he has knowledge of his hands, that it is not a matter of knowing at all. There is something fundamental, something bedrock about this belief, and it is with such beliefs that justification ends. Thus, the idea or the conclusion that knowledge rests on beliefs outside the scope of epistemological concerns, something more fundamental, as expressed in the first three ideas of this thread.
Finally, the ideas expressed here solve two problems that have plagued some epistemological theories. First, the infinite regress problem, viz., that there is no end to justification, and the problem of circularity.
Comments (1695)
Quoting Michael
Hm. I suspect Sam might agree. It's as if he started a thread on sports cars and it turned into a thread about sewing.
What about a theory that claims merely to provide a better answer?
And indeed, a pragamatic theory of epistemology that says there are no ultimates as such, so a theory that would benefit from the self-endorsement of the very attitude it adopts?
Quoting Banno
But you often speak as if you believe the world is the ultimate arbiter. Curious.
Anyway, my pragmatic point is that the best epistemology has this self-limiting nature. Instead of taking the world as some brutely ultimate limit on inquiry, it sees inquiry as itself relative to a self-centred limit of interest. We enquire into the facts so far as they seem to matter to us. Beyond that, there is no particular point of view being served.
It gives epistemology a self-grounding basis while also allowing it to grow or develop as large and complex as it likes. It is a closed and reliable system, yet also open and adaptive at the same time.
And so far, I haven't seen your argument against it. That is probably because you are basically a pragmatist but hate to be identified as such. You have some strong bias towards a linguistic level of semiosis - an interest in "truth" as a language game - and so resist Peirce's more universal model of such games.
As I've said, a problem there is that it tends to conflate ordinary language games with mathematico-logical ones. And that is a very big problem in the social history of AP. It has been a bad turn in philosophical thought.
You want language games to stand for something epistemically generic. Yet you don't actually want to get forced too far from an ordinary language ontology. So your instinct for pragmatism lacks the semiotic machinery to cash itself out. It remains a vague gesture without the internal means to sustain a full theory as such. Therefore it has a considerable self-interest in decrying the very business of "having and arguing for an ultimate theory".
The self-interest at the heart of philosophical quietism is pretty transparent. ;)
Quoting Banno
Odd? Or empirical evidence that it qualifies as being better?
As a point of interest, note how the quietist likes to confuse regulative and constitutive principles.
Arbitrary human-invented rule-based systems like chess are a favourite as they clearly have the least metaphysical-strength necessity. A bishop travels the diagonal just because we agree to say so to get a game going.
And then - in sly conflation - the same is suggested of geometric truths.
If we say the world is flat - make that arbitrary constraint - then the three angles of a triangle sum to a rotation of exactly pi. But if we relax that rule about the world being flat, then - hey presto - we have a new game called non-Euclidean geometry.
And I guess now we are not supposed to stop and ask what further games lie beyond curved metrics? We should continue to treat the situation as being as arbitrary as a game as chess?
It is a transparent quietist gambit.
Quickly - whenever the anti-metaphysicist senses that the removal of constraints is arriving at some fundamental limit - s/he will switch attention to the possibility of instead adding constraints in arbitrary-feeling fashion. As we get too near the bedrock of what might be constitutive, there is a bait and switch so we find ourselves safely talking about the merely regulative again.
Hey, step away from that foundational vagueness! It can really mess with your mind. Step away from the abyss and think instead about all the arbitrary rules we can freely invent to create a metaphysics-free structure for our reality.
We can understand our world in simple terms like the bishop that moves on the diagonal simply because that is a convention of a language game.
So far as hands and chairs and capitals of France go, it doesn't do too bad a job.
Yes. That's rather the point.
If I say, "I am not certain that the chess expert knows what he's talking about?" - how is this different from "I doubt what the chess expert is telling me?" Expressing a doubt about X, in many cases is the same as saying, I'm not certain of X. There are also cases where one could replace the words "I know X..." with "I'm certain of X," and mean the same thing. However, there is a difference between an expression of certainty as an attitude, which might be expressed in the way one emphasizes words, or it might be expressed in the way one gesticulates. However, even the expression of an attitude of doubt in my chess example seems out of place.
Yes, I'm saying that in some contexts or situations there are not good reasons to doubt the expert's claims. I gave an example above, namely, when the chess expert is explaining the basic rules of chess. However, that doesn't mean that we can't find contexts or situations in which it would be meaningful to doubt the chess expert.
I don't agree that because it's possible that the expert could be wrong, that that in itself is sufficient reason to doubt the expert. The same is true when it comes to knowledge. I for example, could make the claim that I know my car will start, but it's certainly possible it might not. So because it's possible that I could be wrong, does it follow that I don't know it? Do knowledge claims require absolute epistemic certainty? No. The same is true with regard to doubting, just because it's possible that the expert could be wrong, that in itself doesn't give me good reasons to doubt the expert. What's possible does not give sufficient reason to doubt, or to make a knowledge claim.
I'm not saying you should be certain of something that isn't certain. The problem is that you're using the term certain in a way that requires absolute knowledge. You seem to think that one can reasonably doubt something even if we have a very high probability that we're certain, or that we know. I definitely would disagree with this. For example, would it be reasonable to doubt the car will start if there's a 99% chance that it will start? The answer is no. It would not be reasonable to doubt the car will start, especially based on the notion that it's possible it will not start.
Let's give another example, it's logically and ontologically possible that I'm the only mind in the universe, but does that possibility mean that I have good reason to conclude that I am the only mind in the universe, or to doubt that there are other minds? No.
And yes, I am using the term doubt different from how some are using it in this thread
I agree with this statement, but maybe not in the way you think.
Quoting Magnus Anderson
Wittgenstein isn't saying that Moore's propositions aren't true or false because they're analytic propositions. This is clear if you read the complete text of OC. He's saying that they're not true of false, or not knowledge claims, because these propositions hold a special place in our language.
I have a thread under Philosophy of Language, called A Wittgenstein Commentary that explains this in much more detail.
So to the extent that we neither have to question ourselves nor our worlds to any degree, commonsensicalism works fine as an epistemology?
It does appear that your philosophical ambitions are mightily limited.
Quoting Banno
Nope. The point was that there are constitutive principles as well as regulative ones. And that your game of always diverting the conversation away from the natural or necessary to the artificial or arbitrary is a transparent gambit.
This is not correct. "4" must necessarily refer to one unit. Each of the numerals, "2", "3", etc., refer to individual units. If "4" referred to four distinct units we would not be able to carry out the mathematical proceedings which we do. For instance, 4x1 would be 1x1x1x1x1 if "4" referred to four distinct units. Instead, "4" must refer to one unity, a unity with the value of four individuals.
Quoting PossibleAaran
You ought to doubt this, because the way you've described what "4" and what "2" means, is clearly incorrect.
Here is the issue which Banno needs to consider. We can know, and follow a rule without understanding that rule. It is only when we doubt the rule, and thereby analyze it for validity, that we actually come to understand it.
Quoting PossibleAaran
If you do not actually understand the rules which you are following, then you might misrepresent what is meant by the rules, as you misrepresented what is meant by "2", and "4", above. When we doubt the rule, we proceed toward understanding it.
Keep in mind how Wittgenstein defined certainty in On Certainty, as logically excluding the possibility of mistake. At this point it is implied that this is what is required to render doubt unreasonable.
He later waffles though, and defines certainty in a different way, such that if it doesn't make sense to doubt it, then it is certain. The bedrock is the fundamental things we agree on, and so it doesn't make sense to doubt them. However, agreement only makes doubt unreasonable for all those who agree. If there are others outside of this agreement, it may be reasonable for them to doubt it. So those bedrock propositions are not really beyond doubt.
I find the very term "language game" rather strange. It apparently means nothing other than "set of restrictions". Still, it bothers me that there are people who choose to call it "language game" instead of something simpler such as "set of rules". There must be some kind of strange process going on behind the scenes. I am not following what is popular, apparently. Certainly not Wittgenstein's train of thought.
I am looking into it. I have to say this is all very confusing. We have this weird guy who calls himself Moore and who wants to prove the existence of an external world and that by waiving his hands. And then we have these skeptics who question the existence of this same external world. What does that even mean? That's the first question we have to ask. But Moore skips this step and proceeds to counter the skepticism using a rather dull argument. And then Wittgenstein goes on to make a career out of this. Sorry if I can't take this stuff seriously. Fortunately for me, Banno isn't a moderator, so he can't ban me. The statement "there is an external world out there" must mean something specific so that we can test it and thus either verify or falsify it, and again, only to a degree. I can interpret it to mean "there is a world out there that is not under our control". This makes perfect sense. Lots of things that are not under our control. So it's pretty clear: there is an external world out there. But I am pretty sure these guys don't see it in this light, and in fact, I have a feeling they have no clue what they are talking about. Either that or we simply don't understand what they are talking about and we should first make an attempt to understand them before we proceed to dedicate an entire philosophy to them.
Wittgenstein, as far as I know, never defined certainty as logically excluding the possibility of a mistake. In OC 194 Wittgenstein asks, "But when is something objectively certain? When a mistake is not possible. But what kind of possibility is that? Mustn't mistake be logically excluded?" The answer to this question is seen in the way Wittgenstein deals with these questions throughout OC. There are propositions, bedrock propositions, and they are grounded in a way of acting, they are not grounded in some epistemic or psychological certainty (objective or subjective certainty). So when he is talking about a mistake being logically excluded, it's not in reference to knowledge or certainty, but in reference to his hinge-propositions, which are outside any epistemic considerations. In fact, doubt is something that is part and parcel to knowledge, which is why Moore's propositions aren't the kind one can know, and it follows that they're not the kind that one can doubt. The answer to his question is in the negative, and that is seen in the overall picture of what Wittgenstein is trying to accomplish.
Quoting Janus
Fascinating. I hope you are right about this. Could you tell me, what is it about doubting the veracity of memory that entails that all discussion (thought?) is meaningless?
Quoting Metaphysician Undercover
Note first that I didn't say that "4" refers to four distinct units. I said that 4 means four distinct units. It is usual to recognize a distinction between the intension of a word - what it is that I have in mind when I use the word - and the extension of the word - the thing or set of things that the word is used as a label for. Take the concepts of "having a heart" and "having a kidney". Everything that has a heart has a kidney and so the extension of the concepts is the same. But the intension of the words is clearly different, since what I have in mind when I say "I have a heart" is different from what I have in mind when I say "I have a kidney".
For all I know, it might be that the extension of "4" must be one unity with the value of 4. Or, to put it differently, it might be that "4" is the name of a platonic form, FOUR. That doesn't change the fact that when I say "4", what I have in mind is four distinct individuals. Literally, what I picture when I picture "4" is four distinct units.
Now, you say that if the intension of "4" were four distinct units, it would follow that 4x1 is 1x1x1x1 and you say this is objectionable. That just sounds like you don't understand what multiplication is. The intension of "4" is
I I I I
and we are saying that we want this many units, once. If we said 4x2, we would be saying we want this many units, twice:
I I I I I I I I
Hence I don't see the issue.
Quoting Magnus Anderson
I don't follow it either. He is enormously popular, but whenever I have interacted with an advocate of his views, they have begun by advocating something apparently novel, controversial and interesting and then after persistent questioning, it is revealed that they are really saying something trivial and uninteresting in some very pompous language - "language game" being one such example.
Reality itself is a kind of framework that allows us to act in certain ways, it is bedrock to a way of life. Language and language-games develop within this framework, which seems to indicate that what we come to know, what we are certain of, happens based on this framework. I'm allowed to form epistemological language-games because of the existence of the framework. Reality is the hinge upon which everything else swings. The certainty that is the result of the reality we find ourselves in, doesn't fit within our epistemology, but our epistemology is allowed to occur because of it. My subjective certainty which may be expressed by an attitude of certainty, does seem to reflect the feelings we have about Moorean propositions, a kind of sureness about his propositions, but it's not epistemic. "There is something universal here; not just something personal (OC 440)." It's this universality that makes it more than my subjective certainty, more than an attitude, that attitude is able to gain a foothold because of it. Just as objective certainty (knowledge) is able to gain a foothold because of it.
Wittgenstein says in OC 415 that "...certain propositions [I think the "propositions" is a poor descriptive term] underlie all questions and all thinking." It's this thinking that makes me think of Moorean propositions (bedrock propositions) as a kind of foundation. If we think of the foundation and the framework of a house, it is because of the framework and the foundation that life within the house occurs. It's foundational to all that occurs within. It's not part of the life that occurs within, but allows that life to occur - it is bedrock or foundational in an important sense.
For some reason this last paragraph shows up as italicized, but I have no idea why.
Right, this confirms what I said. Wittgenstein claims at 194 that objective certainty is when the possibility of mistake has been logically excluded. "When a mistake is not possible." "Mustn't mistake be logically excluded?"
Quoting Sam26
I think you demonstrate a misunderstanding of Wittgenstein here. Clearly, Wittgenstein associates objective certainty with when the possibility of mistake has been logically excluded. So for you to go on and say " when he is talking about a mistake being logically excluded, it's not in reference to knowledge or certainty, but in reference to his hinge-propositions", you completely misrepresent Wittgenstein. When the possibility of mistake has been logically excluded, this is objective certainty.
What is the case, is that at 203 he goes on to talk about "certainty" in relation to when an hypothesis is in "agreement", with the world of facts. We might say we are certain if we find it difficult to disagree. He continues to discuss this notion of "agreement", and by 270 he produces a new definition for "objective" certainty:
270. “I have compelling grounds for my certitude.” These grounds make the certitude objective.
This is what I meant when I said that Wittgenstein "waffles". First, he says that objective certainty is when the possibility of mistake has been logically excluded. Then he produces a compromised "objective certainty", notice how he refers to this as objective "certitude".
So, when you speak about the hinge-propositions, and how they are the grounds for certainty, what is really the case is that they are the grounds for this "objective certitude". Since the objective certitude is defined by "I have compelling grounds for my certitude", (the grounds being hinge-props), and not defined as "the possibility of mistake has been logically excluded", there is a substantial difference between "objective certainty" and "objective certitude".
We know that objective certainty would remove any rational doubt, because it would be irrational to doubt when the possibility of mistake has been logically excluded. However, the issue is with respect to objective certitude. Is it rational to doubt, even though I have compelling grounds for my certitude? I think that in our activities of daily life, it is not rational to doubt in any case that I have compelling grounds for my certitude, despite the fact that mistake is still possible. However, when we are seeking fundamental principles of epistemology, in which case we are seeking the highest level of certitude possible, it is rational to doubt until the compelling grounds for certitude reach the level of mistake having been logically excluded.
Sort of what I said? Why is this so? It's clear to me Moore's propositions are empirical. "Here's a hand" means "what I'm looking at right now is what is symbolized by the word 'hand'". This is either true or false.
Wittgenstein appears to be saying that Moore and skeptics are violating the rules of language. Who cares? The important thing is are they stating a belief, and if so, what is this belief and is it true?
The coherence of all discourse is predicated on our ability to remember what we and others have said in the past and from moment to moment. This is part of the general presupposition that what is past cannot change.
Such "compelling grounds" are ruled out by your game of faux radical doubt. This is chimera-chasing that demands absolute certainty which can never be reached and in the process of pretending throws out the realization that in its very activity it is still taking countless things for granted.
The point is that in the process of doubting X other things must remain beyond doubt. You cannot doubt everything at once. You can only create artificial imaginary contexts in which you could doubt specific things.
Yeah. It is difficult to see what is considered special about this as it seems simply another restatement of pragmatist, or social constructionist, approaches to truth.
But at heart, it seems to be driven by a particular philosophical disappointment. AP had the hope that a mathematical kind of mapping relation would apply to language use. The meaning of our words would not be some free act of interpretation - an inductive connection - but instead a rigid act of designation, or deductive kind of connection.
So ordinary language, which seems sloppy, allusive, often ungrammatical and even paradoxical, would be shown to have a tight mathematical-strength logical structure as the sturdy skeleton supporting its spongy flesh. It should thus be possible to speak with complete and unambiguous precision.
But language does not represent meaning in this kind of simple, dyadic, mapping fashion. Talk about language games and ways of life then become an examination of how we actually use language. And that leads towards a more complex triadic relation which involves a “self” in a sign relation with a “world”. Words are used to achieve purposes. And so to the degree that purposes are purposes we have in common as communities, meanings seem easy to share. Yet also, we all have more personal purposes, and so there grows that which can’t be so easily and closely shared.
All this can seem like a game, a social game, as it makes meaning a matter of subtle negotiations. We are always engaged in interactions where the personal and the communal are in tension. So every sentence spoken and offered up for creative interpretation could be pulled either way.
There are no grounding rules as such. Or none that anyone must stick to in some ultimate way. But there are general constraints at work - a deep structure of developed communal habit, like a well worn forest path - that we can detect and respond to in terms of our own agendas. We can either decide to stick as closely as possible to an inductive sense of the “standard meaning” as we can, or instead play the other game of stretching the interpretation creatively in the direction of our own interest or advantage.
All this free play in the works completely destroys the hope of finding some inner skeleton of rigid and truth preserving connections in speech acts or propositional-sounding language. But on the other hand, language still works marvellously. It has an organic flexibility that is quite unlike the brittleness and mechanicalness of a rigid mapping operation - a computational kind of relation. And the secrets of that organicism are a pretty huge and important philosophical subject to explore.
Sadly, all those who are fixated on Wittgenstein seem caught up in the tragedy that was AP’s great failed dream. They only want to talk about what turned out not to work for them, and so the complete abandonment of any grand projects.
Meanwhile largely unnoticed, there always was the organicism project taking shape in the background. CS Peirce in particular had laid out a triadic semiotic which gets at the true deep structure of what is going on.
It's not that you don't have to, its that you can't, doubt everything at once, which makes it misleading to say that everything may be doubted. You should be saying that anything may be doubted; which still leaves the question as to whether any particular doubt is genuine and reasonable, as opposed to artificial and unreasonable.
I'm just a grumpy old bastard.
But it is interesting to see your thinking progress. I suspect you would agree with much that Wittgenstein says - as i mentioned earlier.
So, what should one doubt? It's a question worth asking.
You appear to think that there is a universal set of rules that everyone must adhere to. There isn't such a thing. Anyone can do whatever they want. What I can do is I can explain to you how my type of organism functions. But I am not motivated to do so. Another thing we can do is we can explore all the different manners in which organisms that inhabit the environment within which we live operate e.g. we can observe how they behave and based on that develop various models of thinking. But I am not motivated to do so. Not at this point in time. Other than that, there is nothing we can do. We cannot ask questions such as "what one SHOULD do?" because all behavior is fundamentally irrational. It's a relative thing. You must first choose a goal in order for such a question to make sense and when you do so you are no longer asking a general question, but instead, you are asking a specific question that only applies to organisms that posit the goal we chose for our discussion.
So no normative constraints should apply to intellectual discourse; we can all just assert whatever we want? Sounds like a recipe for fun (if you like that kind of senseless chaos) and/or disaster (like it or not).
Gravity and such, perhaps; but otherwise, no.
Quoting Magnus Anderson
But that's not right. There are all sorts of things that we can't do - walk through walls, Fly like superman, play guitar well without practicing... It's a long list.
Quoting Magnus Anderson
Exactly. So, what are your goals?
Integrity, if you like.
Same goes for the things we do.
When it comes to intellectual discourse the rules of consistency (non-contradiction) and coherency must apply else discourse fails. Someone who says we can doubt anything would say that we can doubt even these principles; but that would be a performative contradiction.
Edit; I see you posted something similar above while I was composing my response. 8-)
Gravity isn't a universal rule. There is no such a thing as a universal rule. There are temporary rules and among them there are rules that exist for a long period of time and rules that exist for a short period of time.
Quoting Banno
Anyone can do whatever they want provided that they can do it. Do I have to say that? I think it's a given.
We ask "should" questions precisely because we have a degree of freedom in deciding how we're going to act. That does not mean we can do anything we want. Freedom has limits. When I say "one can do anything one wants" I am saying "anyone can do anything one wants within the limits of their freedom".
I can see how Wittgenstein would look odd from your point of view. "Language game" gained such notoriety in the eighties ad nineties that it became almost useless. In the Investigations it starts as a term for simple mind games such as counting apples and stacking blocks. The import was that such things do not consist only of words, but are integral to things we actually do in the world. This was Wittgenstein's reaction against those who saw language as somehow independent of our actions. The meaning of a term ceases to be some abstract entity and becomes the use to which we put that terms. It was part of an admonishment for philosophers to look to the way we actually do things rather than sit around and make things up.
It would be agreeable to think of language games as a group of actions and their associated set of rules. It's more than just the rules.
That's not what I said. We can discuss all sorts of imaginary scenarios if you want to. We can talk about the life of a psychopath and the kind of decisions he should make if he wants to fully express his way of life. Or we can talk about us, our own ways of life, if that's what you prefer. The problem is I have no interest in these things. Alright? What I am attacking here in this thread is this idea that there are propositions (or more precisely, assumptions) that are beyond doubt. Wittgenstein's claim is that there are propositions that lie beyond questions of knowledge and doubt. That's my interest. You can discuss all the different patterns of doubting and you can discuss whether it is a good or a bad decision to doubt within a specific situation within some framework, you can do any of these things if you want, but that's not what I want to do. All I am saying in this thread is that the universe does not necessarily follow some set of rules that we came up with or any rules at all.
There's no point in arguing for coherence and consistency. If someone does not take it as a given, the best thing is probably to walk away.
But the fact that Magnus is presenting well-crafted thoughts shows that although he(?) might say we can do anything, he has a preference for coherence and consistency, too.
To know the answer to Wittgenstein's question, "Mustn't mistake be logically excluded?" is "No," is to think about not only what he said here, but what he said elsewhere. However, there are a couple of important points to be made. First, there are two kinds of statements involved when considering this quote. Moore's statement, which isn't according to Wittgenstein an epistemological statement (although Moore thinks it is), hence in this context, that is, Moore's context, a mistake is ruled out. It's ruled out because Wittgenstein is saying that Moore's statements aren't the kind of statements we generally doubt. Thus, not only are these statements not a matter of knowledge, but they're outside the purview of doubt, which works alongside knowing.
Moore puts his propositions in the arena of knowledge, and it's in this arena that doubts can arise. What does this mean? It means that if you claim to have knowledge, it must be demonstrated that you do indeed have it, that is, objectively demonstrated (OC 14). What's the purpose of objectively demonstrating that one does know what one claims to know. It's to assure those of us who hear your claim, that there's no reason to doubt your claim. When we see your reasons or evidence it is supposed to alleviate the doubt. Once I too see that you have objectively demonstrated your knowledge, then the claim is validated, and the doubt is alleviated. However, if I don't agree with your assessment, then the doubt about your claim to knowledge remains. One must show that a mistake hasn't been made in your reasoning.
Remember that Moore is demonstrating his knowledge to the skeptic, and as such, he is allowing the doubt in the door. The skeptic wants to know how it is that Moore knows (hence, the doubt)? Wittgenstein is saying that both are incorrect in Moore's context, because the statements Moore is making are not epistemological, that is, there is something different about these statements. It's not only the case that Moore is in error, but the skeptic is also in error. Why? Because of the nature of these kinds of statements or hinge-propositions. The language-game of knowing and doubting are inappropriate when using them in Moorean contexts.
Now note that in OC 194 Wittgenstein's question is about objective certainty, and as such, when he asks about a mistake being logically excluded, the answer to his question is no, and we know this by looking at his assessment of Moore's propositions. Surely one's doubt isn't dismissed simply by someone telling you that one knows X. My claim to knowledge isn't a guarantee that I know, which is why we want to know how it is that you know, thus the doubt.
It's what is known as "ontology" in AI, isn't it? I don't like that term either. Very strange. But I understand that it's basically just a bounded possibility space. When I say "rules" I mean the limits of what is possible such as "the chess board is made up of 64 positions aligned in a 8x8 grid" instead of "there is an infinite number of positions on a chess board". Also things such as "the rook can only move to an adjacent position in one of the four directions: left, right, up and down" instead of "the rook can move to any position on the chess board". Boundaries narrow the possibility space. They make it simple. And yes, when you limit the possibility space, certain things become impossible and thus immune to doubt. If we say that the chess board is made up of squares aligned in a 8x8 grid it is impossible for a chess piece to be on a position outside of this 8x8 grid (such as i9 square.) But it is better to say that it is illegal for a piece to be on a position outside of this 8x8 grid because it is nonetheless possible for a piece to occupy i9 square. Yes, that would no longer be the game of chess, but it is nonetheless possible.
Not meaningless but simply difficult to understand. If I am not speaking in a language that is familiar to you, does that mean that what I am saying is meaningless? Not necessarily.
Quoting Sam26
The infinite regress problem arises when people start asking for an infinite number of explanations on how you know what you know. The problem arises as a conflict between your desire to answer every single one of their questions and your other desires (such as the desire to do something else in your life other than to justify yourself.) The problem is solved by simply ignoring their questions and objections.
The problem also arises when you think that your beliefs must be "beyond any kind of doubt" in order to accept them. In such a case, the problem is solved by understanding that your beliefs do not have to be "beyond any kind of doubt". The problem is NOT solved by deceiving yourself into thinking that there are beliefs that are beyond doubt (classical dogmatism) or that there are beliefs that are neither true nor false and thus not subject to skeptical scrutiny (Wittgenstein's position.)
Exactly. The ground has moved; we are no longer playing chess.
Right, the infinite regress is about justifications. For example, how do you know X is true, because of A, B, and C. How do you know A, B, and C are true, because of D, E, and F, and so on; but my theory ends with statements or propositions that are outside of any epistemic considerations. I don't think this would solve all infinite regress problems, but some, or many.
The problem is solved in realising that there is a way of understanding a rule that is not given by another rule, but in actually following the rule in what one does.
That's Wittgenstein again; I'm using him heaps here.
The regress is caused by an over-reliance on words for explanation. Telling me you can add two and two does not show that you can add two and two. The proof is in the act.
I have yet to understand your position fully but my current impression is that this isn't the right solution. The right solution is to understand that you do not need to justify yourself "all the way down".
Quoting Banno
People want to know why you choose X instead of Y. For example, they want to know why you believe the Sun will rise tomorrow instead of believing the Sun will not rise tomorrow. They want to know what causes you to choose X instead of choosing Y. Really, what they are looking for is a correlation between some event or some set of events in the past and your choice of X. If there is no such a correlation then that means that your choice is arbitrary; it means it's irrational.
Now, when you say there are rules that are not given by other rules, what you are saying is that there are choices that are arbitrary or irrational i.e. that there are choices that are not caused by some other events (such as some other choices.) Does this make sense? To make things worse, you can never be absolutely sure that a choice is irrational. It might be the case that you are simply unaware of the causes of your beliefs.
You can say "the rook can't move diagonally". I can ask "why?" and you can answer "because that's the rule of the game" I can then ask "why is that the rule of the game? why not something else?" and then what do you answer? because you chose so? you chose that the rook can't move diagonally? I ask "why did you choose so?" and you say "I chose it randomly". "Well, then", I can say, "I can choose equally randomly that the rock can move diagonally". And you're fucked.
I'm going to be pedantic again; I didn't say this, and for me it is important.
I said that there is a way of understanding a rule that is not given by other rules, but shown in the implementation.
Quoting Magnus Anderson
Yes! That's what both Sam and I are saying!
But you are saying there are bedrock propositions that are not subject to skeptical scrutiny. I am not saying say so. It appears that you believe there is such a thing as "down". So you really want to go "all the way down". You are merely claiming that there is a point beyond which it no longer makes sense to go "down". I say that the process of going down is infinite, it has no end, so you can't go all the way down. You can go more and more down but not all the way down.
And for me this bring us to the main purpose of this particular thread, which was started by Sam proposing a theory about the nature of hinge propositions. His idea is that there are some propositions that we are caused to believe.
SO, roughly speaking, we might have three reasonable places to stop the regress.
One might be things we are cause to take as indubitable - Sam, from the OP.
Another might be constitutive rules, which might be doubted outside the game they help constitute.
A third might be propositions that are shown, such as "here is a hand".
Now for me the topic of this thread is the prose and cons of each, and what we might add.
1) The first is too strong. Even an axiomatic or grounding supposition needs to be doubtable to be believable. It has to be framed in a way that has an explicit contradictory - a counterfactual axiom - to even have any explanatory bite and not merely get classed with the set of propositions that are “not even wrong”.
So of course we choose axioms on the grounds of being the least doubtable. That is how they can be the most believable. But the fact that the whole business is founded in this counterfactual game means that the necessity is more about the necessity of just making some abductive leap. We can always circle back to have another go at the axiomatic basis if the results of the axiomatic system don't seem to be working out so well ... on pragmatic or empirical grounds.
2) The second is right in emphasising the need to just make some rule to get a game of inquiry going. Even a bad guess is a good guess so long as it is a definite guess - one that is crisply counterfactual in its framing.
But what we need to avoid is the suggestion that the game is arbitrary. The game is going to be judged in terms of the purpose it accomplishes. So there is that global constraint, the empirically-grounded one, that feeds back to say something about the quality of the grounding axiomatic choices.
And also, more needs to be said about the epistemology of abduction. Peirce already made the mathematical argument that the history of the universe is not long enough for humans to have made even a few right basic guesses at random. So we need an explanation for why our guesses tend to be rather good. And the reason is a non-linearity, as illustrated by the exponential ability to discard alternatives in the classic 20 questions game. If we can cut the total number of possibilities in half at every step, not just knock them off one by one, then it is much less of a surprise that we can employ a dialectical logic to generate our metaphysical axioms.
We arrive at constitutive rules via dichotomies for a good reason. Non-linear search beats linear search by a country mile^2. ;)
3) The third is the baffling one. It seems like an attempt to be empirical. It claims - in pointing to something particular - to demonstrate the existence of some grounding or backdrop context.
But while that background of belief exists, it would be better just to point to it directly. Everyone of course can see by your actions that you presume a certain dichotomy of self and world to be basic. But better to say that directly - put it verbally on the table for forensic examination - rather than try to get away with some ostensive demonstration.
It feels always too much like an attempt to evade real debate than to answer the sceptic. To grunt and point ain't ever as good as presenting a proper epistemic theory.
So yes. There must be some general ground of belief that then makes all further doubts crisply local and particular. That is standard pragmatism, and standard psychology. Without an established set of habits, we could never do anything that actually counted as creatively novel.
But flapping your hands about and appealing to the strength of some established communal belief shared by an audience just seems a bad faith attempt to dodge the serious epistemic questions at stake.
Quoting Janus
Like I said, in my daily endeavours I accept such things without a doubt. But since we're discussing fundamental principles of epistemology here, I see no reason why we ought to settle for anything other than a quest for real objective certainty (in the sense where the possibility of mistake is excluded). This means that as an epistemological principle, anything less than that which gives us real objective certainty ought to be doubted. If your argument is that nothing gives us objective certainty, therefore everything within epistemology would be doubted, then that's the way epistemology ought to be. I see no problem with believing that every fundamental principle of epistemology ought to be subjected to doubt. This could only improve certainty.
If you want to settle for less, saying that we ought to just take things for granted, and not doubt them because they appear to be correct, then that's your opinion. But I don't think your opinion will be acceptable to very many serious epistemologists.
Quoting Sam26
This is not true. Wittgenstein does not answer this question with "No". It is very clearly implied that the answer here is "Yes". And that's why he replaces "objective certainty" with "objective certitude" at 270. If the answer were "No" he wouldn't need to replace "certainty" with "certitude". It is only because the answer is yes that he is forced to seek something other than "certainty", and that is "certitude".
Moore's proposition, as well as any other proposed hinge propositions fulfill the conditions of "objective certitude", but they do not fulfill the conditions of "objective certainty". If you do not recognize this distinction then I think you are deficient in your interpretation of Wittgenstein, by not recognizing his use of these two distinct words.
In the vast majority of circumstances,, "objective certitude" relinquishes any need for doubt. But as dedicated epistemologists it is our due diligence to call for an investigation of (doubt) any proposition which does not obtain "objective certainty".
What does it mean that we are caused to believe some propositions? I very much notice the emphasis on the word "caused". What's so special about it?
Is it related to the following passage?
Quoting Sam26
I don't understand the distinction he's making between "causal basis of beliefs" and "rational basis of beliefs [beliefs based on reasoning]".
He also says that reasoning is a linguistic endeavor and I disagree with that. Language merely represents the process of reasoning in a manner that is useful for the purpose of communication. But then he says "at least as how it is defined here" which makes me wonder what he really means by reasoning.
Why do you think I am so fond of Popper? Popper wanted to pursue truth for its own sake. He had a problem with the idea that some of us, not daring to suggest most of us, pursue truth in order to better secure the attainment of our goals (whatever they are.) He was also a staunch opponent of verification which I think was excessive. What we have common, if there is anything we have in common, is the idea that absolute truth is unattainable; that truth can only be approached or approximated. But then, that's what other philosophers, such as Nietzsche and Mach, thought as well, and that long before he was even born. And what about Hume? We are not going to mention him at all.
All in all, I agree with the stance that our foundations need only to be strong enough so that whatever is built on top of them can be stable. However, Sam's exposition sounds far more complicated than that and that suggests to me that he has something else on the menu.
Banno's notion of belief as explanations for behaviour cannot do this. Our explanation results in Jack's belief. Jack's belief is then - meaningless to him.
Carry on...
I've been quite busy, but this is a great thread...
Cheers again Sam...
Quoting Magnus Anderson
Irony, lost. No offence meant.
Quoting Magnus Anderson
And what of just plain old truth?
Perhaps talk of absolute truth lead philosophers astray, so that they threw out good old plain ordinary truth along with absolute truth.
So folk like Apo get stuck not being able to say that it is true that Paris is the capital of France and so on.
Any explanation would be meaningless to Jack. That does not make the explanation wrong.
No - it's just pointing to a hand.
Quoting creativesoul
Going to the food bowl is meaningful to him; and not as head-furniture, but as a way of living - meaning as use.
We all know that's wrong.
Actually, it seems to me to be that folk reify belief; they think a report of belief must be a report about a thing.
Folk assume that because Jack believes his bowl is empty there must be an empty-bowl shaped thing in his mind. But all there is, is empty bow, go meow at Banno and try to trip him and generally annoy him until full bowl. A series of actions.
This is one of the most absurd things I've ever read.
Your explanation of my belief is not equivalent to my belief. The same holds good of Jack.
Sure, plain old truth is attainable and there is nothing wrong with saying that it is true that Paris is the capital of France.
It's "your explanation of my behaviour".
Cheers Banno!
X-)
I believe we ought be respectful of other beasties. But I am roasting a chook (chicken, for you foreigners) despite that.
My conclusions about prelinguistic beliefs are that some are causal in nature and some are not, and I explained the difference in another post. The point though is that these beliefs form a kind of world picture for us. So that I have two hands is a world picture belief, and is demonstrated in our actions apart from propositions/statements, and is also demonstrated in our use of propositions/statements.
Quoting Metaphysician Undercover
When he talks about objective certainty and objective certitude, it's basically the same thing. Both are epistemic in nature, and certitude is a synonym of certainty, so what are you talking about? Why do you think they are two different words? There can be a slight difference, but when used in terms of objective certainty or objective certitude as Wittgenstein is using it in this quote, and in the quotes that follow 270, there is very little or no difference. So again my argument stands.
MU much of what I'm saying isn't just my interpretation, but what other philosophers familiar with Wittgenstein's On Certainty are saying. Now that in itself doesn't make it right, but it sure lends support to this interpretation. On the other hand, I have read nothing in support of your interpretation, and if there is writing that supports your interpretation, please share it with us, because I for one would love to read it.
At some point I just stop engaging with certain people (MU for e.g.), because I don't see that we agree on much, even the use of certain words, e.g., the post above (objective certainty and objective certitude). There has to be some basis for agreement, otherwise it seems pointless. So I just keep posting for those who are reading the thread and are not necessarily responding.
Quoting Sam26
Yes. Odd that this should take prominence.
Get some sleep.
Quoting Sam26
I've explained this to you already in this thread, but I'll explain it again. To doubt is to request justification. Knowledge requires justification. Bedrock propositions as you describe them, are not justified, therefore they are not knowledge. In order that it may be accepted as part of a body of knowledge, any proposed bedrock proposition requires justification, therefore it must be doubted. If it is not doubted, (and consequently justified), it remains outside the body of knowledge and cannot serve as a fundamental proposition.
Quoting Sam26
Again, that 's clearly not true. Look at the difference between where he describes objective certainty at 194: "But when is something objectively certain? When a mistake is not possible." and where he describes objective certitude at 270: “I have compelling grounds for my certitude.” These grounds make the certitude objective."
Your claim that "when a mistake is not possible" means the same thing as "I have compelling grounds for my certitude" for Wittgenstein is clearly untenable. What has actually happened in "On Certainty" is that Wittgenstein started out with the intent of seeking the highest degree of certainty, (when a mistake is not possible), to provide an approach to the skeptic's doubt. However, he realized that such a certainty, "objective certainty" cannot be ascertained in any practical way. So he settles on a different type of "objectivity", one which allows him to say that "my certitude" is objective.
There's a substantial difference here:
True objective certainty, "it is certain", which Wittgenstein recognizes as "mistake is not possible", is attributed to the object, "it" is certain. True objective certainty represents the facts, the way it is. Whether or not any human beings know the way that it is, there is a way that it is, and this is represented by "it is certain that...", where mistake is completely impossible, because "..." represents the way that it is.
On the other hand, when my certitude is "objective", the certitude is a property of me, a subject. So we are now saying that I, the subject have a property which is objective, and this is my certitude. What makes this certitude objective is that it is grounded in the bedrock of inter-subjectivity. Now we have an objectivity that is not based in the object, which was the case with "it is certain that...", it is based in an inter-subjectivity, "we are certain that...".
As reference, consider the difference between how Wittgenstein uses "certain" at 175-200, and then after 200.
Between 175 and 200 he is discussing what it means for a proposition to be certain. At 178 he uses "It is so". Between 183 and 184 he uses "It is certain that". After 200 he switches his focus toward what does it mean if I am certain. At 230 he is asking what gives me certainty? At 242, "Mustn’t we say at every turn: 'I believe this with certainty'?" At 246 he is asking what does it mean if I am completely convinced. And this is where he talks about bedrock, and then produces objective certitude at 270. At 273 he asks "What qualifies as "objectively certain"?", and answers "There are countless general empirical propositions that count as certain for us."
Notice, he has switched from objective certainty, "it is certain", prior to 200, to "objectively certain", "certain to us", after 270.
My argument is that when something is objectively certain, "certain to us", it is unreasonable for us to doubt this, as it is unreasonable to doubt that which one is certain of. However, the "us" referred to here, is never absolutely inclusive, there are always those who are outside the "us". For those outside the "us", the propositions which are certain to us, are not certain. For these people, it is reasonable to doubt those propositions and ask for justification. Furthermore, it is unreasonable for "us" to insist, to those who doubt these propositions, that it is unreasonable to doubt them. It is unreasonable for "us" to do this because it is just an excuse, a tactic to avoid having to justify these propositions.
He wouldn't know he is only hallucinating? Then is he doubting or not?
I just said previously, You are the one making this observation about him. What is his observation?
But that's not really the issue, is it. Yes, of course, it is impressive that we seem to find it pretty easy to deal with everyday "truth". Agreeing on the facts is simply about mastering the right social habits.
So where philosophy begins is when we want to move on to an epistemic theory that itself is "true", or at offers an analysis of the best way to go about things. This is basic to moving away from the everyday socially-constructed forms of knowledge and establishing an epistemic method that can be extended way beyond into the realms of the metaphysical even.
The search for that ideal epistemic method is hard and ongoing. But we can see that it has largely cashed out as pragmatism and the scientific method of reasoning. And philosophy as a training aims to foster the critical thinking skills which are involved in applying that epistemology.
So you can continue with your anti-metaphysical griping. It counts for nothing. Metaphysics is alive and well. In scientific circles anyway. :)
The correct employment of doubts (and beliefs) is an issue. But just as obvious is that most folk have no trouble distinguishing between the everyday socially constructed truths (like Paris being the name given to a city that has also been designated a nation's capital) from the philosophical issues surrounding epistemology itself.
In conflating the everyday with the deeper story, you not only show a failure in critical thinking, you also wind up excluding what is actually fun and interesting about metaphysical level inquiry. And that makes for a dull life, wouldn't you say?
:) Good man. But do get some rest! Sorry I'm busy so am having to dip in and out of paying attention.
Notions of absolute truth were laid to rest at the start of last century, with Moore and Russell's criticism of Absolute Idealism. The world is too complex for one Grand Scheme to provide us with The Truth. The notion that pragmatism holds all the answers is a romantic infatuation, as is the "search for that ideal epistemic method". Such Grand Schemes are never broad enough to encompass everything; they only give that illusion by reducing everything to their own terms.
Pragmatism says nothing of the truth of love, beauty, courage, respect. It is a philosophical sideline.
"Proposition" is probably a bad choice of term in this connection. But what am I to think of you if refuse to acknowledge that you have hands, if you claim to genuinely doubt that, and yet continue to type your responses on your keyboard? Do you really want to claim that I should take you seriously?
Also, you have not addressed the distinction between being able to doubt any particular thing (although even that is questionable) and being able to doubt everything at once.
Grayling, in an essay entitled Wittgenstein on scepticism and certainty, juxtaposes what he suggests are two conflicting arguments in On Certainty. The first, which he refers to as OC1, is found in the sort of refutation of scepticism with the foundationalist arguments found in this thread. The second, OC2, is the relativist claim that truths are dependent on history, language, perspective and so on.
Grayling sees the resolution of the tension between these two views as the the unfinished task of OC. In this, I agree with him.
Grayling proceeds to see the relativist off with reference to Davidson's anti-relativist arguments, and again I am in agreement with him.
Are we left with truths within frameworks, each of which can be interpreted in terms of the other?
65. When language-games change, then there is a change in concepts, and with the concepts the meanings of words change.
95. The propositions describing this world-picture might be part of a kind of mythology. And their role is like that of rules of a game; and the game can be learned purely practically, without learning any explicit rules.
97. The mythology may change back into a state of flux, the river-bed of thoughts may shift. But I distinguish between the movement of the waters on the river-bed and the shift of the bed itself; though there is not a sharp division of the one from the other.
99. And the bank of that river consists partly of hard rock, subject to no alteration or only to an imperceptible one, partly of sand, which now in one place now in another gets washed away, or deposited.
164. Doesn't testing come to an end?
165. One child might say to another: "I know that the earth is already hundred of years old" and that would mean: I have learnt it.
166. The difficulty is to realize the groundlessness of our believing.
255. Doubting has certain characteristic manifestations, but they are only characteristic of it in particular circumstances. If someone said that he doubted the existence of his hands, kept looking at them from all sides, tried to make sure it wasn't 'all done by mirrors', etc., we should not be sure whether we ought to call this doubting. We might describe his way of behaving as like the behaviour of doubt, but this game would be not be ours.
256. On the other hand a language-game does change with time.
257. If someone said to me that he doubted whether he had a body I should take him to be a half-wit. But I shouldn't know what it would mean to try to convince him that he had one. And if I had said something, and that had removed his doubt, I should not know how or why.
336. But what men consider reasonable or unreasonable alters. At certain periods men find reasonable what at other periods they found unreasonable. And vice-versa.? But is there no objective character here?? Very intelligent and well-educated people believe in the story of creation in the Bible, while others hold it as proven false, and the grounds of the latter are well known to the former.
337. One cannot make experiments if there are not some things that one does not doubt. But that does not mean that one takes certain presuppositions on trust. When I write a letter and post it, I take it for granted that it will arrive - I expect this. ?If I make an experiment I do not doubt the existence of the apparatus before my eyes. I have plenty of doubts, but not that. If I do a calculation I believe, without any doubts, that the figures on the paper aren't switching of their own accord, and I also trust my memory the whole time, and trust it without any reservation. The certainty here is the same as that of my never having been on the moon.
By "foundationalist arguments" are you referring to Moorean types of 'arguments' or something else?
It would seem that we are left with "truths within (translational) frameworks". I think a distinction needs to be maintained between the idea that truth is dependent on "history langauge, perpective..." and the idea that expressions of truth are so dependent.
Hah. Well there is certainly still something in Hegelianism. But it took Peirce to make the case that there is no direct correspondence between the reasoning subject and the objective world. The mediation of the relation by signs pretty much ensures that there isn't - as the comprehending self and its comprehended world arise separately from the world in itself.
So what you are expressing here is some personal prejudice about what have been the twists and turns in the development of epistemology. Moore and Russell hardly ended anything. They were already blundering into logical atomism.
Quoting Banno
Oh dear. Again that may be your impression, but after checking out the great variety of epistemologies on offer, I am repeatedly surprised by what a robust scheme Peirce arrived at.
So you have your view. I have mine. The difference is mostly that I am prepared to supply the arguments and evidence for mine. You instead have adopted the easy position of the arch-sceptic. You can just keep saying "I doubt that very much".
You even seem proud that you won't even read anything about Peirce when it is offered. It's a funny attitude to encounter. But variety is what I enjoy.
Quoting Banno
Hmm. But pragmatism done properly speaks directly to the values of the "self" that is doing the philosophising. I keep point that out to you. It puts the other side of things - the self that hopes to discover itself in its world - in the limelight.
Of course, this is a fundamentally anti-Romantic and anti-Transcendental enterprised. A lot of folk - you too apparently - don't like that mystical side of life being called into question and treated as a scientific inquiry.
Yes. I can see how it might seem to threaten Philosophy. Science has taken over metaphysics pretty much entirely, and now it is back for the rest. :)
But to me, that is what progress looks like. And I'm always willing to make the argument in full. I don't need to hide behind ambiguous non sequiturs and one liners.
I think I have to state this in order to clarify my position. I do not refuse to acknowlede that I have hands. I do have hands. I don't doubt that. What I am saying is that the reason I don't doubt that statement is not because it is impossible or non-sensical to doubt such a statement but because I choose, for one reason or another, not to do so.
You appear to be arguing that it makes no sense to doubt our memories. I don't understand that. You think it's impossible for us to wake up one day and realize that we've been dreaming all along?
Again, I share @Banno's sentiment that we should not take such possibilities seriously. It's possible that I am a centaur who's dreaming of being a human but that does not mean that I should take such a possibility seriously. I personally don't. I think I am a human and that I will remain so for the rest of my life.
Quite so. Truth is not one thing - indeed, it varies from case to case, as is demonstrated by the T-sentence.
Special Relativity has a strong metaphorical role here. What is true in one frame of reference may not be true in another - except that the mathematical transformations developed by Einstein permit what we might call a translation from one frame of reference to another. Using that translation, the frames of reference are found not to contradict one another.
This is quite close to Davidson's argument agains relativism. What is true is what is the case under translation in both frames of reference.
While non impossible, it is, I submit, nonsensical to doubt that you have hands while you are engaged in typing.
OR can you provide a sensible account of how tis might come about?
Indeed, as you were so forthcoming when asked if it is true that Paris is the capital of France.
My point is that you can question your memory. For example, I remember the sensation of my fingers hitting the keys on my keyboard just a few moments ago. My point is that this memory can be questioned. Perhaps no such experience took place. Perhaps there is nothing but an imagination of such an experience. That's all I am saying.
I haven't seen any argument from you as to how it could be reasonable to doubt that I have hands, or why, just because someone (who, for the sake of the argument, is not deranged) could always say they doubted the existence of their hands, I should believe that the person genuinely doubted that.
As to doubting our memories, of course individual memories may be more or less subject to doubt; my point is that memory as a whole faculty cannot be coherently doubted.
I also agree with what you say about taking such possibilities seriously. Really, that is the whole point. I guess where we disagree is that you seem to believe that otherwise reasonable people are capable of genuinely doubting the kinds of things we have been discussing (which would mean taking such possibilities seriously) whereas I see no reason to believe that they are any more capable of doing that than I am.
That's a little lame when you wouldn't give a definition of what "truth" might be taken to mean in your view.
I agreed it might be tautologically true according to some social convention. And I pointed out how inadequate such a definition of "true" might be in any sensible debate about realism - as might hinge on Prof Moore and his flapping hands.
But as usual, when faced with an actual argument, you went radio silent for a while. And now re-emerge clinging onto this as some unanswered winning remark you might have made.
You can always go back and address my actual replies. But I know you won't. It's all impression management as usual.
"P" is true IFF P.
That's as close as can be got, and I have said it to the point of tedium.
Apo, a reminder that you are a sideshow here. This is a thread about On Certainty, not about Pragmatism.
You did not answer the question. If you did, provide links.
Let's make it simple. If you agree that it is possible that our memories can turn out to be wrong, we are on the same page. Because that's all I am saying.
It seems we do agree then. :)
And to the point of tedium, you won't discuss the informal acts of measurement that are needed to show such truth in practice. So same old same old. You leave out the "self" that is needed to give propositions any grounding purpose and any natural limits to their concerns about errors, exceptions or doubts.
And of course, that extra stuff is central to making sense of such different classes of proposition as Paris is the capital of France, and here is one hand, here is the other.
It appears to me that you are an honest correspondent; I appreciate that. You manage to hold your own without resorting to insults, veiled or otherwise. And I see growth in your thinking; or at the least, a willingness to let the conversation grow of its own accord rather than lead it down your own particular path.
Do you have a copy of "On Certainty"?
You do now.
So let's take a more useful example to flush out what you could possibly mean by epistemic justification.
"God created the earth and mankind, the Big Bang never happened" is true IFF God created the earth and mankind, the Big Bang never happened.
Fine. In the most question-begging way conceivable, we have set out a truth condition.
But now how would you go about cashing that proposition out? If you claim to be interested in epistemology, then start doing some.
We have two convinced schools of thought - the creationists and the cosmologists. How does "Paris is the capital of France" as your prototypical example of commonsensical truth apply in sorting out how doubt and belief ought now to proceed here.
If you were actually saying anything helpful in pushing that example, its usefulness will be made clear in your very next post.
Notice that you are not asking if it is true, but if it should be believed - what justification it has.
That's the trouble with pragmatism. It does not address questions of truth. It pretends they are all questions of justification.
That's why you are not able to agree that it is true that Paris is the capital of France.
Way fun! 8-)
That's true.
But can you explain to me what the difference actually is as far as you are concerned.
Of course, pragmatism doesn't actually pretend its all just justified belief. Just like it doesn't deny the world exists in some fashion that is separate from our desires and conceptions. So it certainly addresses the question of truth head on and gives its pragmatic answer. But again, the stage is yours. Tell us what the critical difference is here, using the example supplied.
To remind, "God created the earth and mankind, the Big Bang never happened" is true IFF God created the earth and mankind, the Big Bang never happened.
So who speaks the truth here, and in what way is that so?
"My exegetical task is effected by suitably anatomising OC. The view I shall call OC1 and which constitutes a version of a foundationalist refutation of scepticism, and therefore a contribution to the theory of knowledge, has two components, the first of which is that scepticism is answered by appeal to the fact that beliefs inhere in a system, and the second of which is that this system of beliefs rests on foundations which give those beliefs their content. Here are some passages exemplifying the first component of OC1 (all emphases are Wittgenstein's):"
and OC 2 by Grayling:
"OC2 is relativism. Relativism is the view that truth and knowledge are not absolute or invariable, but dependent upon viewpoint, circumstances or historical conditions. What is true for me might not be true for you; what counts as knowledge from one viewpoint might not do so from another; what is true at one time is false at another. Paragraph 97 arguably shows that the relativism implicit in this aspect of OC is of a classic or standard type. Its presence in OC is entirely consistent with its presence elsewhere in the later writings: one remembers the lions and Chinese of PI. What was left open in those earlier relativistic remarks was the degree of strength of the relativism to which Wittgenstein was committed. OC2 constitutes a claim that the framework within which claims to knowledge and challenges of doubt equally make sense is such that its change can reverse what counted as either. That is classically strong relativism."
Continuing with Grayling:
"These considerations rule out relativism. They therefore rule out OC2. There is no other way of taking OC2 than as a seriously strong relativist argument ('the river-bed of thoughts may shift' ... 'a language-game changes with time'). In the ideal state of things, therefore, OC1's offer of a response to scepticism is elected to stand, and OC2 is ditched. But as the text of OC was left to us, Wittgenstein was developing arguments for both, so the next question is: is there any way they could be made to reconcile, further up the road where their parallels meet?"
"But if one does not supplement the response to scepticism (OC1) by some such strategy, the exercise in OC is at best partial, at worst self-defeating, with the self-defeat stemming from acceptance of OC2. As OC stands, it stands defeated in just this way, for it only deals with scepticism at the lower, less threatening level, and fails to recognise that scepticism in its strongest form is, precisely, relativism."
Grayling proposes a third option as a way out of the conundrum as he sees it.
"There are hints in OC of an alternative better way out: namely, some version of naturalism–in Hume's, not Quine's, sense; that is, as appealing to natural facts about our psychological make-up (not, as in Quine, as appealing to the deliverances of current theory in natural science: although the latter form of naturalism takes itself to absorb the former). See 287: 'The squirrel does not infer by induction that it is going to need stores next winter as well.' This hint is strengthened by 505: 'It is always by favour of Nature that one knows something' and the paradigmatically Humean 277: '"I can't help believing ...".' If one re-reads the practice-cum-form-of-life entries in the light of these–a twist of the kaleidoscope–a plausibly naturalistic thesis comes fully into view."
I agree with Graying that there are competing interpretations within OC, but Banno, my view of OC isn't strictly OC 1 or OC 2, it's a combination. There is a way of fitting Wittgenstein's views within a framework, but one has to be careful about theorizing about what Wittgenstein is saying, which is why I try to be careful about equating some of what I'm saying with Wittgenstein.
There are relativistic views in OC, and there is also a kind of foundationalism in OC, and this can be seen in the quotes in this article... http://www.acgrayling.com/wittgenstein-on-scepticism-and-certainty
For me to completely iron out some of my views would probably take a few hundred pages of writing, because most of my writing on OC has been strictly an exegesis. However, I've also gone beyond the exegesis into my own theory of knowledge. There is no doubt that some of what I've been putting forth in this thread does fit within OC 1 as explained by Grayling, and my views are closer to OC 1 than OC 2, but there are important elements in OC 2 that can be explained in terms of a foundational view. When I say foundational view, I'm talking about my foundational view, which has many elements of Wittgenstein, but with a twist on the prelinguistic.
The rebuttal to this is that although reality could be different from what it is, it still doesn't mean that anything can count as true. Moreover, within language-games there are still necessary and contingent truths. And our linguistic views arise within a culture of shared experiences and common knowledge, which are as sure as one can get. That said, there are relativistic aspects to all of this, but they fit within the scope of knowledge (some of this knowledge is relativistic), which has many uses across a wide platform of language-games, including the objective and subjective.
My apologies for entertaining Apo on you thread, Sam. I will get back to your well considered comments soon.
If he's not knowing, then I think he's doubting. Agree?
Dry up Banno. I made posts that addressed his points about neural states and attempts to find a grounding in something inarguable because it is "natural". If we are now discussing red herrings like whether Paris is the capital of France, it is because of your efforts to deflect from the pragmatism towards which Wittgenstein was moving.
There is actually an amusing contrast here. Peirce started off as a quietist and then became keen on a metaphysical-strength epistemology. So how that pans out could be instructive for someone actually wanting a foundational story.
If you are not interested, fine. Butt out.
The irony of attempting to achieve agreement over the notion of language as being public or shared understanding, and continually finding that so-called public speech is understood slightly differently by each participant within a speech community. No amount of clarification of terms will overcome that fundamental untranslatability of language.
But when you say something that actually reaches past a conventional or habitual level of understanding, isn't that the feature rather than the bug? Isn't that how philosophy or understanding generally manages to stay creatively open and progress?
So every sentence of any interest remains open to fresh interpretation - even to oneself. We can twist it and turn it in the light to see new possibilities of what might be meant. The meaning is not fixed but already open to another point of view.
This is one of the things that flips a theory of truth on its head. Language is not a system of frozen meanings, petrified semantic commitments. At the creatively open edge of reason, even the same sentence can be understood many slightly different ways by its own speaker. And that is a good thing. It is how language can both stretch itself elastically while also aiming at some tightest possible fit.
I see that as the dichotomistic tendency of Grayling's OC1 vs OC2 which Sam cites here. Plasticity vs stability. Novelty vs habit. A basic relational freedom combined with the possible discovery that there is some eventual metaphysical-strength limit.
All this talk about belief vs doubt. Sam was saying something that didn't make much sense to me about neural states. But the neurobiological story of the brain is how it is organised by the dichotomy of the habitual vs the novel.
If we want proof that knowledge is built on a "background" of unquestioning belief, then we can read that story into the way the brain is founded on the accumulation of useful and embodied habits. And then in complementary fashion, the brain is also designed to "doubt" - apply its attentional resources - whenever this general backdrop of belief fails to predict the world in suitable fashion.
So a naturalistic basis is right there to be seen. However its logic is dialectical. Which is where things start to go all uncomfortably Hegelian for some. :)
Doubt is not only the result of failed prediction. Whenever something doesn't seem quite right, there is cause for doubt. So doubt precedes action in the attempt to avoid failure. It is more like an intuition, that I may be wrong, than a realization that I was wrong, after the fact.
But how could you know something wasn't quite right unless you were making a prediction that it would be otherwise in some sense?
So yes, the prediction might not be a vivid and specific expectation - an attention driven prediction. But it could still be a prediction in the sense that you have some habitual expectation about things, and then that more general expectancy is the background against which surprises can pop out and catch your attention.
Is this redundancy theory or correspondence theory? Ramsey or Tarski?
So do you mean that "P" and "'P' is true" mean the same thing, or do you mean that "P" is true if the state-of-affairs designated by the sentence "P" obtains?
Doubt is not knowing, so it's not a case of knowing that something isn't quite right, I'd say it's more like an intuition. Intuition is not a knowledge in the sense of JTB. I think that most participants in this thread completely misunderstand and misrepresent doubt, claiming that doubt, like certitude, must be justified. Intuition is not justifiable but it plays a role in epistemology.
As a side note, I did have a short email conversation with Dr. Prichard about something I wrote.
Quotes are taken from this link: http://www.iep.utm.edu/witt-epi/
"Wittgenstein’s reflections on the structure of reason have influenced a more recent “Wittgenstein-inspired” anti-skeptical position, namely Pritchard’s “hinge-commitment” strategy (2016b), for which “hinges” are not beliefs but rather arational, non-propositional commitments, not subject to epistemic evaluation."
Here I agree with Prichard's account of OC that hinges are "...arational, non-propositional commitments, not subject to epistemic evaluation." However, where we disagree is with the idea that hinges are not beliefs. My position is that they do reflect beliefs, but not stated beliefs, beliefs that are shown by our actions; and I point to Wittgenstein's statements in OC 284 and 285 as such examples.
"The question that we raise and our doubts depend on the fact that some propositions are exempt from doubt, are as it were the hinges on which those turn [….] that is to say, it belongs to the logic of our scientific investigations that certain things are indeed not doubted [...] If I want the door to turn, the hinges must stay put (OC 341–343).
"As per Pritchard, here Wittgenstein would claim that the same logic of our ways of inquiry presupposes that some propositions are excluded from doubt; and this is not irrational or based on a sort of blind faith but, rather, belongs to the way rational inquiries are put forward (see OC 342) . As a door needs hinges in order to turn, any rational evaluation would then require a prior commitment to an unquestionable proposition/set of “hinges” in order to be possible at all."
The idea that some propositions (non-propositions, non-propositional beliefs for me, non-propositional commitments for Prichard) rest on what is immune from doubt. These arational hinges, are the foundation for any commitment to epistemological constructs. They are also foundational to doubt itself, that is, we start with certain commitments or beliefs, and this allows us to construct an epistemological inquiry, or to raise doubts.
"A consequence of this thought (2016b, 3) is that any form of universal doubt such as the Cartesian skeptical one is constitutively impossible; there is simply no way to pursue an inquiry in which nothing is taken for granted. In other words, the same generality of the Cartesian skeptical challenge is then based on a misleading way of representing the essentially local nature of our enquiries."
"But it isn't that the situation is like this: We just can't investigate everything, and for that reason we are forced to rest content with assumption. If I want the door to turn, the hinges must stay put (OC 343)."
"This maneuver helps Pritchard to overcome one of the main problems facing Williams’ “Wittgensteinian Contextualism.” Recall that, following Williams, the Cartesian skeptical challenge is both legitimate and unsolvable, even if only in the more demanding philosophical context. On the contrary, argues Pritchard, as per Wittgenstein, there is simply nothing like the kind of universal doubt employed by the Cartesian skeptic, both in the philosophical and in the, so to say, non-philosophical context of our everyday epistemic practices. A proponent of Cartesian skepticism looks for a universal, general evaluation of our beliefs; but crucially, there is no such thing as a general evaluation of our beliefs, whether positive (anti-skeptical) or negative (skeptical), for all rational evaluation can take place only in the context of “hinges” which are themselves immune to rational evaluation."
I wholly agree with Prichard here. For someone to properly understand this, it is crucial to understand the Wittgensteinian connection between knowledge and doubt, which Grayling also mentions.
From your source:
So if you are to maintain that hinge propositions are beliefs, you must maintain that they are propositional.
That's close to my criticism; that pre-linguistic beliefs are statable, even if unstated.
Or is it that you are rejecting the idea that beliefs are propositional?
Again, I take the common view that a belief sets out a relation between a proposition and the attitude of an agent.
They are not necessary certainties. Just certainties. They do not hav to apply in every possible world.
I am saying that such commitments may not be certainties at all. In fact I think it's a mistake to refer to them as certainties.
A given is something taken for granted. But it's not necessary to take it for granted, one may decline it, just like a proposition may be declined, and that is doubt.
A commitment is an obligation. But just as much as one person may feel obliged to take what is given, for granted, another person might feel obliged to request justification for it (doubt it).
So why would anyone insist that hinge propositions are indubitable? They are not certainties, and they are only accepted if one feels obliged to do so. The "indubitable' characteristic is dependent on the obligation, but since they are not certainties the obligation has no efficacy to prevent doubt.
One of your previous questions has led me to look to examining the different sorts of indubitable statements. But the present line of thought is one we have been over innumerable times.
So be it. Your explanation of my behaviour is equivalent to neither my belief, nor my behaviour.
I do not follow you here.
What are you asking me for an example to the contrary of?
We can keep it interesting, despite my absences...
Ha. If I am right in my explanation of your behaviour, then I have set out your belief.
I'm asking, why the sometimes? Can you give an example of a belief not shown by behaviour?
Yes, we assume that there are "hinge-propositions". The point I am making, is that as we are "delving into their nature", it becomes more and more evident that "indubitable" in relation to "hinge-propositions" is a false predication.
Quoting Banno
That's very true, but Sam26 is providing us with more and more information, such that the true nature of the "hinge propositions" is becoming more and more evident. Once we expose exactly what they are, and how they exist, it will be easier to see whether they are indubitable or not.
If it is revealed that "indubitable" is a false predication, then what becomes of Wittgenstein's response to the skeptic?
Let's look a the bishop example one more time.
Can we agree that it would not be viable to play chess against someone who doubted the movement of the pieces?
I don't know about that Banno. At least I do not think that that is always the case. While I do hold that one can correctly report upon both, another's belief and behaviour.
Quoting Banno
Any and all cases of deliberately misleading behaviour.
Wouldn't such behaviour be evidence of another, overriding belief? Not telling the axe-weilding thug at your door where someone is, is evidence of a certain belief, no?
I'd like to remark upon this. It goes back to what I was setting out earlier...
I agree with Banno here in a very specific way. If it is the case that hinge propositions are beliefs, then it must be the case that they are propositional. Hence, the name. I do not even think for a second that that went unnoticed by Witty. He is working from the framework of his contemporaries...
It was wrong.
Once again, it's all about the content of belief.
There's an interesting thing happening with the claim that all belief are stateable. While I agree with that, it quite simply does not follow that all beliefs are propositional, nor linguistic. That is because of the content of belief. It is correlational. Thus, if we correctly set out the connections drawn by the agent, we've stated their belief in a sense, despite the agent's having no language.
Quoting Banno
I offered an example of belief not shown by behaviour. It's quite nuanced, as you are aware, in all of the ways that insincerity is...
I don't follow this paragraph at all. It seems to contradict itself. Can you clarify?
OK, I'll take your point and adjust the definition to belief being the best explanation for some coherent set of behaviours...
(adjusts weight to back foot...)
Yeah, that's unusual enough to be difficult to wrap one's head around.
What do you find self-contradictory? Precisely as possible, I mean...
Right, I wouldn't play if I thought the person might cheat. How would I know whether the person was a cheater or not?
It might be my confusion of statement and proposition, but doesn't that imply that there are beliefs that do not admit to being either confirmed or disconfirmed?
Sam seems to think something like this, that there are beliefs that are neither confirmable nor disconfirmable, adding that such beliefs are true, and indubitable, and hence not propositional.
How do you proceed?
I don't know, I really don't play chess and I'm only vaguely familiar with it. I'm not really into games. I had bad experiences as a child, finding out halfway through, that the others were playing by different rules than I. And even after consulting the printed rules, they'd insist that these are the rules they play by regardless of what it says on the box.
That is, we need some sort of certainty in order to get started.
I do agree that all beliefs are stateable. The overwhelming majority of beliefs are propositional(take the form thereof... belief statements). Where you and I differ, as well as Sam and I(I think), regards the content of belief. Sam notices and attempts to make sense of how language gets off the ground without belief. If all belief has only propositional content, and all propositions are existentially dependent upon language(which they are on my view), then so too are all beliefs(which they aren't on my view). I think you agree here.
I suspect that you don't worry about such things as how language gets off the ground. I mean, there is an overriding notion of not being able to get 'beneath' language. That would be true if the content of all belief were propositional. If some belief consists entirely of correlations drawn by a prelinguistic agent, then we can, because there's nothing stopping us from using language to acquire knowledge of that which exists - in and of itself - prior to...
So...
All correlation is thought and/or belief.
All predication is correlation.
Not all correlation is predication.
I think we're having a fine discussion. Why do you think we need to be certain of anything in order to have a discussion? Usually in discussion I find many mistakes in interpretation, so I think it's better to approach discussion without an attitude of certitude.
Sure we are. But then, we are both confident that we are talking epistemology on a web site in English.
If that were not the case, how would our discussion proceed?
Nope.
Here's my grammar again, just to be clear.
Statements are combinations of nouns and verbs and such like; Some statements are either true or false, and we can call these propositions. So, "The present king of France is bald" is a statement, but not a proposition.
Beliefs range over propositions. (arguably, they might be made to range over statements: Fred believes the present king of France is bald.)
Beliefs set out a relation of a particular sort between an agent and a proposition.
This relation is such that if the agent acts in some way then there is a belief and a desire that together are sufficient to explain the agent's action. Banno wants water; he believes he can pour a glass from the tap; so he goes to the tap to pour a glass of water.
The logical problem here, the philosophical interesting side issue, is that beliefs overdetermine our actions. There are other beliefs and desires that could explain my going to the tap.
How agreeable is that?
Where do correlations fit?
I'm not so confident that what you're discussing is epistemology. And if what you are discussing is epistemology, then what I'm discussing is not epistemology, because we clearly have incompatible descriptions of this thing which we are referring to as "epistemology".
Quoting Banno
Don't you think that we ought to discuss things first, throw some words back and forth at each other, to get an idea as to how each of us uses the various words, before we make any assumptions about certainty? Discussion is prior to certainty.
If I am certain that my opinions concerning "epistemology" are correct, and you are certain that your opinions are correct, then we will never make any progress. And if you're not prepared to doubt your opinions for the purpose of compromise, why should I be prepared to doubt my opinions? Certitude is counter-productive in epistemology, doubt is productive.
Well, at the least your actions in replying to me belie any doubt you might express that we are having a discussion in English.
Sorry, never gave it any thought, because it's irrelevant. So I really doubt that I was certain of it at the time.
Why do you think that I need to be certain that I'm having a discussion in English in order for me to have a discussion in English? I've seen children discuss a lot of things in English before they even knew what "English" is.
Proposition are statements that can be true or false, and we agree on this point. However, "The present king of France" is a proposition, it's a proposition because it does have one of the features put forth in the definition, viz., that of being false. What you stated above is contradictory based on the definition you put forward. Thus, the definition is correct, but your example in not.
This is inaccurate, my mistake.
Hm. Complexity.
"The present king of France is bald" is a statement but not a proposition. It is neither true nor false because it says nothing. It is nonsense in the grammatical form of a statement.
And now we are disagreeing as to the grammar of sentences and propositions, and what is one but not the other.
All beliefs are stateable. I'm not sure what that means. If an animal has a belief, can the animal state the belief? No. So there is one example where a belief is not stateable, unless you deny that animals have beliefs. Now if you're saying that in some linguistic context any belief can be stated, of course I agree with you on that. You can always stick any belief in a linguistic context and say, see, it's stateable. However, what do you do with beliefs that are simply shown and not stated? We know that a belief can be stated given a linguistic context, but not all beliefs originate in linguistic contexts, i.e., they can simply be reflections of our actions, again like Wittgenstein's examples. Language enables us to share our beliefs, but the belief itself doesn't necessarily originate in language. It originates in the mind of the person who has the belief. Then if language is a part of that person's life, it is expressed to others in the form of a statement/proposition. Beliefs aren't simply generated because there is a language, if that was the case, then we could say that computers have beliefs simply because they can make statements.
The point about hinge-propositions is that they're not really propositions. This is seen not only in my discussions about them, but in the discussions of other philosophers.
This is a consequence of what a belief is - a part of the explanation of an action. Explaining is not the sort of thing we can do without language, surely.
But not all beliefs are stated. I believe there are no aardvarks in the stuffing of my armchair. Up until just then, this belief had gone unstated. There are innumerable (literally!) such unstated beliefs. That the beliefs of dumb beasts are unstated is a small consideration.
We are led astray by the picture of a belief as a thing in a mind. A belief is rather post hoc, inferred as a folk explanation of the behavioural results of brain activity. So I can agree with your causal chain leading from perceptions to brain to behaviour; but not to belief. The belief is a different language game - dare I use that term - running in parallel with and about the same thing, the act; but instead of being in physical terms, it is in intentional terms.
Okay, but it seems much more reasonable that the word "belief" gets its meaning from, and refers to, public behaviours in much the same way that sensation words like "pain" do. And I would assume that the word originally referred to human beliefs before anything else. This would make your attribution of beliefs to other animals and prelinguistic man an anachronism, a potential misuse of the word "belief", or at least an error in Wittgensteinian grammar.
ETA: Basically, I'm just reiterating Banno's concern that a belief is not "a thing in the mind".
Let's see if we can find a point of agreement. I would agree that when we proceed with conscious actions, we proceed with "confidence". And I also agree that "confidence" implies a "certitude". This certitude is involved with "knowing-how". However, I maintain a separation between the "knowing-how" of human actions, and the "knowing-that" of JTB. Can you agree to this distinction?
If the certitude which is associated with the confidence of human actions is proposed to be a part of knowledge in the sense of JTB, then I would disagree. I believe that the certitude of "knowing-how" must be broken down through doubt, and the request for justification, before any such beliefs become a part of knowledge in the sense of JTB. The only role that the certitude of knowing-how plays in JTB, is in knowing-how to justify.
Therefore I believe that hinge-propositions, which have the certitude of knowing-how, have no part in knowledge as JTB. They must, of necessity be doubted and consequently justified, before they can play any role in knowledge as JTB. It appears like this would create an infinite regress of justification, but what it really does is expose why we need to go beyond words, to "showing" itself, as the basis for justification.
Notice that in science an hypothesis is tested through experimentation. That is "showing". It is not tested by words and logic, it is tested by actions. Those who carry out the actions (test the hypothesis) must have certitude and confidence in relation to the actions of the testing, but doubt in relation to the hypothesis. We must always maintain that separation between the certitude of knowing-how in our actions, and the certainty of knowing-that in JTB knowledge. They are completely distinct.
I'm not saying the word or concept belief doesn't get it's meaning from public behavior, of course it does.
When I sit on a chair, am I not showing that I believe a chair is there to sit on? No one has to state the belief to know that the person showing the belief, has the belief. You can state it, or I can state it, but that doesn't mean there is no belief prior to the statement. It's often seen in our public actions even before it's stated.
Are you saying that a concept cannot refer to something prior to it's linguistic creation? When I read what others are saying it seems they're implying this, as though beliefs can't exist apart from the concept belief, or the linguistic use of the term belief.
Of course you can't explain a belief apart from language, that's what an explanation amounts to. I'm not talking about an explanation of a belief, I'm talking about how people can show beliefs apart from statements, and thus apart from explanations. Read my reply to Luke.
Some of you seem to be confusing the fact that we can talk about beliefs, share beliefs, explain beliefs, and we're doing this in this thread; but this is quite different from how we show beliefs. Forget about everything prelinguistic, we show our beliefs everyday.
Good to hear. I agree.
Quoting Metaphysician Undercover
While I like the idea of looking for agreement, I can't agree with this. Since the meaning of a word is its use, knowing-that reduces to knowing-how. Language is, after all, a human action.
But a good post, Meta - you have perhaps hit on a basic disagreement.
Quoting Sam26
One thing I've realised in this thread is the extent to which I have mixed J. L. Austin and Searle into my thinking about Wittgenstein.
My criticism of belief as mental furniture comes from Austin, Are there a priori concepts. Roughly speaking he rejects the reification of concepts; so when we talk about the red in the sunset and in the new merc, we are not talking about a concept that is something in our minds, but just using the same word to talk about different things. A concept is not a piece of mental furniture, but just a way of using a word to talk.
One way to think of what I'm saying is this: We talk about facts using the concept fact, and that concept refers to states-of-affairs, but even without the concept, or without minds to apprehend the facts, there would still be states-of-affairs in the universe. Those facts have an existence quite apart from a mind, and quite apart from any linguistic reference to them. So there is an objective reality in back of our language, but how we talk about that reality takes place in a community. Moreover, the concepts that refer to that reality, get their meaning from how we use the words in language-games.
We don't need to be idealists to see that this is wrong. Talk of states-of-affairs only makes sense in relation to talk of points-of-view. And whether we talk of the point of view being subjective or objective, it is still a point of view.
Of course, in practice, we live in a world where it is full of mind-independent events and objects and voids. We don't need to be idealists in our ontic commitments.
But still, we can't then also deny that the very idea of "a state of affairs" is a world description that demands a viewer or interpretant of some kind. That is why a maximally objective point of view is often called the God's eye view - the view from nowhere which is also the view from everywhere.
It gets worse for the naive realist as, in practice, this maximally invariant viewpoint has to start to see the "laws of nature". It has to transcend the nominalist particulars - all the medium-sized dry goods that seem to populate a world that is "a state of affairs" - and focus on what is maximally general or universal about the world being viewed. The local particulars become the contingencies or the accidents in being just the individuated variety contained within the general constraints or invariances.
So the concept of states-of-affairs carries with it both the need for some viewpoint - the maximally objective one - and also a viewpoint that then adds a nominalist fixation on the contingently individuated. It is the viewpoint that reduces the world to some instantaneous collection of concrete particulars.
Thus the very idea of a "state-of-affairs" incorporates a complex metaphysical position. There is nothing direct or simple about it. And to say that the facts of the universe exist in a mind-independent fashion is both true - in regards to an idealist metaphysics - and untrue, in regards to a properly holistic metaphysics such as the triadic model afforded by semiotics.
And yes, a proper understanding of what we might mean by the consciousness is central to having a position. I've been making that point. People hereabouts have been using Wittgenstein as if he absolved us of a need to have a background metaphysics in this regard.
Quoting Sam26
I balk at talking about facts using the concept fact. Following Austin, I think talk of concepts leads too easily to the philosophical error of thinking of facts, beliefs, colours, shapes and so on in the same way we think about moving things around in a room - as mental furniture. So we might say that Fred does not use the word "blue" correctly because his concept of blue is wrong; as if Fred had a thing called "blue" in his head that was the wrong shape and our task in helping him was to make it the right shape. The way we make it the right shape is to carefully explain to Fred what things are blue and what are not, so that his concept of blue becomes the same as our own.
But that is a deceptive picture of what is going on. We can eliminate the mental furniture with no loss of clarity. Rather than manipulating Fred's mental furniture, what we are doing is showing Fred how to use the word "Blue".
Although this path derives from Austin, it fits in very well with Wittgenstein's beetles. Concepts reek of private mental languages, or languages of thought, or whatever you will. Languages of thought are a final vestige of the homunculus fallacy.
Quoting Sam26
With this I am in agreement - especially in pointing out yet again that talk only takes place in a community. There is an objective reality in back of our language. I might add that the "in back of" part is about hinge propositions, but we should remember that our world is saturated by language, and language saturated by our world. It is innately social, so we are quite able not only to see our own point of view, but to understand the point of view of others, and even to take on that point of view. Consider Wittgenstein' discussion of pain. The upshot of that is, even if we grant that we must talk from a specific point of view (and I don't), it would not follow that we could not indeed talk about things in the world. We can and do; those who deny this have missed the lesson of meaning as use.
Correlation is what all thought and belief consist entirely of. There are no exceptions. As many times before, if we are to make sense of a distinction between belief without language and belief with, then both 'kinds' must have common denominators which constitute being belief.
Well, your grammar changes according to circumstances. Be that as it may, here you've invoked the term "relation" as a means to define belief as a particular sort of relation between an agent and a proposition...
There's a few issues I could take, but won't...
I want to see you draw and maintain the obvious distinction between reporting upon another agent's belief and the other agent's belief. Or between talking about thought and belief and thought and belief. Either will do here.
Being stateable, on my view at least, means exactly that. The agent need not be able to state it's own thought and belief in order for it's belief to be able to be stated by another capable agent...
I would say that you have this exactly backwards. Behaviours reflect belief.
Well, there's a whole bunch of unpacking to do here, but suffice it to say that some belief are generated precisely because there is a language. One's belief about social status is one easy example to point towards...
Then the term "hinge proposition" is a misnomer.
It's pretty much the same as the one posted on my user page in the old forum. The only significant difference is that I no longer accept any statement as evidence for any other - part of rejecting coherentist approaches to truth.
"relation" is no more than a predicate of valency 2. Beliefs have the form Bap, where a is an individual and p is a statement.
Reporting another agent's belief is no more than changing the first constant. Bcp.
Don't you find that problematic?
Our notion of belief comes after our realization that we have them...
That's a much better way to look at it.
I don't understand why you would say this, especially since in what you quoted I said, "...they [beliefs] can be reflections of our actions. I've been saying this all through this thread. :-$
Maybe I misunderstood you Sam. It probably wasn't worth mentioning...
To me, saying that behaviours reflect belief is not the same thing as saying beliefs are reflections of actions(behaviours)...
Jack has no statements.
Statements are not necessary for belief.
That's what.
Gotta run!
You too Sam!
(Y)
Just a belief statement that happens to be false.
We have some agreement on justification, but there's a way of using "know" which indicates that it is believed that the thing known is necessarily true. Those who claim knowledge as justified true belief would assert this. That is what I referred to earlier as "a certainty", in the sense of "it is certain that...". We use "know" in the sense of knowing-that to indicate that the thing known is true. I do not think that knowing-how can account for this type of certainty, as "knowing-how" is only supported by that confidence which I referred to, the attitude of certitude.
So this is the issue. If knowing-that reduces to knowing-how, then that certainty (in the sense of it is certain that...) which is commonly associated with the use of "know" in the sense of knowing-that, cannot be supported. This is to say that "knowledge" as justified true belief cannot be supported, because "true" cannot be verified by knowing-how. This is the certainty which is associated with truth. "It is certain that..." means "it is true that...". Now we have no support for the assumption that what one knows is the truth, because what one knows is how to do something, and any determination of truth would be relative to the method or technique, unless there was some specific justified way of determining "the truth". If this is the case, then I argue that there is nothing which is indubitable.
So really, we agree on everything accept the logical consequences of what we agree on. I agree that knowing-that reduces to knowing-how. But I apprehend as a logical consequence of this, that JTB cannot be supported because the certainty required for truth cannot be provided by knowing-how. So I argue that if we ask of a proposition, is it true, there is no proposition which is beyond doubt.
Quoting Banno
Thanks Banno, coming from you, that means a lot.
Woe. Suddenly we are miles apart.
There's that word necessarily. I use the possible worlds interpretation to make sense of modal logic; if I recall correctly, you use it entirely differently, in a way that I could not make any sense of. SO I will just try to work around that for a bit.
Let's look at some other examples of know-how. The ubiquitous example is knowing how to ride a bike.
Notice that knowing how to ride a bike presupposes a bike? Sans the vehicle, the notion of riding a bike is nonsense.
Sound familiar? It's the same issue as the certainty of hinge propositions. Knowing how presupposes the stuff of our everyday world. Knowing how to use language is no different.
Now you seem to think there is a problem here for JTB. Please understand that from my reading, OC shows that it is illegitimate to say that we know hinge propositions. That's because they do not admit to justification, and hence are not subject to the JTB definition, and hence not examples of knowledge. No potential to be wrong, no knowledge.
So not only is certainty central to knowing how, it is central to knowing that.
Quoting Banno
He cannot believe "that's my tooth" anymore than he can believe Paris is the capital of France.
That Jack cannot state his belief does not mean that it is not his. We agree there.
It's the content that needs to make sense here Banno. Jack's belief does not consist of statements. He has none. His belief cannot consist of statements. Nor can it be the case that Jack's belief is some attitude or other towards a statement.
:-}
It really doesn't. Jack's belief is the compliment of his actions and his desires. You're just indulging in reification.
Try this... open your eyes a bit wider...
How would you know if you were wrong in your claims about Jack's belief? What would have to be the case in order for you to be wrong in your report of another's belief?
If you accept that the concept belief takes its meaning from public behaviours, then what of your "private beliefs"? If you are merely saying that there is some internal aspect to belief, as there is e.g. an internal aspect to pain, then I agree - although I'm not sure what pre-linguistic man's internal aspect of a belief could be without language. But also, as I've said before, I think it confuses matters to use the word private here, given its Wittgensteinian usage, i.e. where something cannot be made public or can be known only by a single individual. If you accept that the word belief gets its meaning, and that beliefs can be expressed, via external, public behaviours, then it confuses matters to refer to beliefs as private, especially when the discussion is also about Wittgenstein.
The presupposition of "a bike", is just that, a presupposition. The presupposition cannot grant truth to that which is presupposed.
That you know how to ride a bike means that there is an activity which we call "ride a bike", and you are judged as knowing how to do it. You are judged to be correctly doing what is called "ride a bike" . The use of the word "bike" to refer to what you are engaged with, doesn't necessitate logically, that there is a bike there. Your fallacious "necessity" is hidden in your presupposition.
Quoting Banno
Right, the hinge propositions support a knowing-how. I would call this knowing how to use words. The know-how is judged according to the conventional use of words. However, the proper use of words does not guarantee "truth" in any meaningful sense of "truth". As in your example of the bike, truth is "presupposed" by conventional usage. If it is conventional to call the thing a bike, then it is true that it is a bike.
Because hinge propositions are not subject to JTB, the knowledge they support is not JTB knowledge. It is lacking in an essential aspect, real truth. Hinge propositions support 'truth by convention".
If Jack has belief, then not all belief consists of statements/propositions, for Jack has no statements/propositions.
That's something to consider here folks...
The reason that that(belief content is propositional) has been held for so long is as a result of the justification aspect of JTB, which would have been much more aptly named JTP. When one argues for his/her own belief such as is necessary in order to justify one's belief to another, they are reporting upon their own thought and belief. That is to say that they are involved in a metacognitive process. They are thinking about their own thought and belief. When doing this, it is done so via language use... belief statements/propositions. Language is required in order for an agent to become aware that it has thought and belief. Written language to be more specific...
It does not follow from the fact that Jack cannot argue for his own belief that he has none. It does follow from the fact that Jack cannot justify his own belief that he does not have the means for doing so. It does follow from the fact that Jack has belief and no language that not all belief is existentially dependent upon language. It does follow from the fact that Jack has belief and no language that not all belief content is propositional/statements...
All correlation is thought and belief.
Not all correlation is predication.
That's how it works.
Jack draws correlations between his own behaviour and getting fed. He attributes causality. Thus, he expects to get fed again after behaving the same way enough times and getting fed afterwards. He believes acting a certain way results in getting fed.
Think Pavlov's dog and the bell...
My one cat has drawn correlations between the sound of certain kinds of plastic rustling and her own getting fed(treats). She has also drawn correlations between the sound of cat food hitting her bowl and getting fed. She has also drawn correlations between certain vocalizations she has and getting fed. She also has drawn correlations between certain vocalizations and other cats around my house that are feral and mean...
Her behaviour puts all of this on display. She has certain expectations as a result of these rudimentary thoughts and beliefs, and she makes them known. She doesn't think in statements. She thinks in meaningful correlations...
As do we all.
Over and out. You guys/gals have fun, I've a bunch of much more practically important engineering to do.
X-)
A belief is a firm opinion, a conviction. To expect is to regard as likely a future occurrence. A correlation is a mutual relation or dependency of two things.
If I understand you correctly, you say that the cat with its mind, recognizes a relation between two things. Because of this it considers a future occurrence to be likely. This you consider is a firm opinion, a conviction, belief.
How does "doubt" relate to this scheme? When the cat considers as likely, the future occurrence, does it still respect the possibility that the occurrence may not happen? When a person has a belief, a firm opinion or conviction, does that person still accept the possibility that it may be false?
You don't.
Conviction is belief based. Expectation does not require any understanding of likelihood/probability. Correlations are drawn by agents. Belief consists entirely of mental correlations...
Oh, sorry for the misunderstanding. I was trying to be sure of what you were saying so I took dictionary definitions. I suppose you have an idiosyncratic understanding of these words?
So...
Quoting creativesoul
Exactly, couldn't have said it better myself. Very precise, and very clear.
Quoting creativesoul
Again, I like it Creative, very direct and to the point.
Yes, that's all I mean by private, that there is an "internal aspect" to belief. But then you ask, "...I'm not sure what pre-linguistic man's "internal aspect" of a belief could be without language[?]" - It would be just that, a private belief, if kept private, or become public in two ways - first, by expressing the belief publicly via an action apart from language, or two, expressing the belief via language, which are both public.
I do except the fact that beliefs get their meaning in a public way, i.e., the concept belief is a public happening. It doesn't confuse things if you understand that there is an internal aspect to a belief that is a necessary condition for belief (here I'm separating the internal from the external). However, language itself, is not a necessary condition for belief, although it's necessary for the linguistic application, or the expression of a belief, which are public.
I don't think I confused the issue of what I meant by private beliefs, but I can see how others confused the issue. The problem as I pointed out to Banno, was that the concept belief doesn't get it's meaning from the private mental happening. I explained how this idea a couple of times, and how it differed from what Wittgenstein was saying. Now, could I have worded it more accurately, probably, I would have to go back and look at what was written.
Judging by the discussion in this thread, there is no such thing as "the concept belief". Doubt is clearly warranted.
I don't follow your logic. Jack has a red ball is not a belief that Jack would have (if Jack is a dog). If I say, "Jack has a red ball," that would be my belief expressed in language.
"Jack has a red ball" cannot be true if "red" is our descriptions of Jack's ball, since our descriptions are not Jack's descriptions.
So Jack went to the bowl because he was hungry and he believed the bowl might contain food: act explained by desire and belief.
Or Jack went to the bowl because he wanted to view some art and believed that there was an excellent fish motif on his bowl.
Or Jack went to the bowl because he believes that the great god Zarg requires him to sniff the bowl at least five times per day.
This doesn't follow from what I've been arguing Banno.
"Jack has a belief" cannot be true if all beliefs are descriptions of behaviour, because Jack has no descriptions of behaviour.
That would follow what I've argued.
"Jack has a red ball" cannot be true if all cases of having a red ball are descriptions because Jack has no descriptions.
That would follow what I've argued.
I warn against conflating the necessary and sufficient conditions for having a red ball with a description of having a red ball. That's what's going on with your account.
Indeed, how could we be wrong about Jack's belief if we first hold that it consists entirely of our statements about his behaviour?
Quite simply, we would be dead wrong in every case if we first held that the content of Jack's belief was propositional/statements... each and every claim would be equally wrong. Jack has belief. He has no statement. Jack's belief does not consist of statements.
Our report of Jack's belief does.
X-)
Thanks Sam. I've been telling you that we're not that far apart... well, on this matter at least.
;)
Yeah. Except that a belief is a description.
SO what more is there to the content of a belief than subject and statement?
Then Jack has no belief, and your position is self-contradictory. It also cannot admit of belief prior to language, for descriptions are existentially dependent upon language.
It's not more... it's less AND more.
That's what getting to the root of things goes. It provides the simplest adequate explanation for the widest scope of application.
Correlations Banno... that's what all thought, belief, propositions, and statements consist entirely of.
Oh... and if shifting your weight to your back foot is a defensive posture, there's no need my friend. I'm not attacking you. I'm focusing upon the content of your writing...
Just an admission that your argument at that stage carried some weight. I went into how, here.
Now that I re-read my statement, it's a mistake to say that beliefs are reflections of actions, so you are correct in that actions are reflections of a belief. So I did reverse this, and this is what Wittgenstein pointed out, i.e., I see a particular kind of action, and that action reflects a belief or beliefs. I'll have to re-read my posts because I'm sure there are other errors that I made in my expressions. This though is a kind of typo more than anything else, but I also didn't realize what I'd done when I re-read what I typed.
The content of belief...
He didn't figure it out. His use of "hinge proposition" shows that. I've been called arrogant more times than I care to count. You'll have that.
Jack cannot speak. He cannot tell us what he believes. We infer that he does. What can be reasonably inferred about Jack's belief and more importantly, upon what ground? What is the criterion for belief such that when it is met we have a case of belief?
I wouldn't put it like that; it will only lead to confusion. "Hinge propositions" are like riding a bike; they constitute know-how, so it is not illegitimate to say that we know hinge propositions. Of course knowing how does not require justification, and if knowing that is reducible to knowing how then neither does knowing that require justification. It is beliefs, which come into play in the absence of knowledge, that require justification or at least explanation in terms of what causes them. And any such explanation, being hypothetical (that is being belief, not knowledge) will itself require justification.
The mistake you are making consists in thinking that hinge propositions are beliefs. As I explain above they are not; they are know-how. "Proposition" is a bad choice of term here.
Definitely not. I've seen you guys go around in circles for weeks before, but I'm thinking maybe this time there will be a break through.
Quoting Janus
Same thing. Haven't you been reading the discussion? Beliefs are know-how.
Then you are collapsing the distinction between beliefs and knowledge. Knowing that is reducible to knowing how, but believing is not. Believing that, with sufficient practice, you will be able to acquire the know-how necessary to ride a bike, or speak a language, is not itself know-how; although of course it presupposes other kinds of know-how that are necessary in order to be able to frame the belief. That is why everything cannot be doubted; because to doubt anything requires know-how which itself is not subject to doubt.
Tell that to Banno. who says that belief is demonstrated by actions.
Quoting Janus
The belief you describe here, is itself a know-how, it is just not a knowing how to ride a bike, as you admit when you say "other kinds of know-how that are necessary in order to frame the belief". How could the belief be anything other than these different kinds of know-how?
I don't get your argument, it seems senseless. You claim that all cases of knowing-that are reducible to knowing-how, but belief is not. So do you think that a person can believe without knowing how to believe?
It doesn't follow from the fact that know-how is required to frame beliefs that particular beliefs are reducible to know-how. If you think it does then produce an argument.
I can say that knowing that, for example knowing that Paris is the capital of France, is reducible to knowing how to speak English, and knowing how to interpret maps, or travel to France or to do whatever I did to acquire the knowledge and represent it to myself. Believing has an extra element, which is the uncertainty inherent in the fallibility of a belief. How can you reduce that uncertainty to know-how when it is on the contrary a not-knowing-how to achieve the certainty of knowledge?
You'll need to clarify what you mean by "frame beliefs". I don't apprehend a difference between a belief and the frame of a belief. What could frame a belief, but another belief. And if this is the case, the framed belief, being supported by the frame, is just as fallible as the frame.
Quoting Janus
The uncertainty, which you say is an extra element of belief, not found in knowing-how, is actually very evident in knowing-how as well. No matter how many times we've done the same thing over and over again, there is still the possibility we might fail in the next time. That is why those of us who work with machinery must be very careful every day, and never let down our guard, no matter how well we know how to do what we do, lest we be injured.
Quoting Janus
As I argued earlier, the certainty of knowledge is only produced by separating knowing-that from knowing-how, and allowing that knowing-that obtains levels of certainty not obtained by knowing-how. If you reduce all knowledge to knowing-how, then all knowledge suffers from the fallibility of knowing-how.
And yet ALL doubt is belief based. Therefore, until one holds some belief doubting is itself humanly impossible. Until one has a baseline of belief upon which to ground doubt, doubting cannot happen. Reasonable doubt requires justification. The aforementioned baseline is comprised of belief that hasn't been doubted for it cannot be... yet.
I think that that baseline was Witt's aim with hinge propositions...
Jeez.
A subject and a statement do not suffice, as I've already argued for without subsequent refutation. Not all behaviour shows the belief of the agent behaving, as I've already argued for without subsequent refutation.
Is there a single case of drawing a correlation between things that doesn't count as thought and/or belief?
I think not.
Is there a single case of imagining, thinking, thought, and/or belief that doesn't consist entirely of drawing correlations between things?
I think not.
What stronger ground is there for holding that the content of all thought and belief is correlation?
I don't agree, but this is only because you and I wouldn't agree on what describes "belief". I think that a living being can think without holding belief. And I think that if we allow a distinction between memory and belief, then a lot of what you describe as belief is actually thinking without belief. I also think that doubting is more closely related to thinking than to believing so that one could be thinking and doubting without believing.
One can be considering while suspending one's judgment. In this case, it is described as thinking. I've no issue with that kind of talk. There is no thought without belief.
All correlation presupposes the existence of it's own content, no matter how it is later qualified(imaginary, real, or otherwise)...
I'm not interested in quibbling over the differences between uses of "thought" and "belief". There are often times that those words mean different things. There are no cases of either that do not consist entirely of correlations. Ultimately, I draw and maintain a distinction between thinking(as just considering) and believing(as already considered and decided).
Memory is re-drawing and/or revisiting past correlations... and is notably error prone.
However, learning the names of things requires believing that something is there... One cannot doubt that that is(called) "a tree", while learning how to use the words... There is no just considering whether or not that is a tree during language acquisition. Rather, one first draws a correlation between the tree and the vocalization(the word)... and it's meaningful as a result.
Witty used "slab"... or at least that's the translation. Banno uses "a bishop moves diagonally". These are all examples of a baseline upon which one can doubt something that is said after the baseline is in place. If you doubt that that is a tree, then you simply do not know how to use the words... Same with how a bishop moves, and knowing how to play the game... Same with "slab" and knowing what the mason is asking you for...
"No! Not that... THIS. This is a slab."
Or five red apples...
Call it what you like. Let me know when you find something to call it that does not consist entirely of correlations...
We can say the same for a cat and it's 'toy' mouse or rat or lizard or moth or....
Does the cat believe that "the toy is under the rug"?
Seems like a fine thing to say, but is it? The cat need not know the name "rug" or "toy" to know that a toy can be under the rug. In this case, it seems Banno's explanation fits. I mean, I think that saying the cat believes the toy is under the rug, in a situation where the cat is looking for the mouse that just ran under the rug seems perfectly acceptable.
The challenge then, for me at least, is to put this in terms of correlation...
The baseline...
Let's say that thinking is drawing correlations. One can do this without believing. The content is memories. Belief is a certain type of judgement, such that not every judgement is a belief. The judgement which results in an action doesn't necessarily require belief. Knowing-how doesn't necessarily imply belief.
Quoting creativesoul
The issue is to establish some criteria to determine what qualifies as "belief". There is much mental activity, and we need to make some distinctions, to proceed in an analysis or else we just assume that all mental activity requires belief. If we don't want to assume all mental activity involves belief, then we need to make some distinctions.
Memory is a good place to start. I think you would agree that not all memories qualify as beliefs. But if we revisit our memories, dwell on them, correlate them to other memories, and pass a type of judgement, then maybe we have formed a belief.
Quoting creativesoul
I don't agree with this use of "believing that something is there". If "believing" in this sense constitutes "belief", then I think all mental activity would require belief. That is because there could be no content without believing that something is there. Consider dreaming for example, there is a form of certitude, of "believing that something is there", which is proper to dreaming. The dreamer is convinced, within the dream, that all these things are really happening. But this type of certitude, whatever it is, is extremely fallible, so I wouldn't class it as "belief".
So I do not believe that learning the names of things requires "believing that something is there". All it requires is the experience, the same type of experience as dreaming, and the same type of certitude, that I am experiencing something, which we have in dreaming. I would not call this belief, it is just a basic aspect of mental activity. The difference though, is that in learning words, we have people demonstrating the use of words. And contrary to your claim, we can and do doubt that that is called a "tree" when learning a language, because we are exposed to many different people using the language in many different ways. So if one person calls it a tree, and another a shrub, there is doubt.
Quoting creativesoul
Right, there is doubt which precedes the use of words. And the use of words is filled with doubt. Anytime you have to think about what to say, prior to saying it, this is doubt. So the idea that we cannot doubt the "baseline" is just nonsense. There really is no such baseline, or hinge propositions, there is just the shifting sands of language use. It's all shifting because of doubt.
Quoting creativesoul
Again, I do not think that this is a proper use of "believe". The child has memories. The child thinks about where the toy might be, and looks there, behaving according to memories. But the toy is lost to the child. The child has no belief about where the toy is. This is the same thing as your examples of Jack the cat. Jack has memories concerning the food dish, and acts accordingly, but Jack has no belief about this. If we use "belief" in this way, we'll only find that all mental activity requires belief, because all mental activity requires content, and you just refer to all content as belief.
I think that belief requires a high level of stability in the mental content to produce the conviction required for what we call "belief". This stability is only provided for by the use of words, as things which maintain the same appearance time and time again. Prior to the use of words, memory could only consist of mental images, which would be very hard to maintain because of the detail, and differences, therefore very fallible as you say. So I think that "belief" in the proper sense of the word, referring to conviction and certitude with significant temporal extension, can only be understood as a result of the use of words.
As I finish writing this, I now see that the key here is the temporal extension. There is a certitude which accompanies the immediate experience of "now", and this is the certitude found in the dream, the certitude of "believing that something is there". But I think that this is not "belief". Then there is the certitude of a very recent memory, what just happened. And neither is this "belief". "Belief" refers to a certitude or conviction which maintains stability over time. If we dismiss this requirement, of temporal extension, then all the certitude, beginning with the certitude that I am experiencing something right now, is belief, and all mental activity is composed of belief.
Sam, if you remember pages ago, I warned of the above when it comes to Meta... S/he has shown a historical propensity for arguing against someone by virtue of using a different linguistic framework. Semantic twaddle.
Fucking idiots...
Nonsense that is borne out each and every day - all day long - across the globe...
:-}
There are children all over the world who are currently doubting that that is called an imbecile... while first learning what counts as an imbecile...
We clearly haven't determined what counts as a belief. So what makes you think that anyone has determined what counts as an imbecile?
What is really the case is that we assume that there is such a thing as an "imbecile", that there is such a thing as a "belief", that there is such a thing as a "world view", that there is such a thing as a "baseline", because people use these words. But such assumptions don't make it true that one can say without a doubt, what an "imbecile", a "belief", a "world view", or a "baseline" is. Nor do these assumptions make it true that there even is such things.
Suppose I see the sun set in the west in the evening, and rise in the east in the morning, so I claim that a "dragon" carries the sun around from its setting point to its rising point every night. This word, "dragon" refers to my explanation of what happens to the sun every night, just like "baseline" and "hinge-proposition" refer to what is foundational to epistemology. They are nothing but words which refer to non-existent nonsense, indicating that the people using these words misunderstand what is really going on.
The same beliefs can be framed in different languages. Languages cannot be fallible or infallible they are just tools, just know-how. We cannot frame a belief without a language, but it doesn't follow from this that we cannot believe without a language.
Quoting Metaphysician Undercover
No, that uncertainty consists in our belief that we know how to do something, not in our knowing how to do something. People can certainly believe that they know how to do things that they do not know how to do. Your 'operating machinery' example is not relevant; the kinds of failures you are referring to are failures of attention, not failures of know-how.
Quoting Metaphysician Undercover
No, the separation of knowing-that from knowing-how produces only doubt (out of which certainty cannot ever be derived). There is no fallibility in knowing-how, but only in believing that you know-how; if you know-how, then you know-how, end of story.
So the belief is framed by language. I assume then, that know-how is required to frame a belief. With know-how we put a belief into language.
So I don't understand what a belief is then. My beliefs are in language, I believe this, and I believe that, all statements of language. They are formed in language and they exist in language. Never do they exist in any other form, needing to be framed in language, because they are created in language. How do you think that the belief is framed in language, when the belief itself is created out of language?
Quoting Janus
Well that's nonsense. A failure in attending to what you are doing, when you are doing it, is obviously a failure in your know-how. What could 'know-how" be, other than the capacity to attend to what you are doing, and get it done? If you can't attend to it and get it done, then clearly you don't have the know-how. Being able to focus your attention on the task at hand is an integral part of know-how.
Quoting Janus
OK, that's your assertion then. If someone has the know-how to carry out a particular procedure, then it is impossible that the person will ever make a mistake, and fail in carrying out that procedure. However, evidence demonstrates that this assertion is wrong. People make mistakes and fail in tasks that they have already been successful at numerous times before. And to say that the person's failure is a failure of something other than the person's know-how, like a failure in the person's attention, is just nonsense. Because if in some instance, the person cannot maintain one's attention long enough to get the job done, then that's a failure in the person's capacity to do the job, and therefore a failure in the person's know-how.
Same problem historically that epistemology has succumbed to...
The logical consequence is either non linguistic agents have no belief or propositions are prior to language. Neither is acceptable.
There's no reason to deny talking in terms of Jack believing that the toy is under the rug, but we must be careful to not personify Jack(anthropomorphism). He doesn't believe the statement. He believes that the toy is under the rug. Our statement sets out the way things are. Jack's belief is made up of much the same, but without language. We draw meaningful correlations between language use and the way things are with the terms "rug", "cat", and "rug" and the spatial relationship between them. We know what sort of situation that statement describes. Jack doesn't have a clue about describing the situation, nor need he. He witnessed it.
If our language sets out a situation which does not require being set out in order for it to obtain(be that way), then we've hit upon a case of our describing something that is not existentially dependent upon language.
Language allows us to become aware of(discover) things that are not existentially dependent upon language, and things that are. Jack knows nothing about nouns or verbs or any other sort of syntax, nor can he. He can, however, hold belief about some things we name.
The difficulty lies is knowing the limits.
That is the distinction between thought and belief and thinking about thought and belief. Framing a belief is thinking about it, assuming we're framing it on purpose, as in offering our ground for assent.
In order to frame one's own belief, one must have belief and an ability(means) to frame it. Belief comes prior to framing... or simultaneously in many cases...
Thoughts and beliefs are already framed in language, and that framing doesn't require thinking about thought and belief. Thinking and believing are not necessarily framed as thoughts and beliefs. though. Thinking about thought and belief is a still further process.
Quoting creativesoul
I would say you are not drawing the crucial distinctions between thinking and thoughts, and believing and beliefs.
What I am saying is that what is required to fulfill the conditions of what we understand by "belief", is thinking about thought. This is the only thing which can bring about the conviction required by what we understand as "belief". If this produces the conclusion that non linguistic agents have no belief, then you ought to accept this, instead of trying to characterize some type of thinking which does not suffice to fulfill the conditions of "belief" as belief. Calling that type of thinking "belief" is nothing but a misuse of the word.
Agreed regarding some kinds of thought and belief, as well as some kinds of talking. However, regarding classic epistemology, one is most certainly thinking about one's own thought and belief. When one argues for what they believe, they are thinking about their own thought and belief. When one is arguing against what another thinks and believes, they are doing the same...
This is just self-contradictory language use. While I would agree that folk frame their own thought and belief using different terms than "thought" and "belief", that is as far as my agreement would stretch.
I would agree. Thinking is what we do and/or ore doing when we're drawing correlations, and thought is the correlation. The same holds with believing and belief. There is also a clear distinction between thought and belief, if the former is not necessarily held to be true by the agent in question, and that is most certainly thinking about one's own thought and belief.
We - as believing agents - do not determine what our mental ongoings consist of. We believe things long before our ability to talk about our thought and belief. Thus, we can be wrong in how we take account of that which exists - as it is - prior to our awareness of it.
Oh, the irony...
What I'm telling you is that in order to fulfill the criterion for your notion of "belief", one must think about one's own thought. Doing that requires complex(written) language use. Thus, according to your criterion for "belief", one cannot have belief until and unless one is already fairly affluent in language use. As a matter of fact, if what you say here is true, when one first learns that that is(called) a "tree", s/he does not believe - cannot possibly believe - that that is there(whatever and wherever that may be). Nor can they believe that that is called a "tree" until after they've learned to consider their own mental ongoings. For fuck's sake, if what you say is true, then one cannot even believe that they have things called "thought" until they've already begun thinking about their thoughts...
Seems to me that you've no idea what you're talking about. The notion of "belief" your working from is found lacking, wanting, and basically begging for truth. Everyday fact contradicts your notion, and yours isn't the only one...
Misuse of a term is neither determined by nor equivalent to being different from your use. I've just shown some of the issues with yours. All you've done is hand wave... Gratuitous assertions won't do Meta. It does not follow from the fact that you work from a different notion of "belief" that I am misusing the term. Take the semantic quibbling elsewhere...
:-}
It seems to me that Knowledge without Belief is impossible and maybe at a certain level their distinction vanishes, but it is clearly not the other way round, Belief without Knowledge happens all the time.
Belief has an emotive quality, an intensity, perhaps this how we bring value to the epistemic. If belief is traceable back to feeling then language may not necessary for belief, but still some sort of semiotic connection.
Note I said "thoughts" and "beliefs" and you responded using "thought" and "belief". I have been referring to thought as 'thinking' and belief as "believing". So, in my terms a thought or a belief, being defined as a determinate entity, must be linguistically framed; whereas thought and belief, or thinkings and believings need not be so framed.
Not my problem.
The term "thought" can refer to either a plurality of thoughts, or a single one. It can also be used to refer to what one is doing when they are sitting around contemplating their own mental ongoings.
When the discussion is based upon what counts as a single thought, it goes into the direction of content. That's where I've been and will stay.
I've set out the necessary and sufficient conditions for each and every sense of each and every word ever spoken and/or written, regardless of the individual particulars.
Belief must be meaningful. Thought must be meaningful. All meaning consists entirely of correlations being drawn by a capable agent. The capability consists of something to become sign/symbol, something to become significant/symbolized, and an agent to draw a correlation between the two... All meaning is attribution, and that's precisely how it's done.
Now what?
No, your problem is that you're not interested in anyone else's thoughts and beliefs, even when they are patently more coherent than your own.
I'm not interested in such petty bullshit.
No, the term "thought" refers to the process of thinking; it is the noun equiavelnt to the verb "thinking, in other words. The term "a thought" refers to a single thought, and the term "some thoughts" refers to a plurality of thoughts.
It's not "petty bullshit" but suggested refinements, for the sake of greater clarity, of your inadequate terms.
That is not a suggested refinement. That's petty bullshit.
That's right, it's a goad to motivate you to pay attention to suggested refinements.
More adequate terms are more precise in that they enable more distinctions and acknowledge more subtle distinctions.
Show the flaw. You've done nothing hitherto aside from teetering upon the fence of equivocation.
Evidently the term "term" refers to more than one. By my lights, not everything captured by quotation marks counts a being a term.
See how this works?
"A" is a term. "Thought" is a term. "A thought" is two terms captured between quotations.
From Google search, here:
https://www.google.com.au/search?q=term+definition&ie=utf-8&oe=utf-8&client=firefox-b&gfe_rd=cr&dcr=0&ei=amyCWq6XL83N8gealryYAw
Term
t??m/
noun
noun: term; plural noun: terms
1.a word or phrase used to describe a thing or to express a concept, especially in a particular kind of language or branch of study.
"the musical term ‘leitmotiv’"
synonyms: word, expression, phrase, turn of phrase, idiom, locution; More
Got an argument or valid criticism/refutation?
Grant the terms.
So, you reject the dictionary definition, then?
Quoting creativesoul
Not so bright! Turn up the wattage; you'll gain clarity... :-}
Right, that's exactly what I am arguing.
Quoting creativesoul
Right, I would not call that a belief. When a child learns one's first words, "mommy" and "daddy", for example, I wouldn't say that the child believes these are things called "mommy" and "daddy". The child is just learning how to say things.
Quoting creativesoul
Correct. Why is this a problem for you? It's nonsense to say that a person would believe oneself to have something called "thought" unless one was already thinking about thought. Would you say that a person could believe that there's something called a "tree" without having thought about a tree?
Quoting creativesoul
As I said, you describe "belief" in your way, I describe it in my way. I think mine looks toward what "belief" really is, and yours just looks at common usage of "belief', which is varied and ambiguous. That's why I think mine is better, it provides a clear indication of what a belief is, while you just insist that if something is thinking, it has beliefs.
Back to Jack. A different turn...
"Jack" is Jack's name.
"Jack" is not Banno's cat.
Jack is Banno's cat.
"Jack" is not Jack.
"Jack's belief" is... or is not... Jack's belief?
Let the record show that Meta is assenting to the belief that one can learn the names of things without believing that things are there. One can evidently, according to Meta, point towards a tree without believing that 1.)they are pointing to a tree, or that 2.)they see a tree, or that 3.)someone else is pointing to a tree, or that they are doing stuff with someone else, namely the teacher who's pointing to a tree whilst teaching the child how to use language in a meaningful way. Again, according to Meta, the student cannot possibly believe any of that.
And they can still yet learn how to use language?
I'd like to see the criterion that clearly sets out what language acquisition is existentially dependent upon.
Let the record show that this has no bearing upon what I've been arguing. In a more sarcastic tone, it could be said that Meta is arguing with his own imagination. Straw men.
The child, if asked where mommy and daddy are, will show you. According to Meta, the child does not believe that those are mommy and daddy.
An impoverished recollection of this thread.
Sigh...
No I do not reject the dictionary definition. I'm telling you that you cannot validly criticize another's argument by virtue of not granting what is an otherwise perfectly acceptable sense of a term. I'm telling you that your being a twit by thinking that you can.
I was criticizing your argument by pointing out more and subtler distinctions you could make if your terms were more rigorously used, not being pedantic about your use of terms.
Hey Cava...
Yup.
Belief is traceable back to emotional states. To attribute/recognize that touching fire hurts is to attribute the pain to the behaviour.
Learning that fire hurts doesn't require language, but most certainly requires believing that touching fire causes pain. All that takes is a capable agent making the connection between touching fire and the pain that follows...
Making the connection is thinking. The connection itself is a thought.
Funny. Point there again, I missed em. Where are those subtler distinctions?
Go read the recent posts. It always ends like this with you. :-}
Correct, the certitude "that something is there" does not qualify as belief. As I explained earlier, this certitude exists in dreams, and in the subconscious levels, plants might even possess this certitude. That certitude "that something is there" does not qualify as "belief" because "belief" is restricted to being the property of a conscious mind. Therefore I do not consider the certitude "that something is there" to be belief. This is why the skeptic's doubt of "existence" is justified.
Quoting creativesoul
Language acquisition is dependent on the will and desire of the human being to learn language.
Sigh...
And Meta...
Does he still beat his wife?
According to Meta, Josh does not believe that he has legos, nor does he believe that he goes to school, or that it's time to go to school, or that school is almost over and it's almost time to go home when clean up time begins...
And yet he talks about this stuff all the time, but he doesn't ponder their truth. He presupposes it. All belief does. It is only after one becomes aware that some belief or other they have is false(after suffering the consequences) that one's attention can begin to consider whether or not something else they believe is true.
X-)
...before being able to conceive of language.
At four years old, your friend Josh is well versed in language use, and clearly capable of holding beliefs.Quoting creativesoul
Obviously. "Language" is not the first word learned, so the individual learns how to use language before conceiving of what "language" is.
Have you read any Plato? Socrates' most prominent enterprise was to demonstrate that people know how to do things without knowing what they are doing. This is what Socrates did. He went to all sorts of different people who claimed to have knowledge, and demonstrated that all they had was technique, method, without understanding what they were doing. They knew how to do things without knowing what they were doing. So he demonstrated that they really didn't have the knowledge they claimed to have. This is very evident with language use, children learn how to use language without knowing what they are doing.
WTH???
It's all sighs and irrelevancies with you! I wonder what rich trove of hard won/obsessively cobbled together insights/realisations you are desperately trying to protect/ hide behind. :P
Another example of idiot speak...
Thinking about one's own thought first requires a means to isolate and further contemplate one's own thought...
We use the term "thought" amongst many other terms...
Josh does not have that ability... yet.
You're boring me Meta.
Statements are statements of belief. Truth is presupposed. That's how "is true" becomes redundant.
Josh makes all kinds of statements. He cannot yet write them. He believes them all.
Meta is lost.
And some talk of conviction being necessary for belief. I say that those who talk that way may be... just may be... projecting.
Protect/hide?
Are you shitting me? :-}
I've been not only called "arrogant" more times than I can count, but also "honest to a fault", "too generous", "naive", and "clueless"...
The last two are typically regarding being too trustworthy of those who ought not be trusted in the eyes of the name-caller, or not picking up on unspoken 'social cues'...
I've set out the necessary and sufficient conditions for all meaning. As a result, I've a baseline from which to judge all kinds of claims about all kinds of things.
If all meaning consists of 'X', then everything ever spoken, written, thought, and/or believed is existentially dependent upon 'X'. Any and all claims that contradict this are wrong, no matter how long they've been believed.
Back to Jack. A different turn...
"Jack" is Jack's name.
"Jack" is not Banno's cat.
Jack is Banno's cat.
"Jack" is not Jack.
"Jack's belief" is... or is not... Jack's belief?
A non-linguistic agent cannot have belief that is itself existentially dependent upon language.
Our reports of such belief are dependent upon language.
The difficulty is parsing these things out...
All cases of drawing connections, associations, and/or correlations are adequate for being rightfully called "thought" and/or "belief". There are no cases of either term - regardless of the sense - that do not consist entirely of correlations. All thought and belief consist entirely of correlations. All correlation is thought and belief. Not all thought and belief is existentially dependent upon language.
Earlier I offered the example of my own cat and her thought and belief...
I agree. You write in incoherent fragments. I'm lost.
Ahem...
Because that is what amounts to being incoherent.
I know right?
I'm waiting for something other than irrelevant or invalid shit to be said. Make an argument. State your objection. Make sure it's valid(follows from what I've been arguing). If there's any question about what I mean, let me know and I'll set out the correlations for you, so that that meaning can be better understood/shared.
Show me where I'm conflating the abstract with the concrete, since that's a charge you've levied. Make the case. I mean, step it up...
Nah, you're not serious about being unprejudiced, and making a genuine effort to explain and critique your own positions, so it just aint worth the effort.
My cat, the sound of certain kinds of plastic, and her getting treats. My chickens, the sound of certain kinds of plastic, and their getting fed. My chickens, the sound of the slider doors out back, and their getting fed. One particular rooster, a particular motion that I make, and rocks suddenly coming towards him in the air. My cats, a certain rumbling noise outside, and another cat about to come through the kitty door in the window.
The cats believe that they're about to be fed, or that another cat is about to come through the kitty door. The chickens believe that they're about to be fed. The rooster believes that I'm throwing a rock towards him.
The behaviour verifies this. The issue, of course, to return to it... is that the only plausible explanation for their behaviour? Or better perhaps...
By what standard do we determine which report of non-linguistic belief is best?
Suit yourself. My position survives the same critique(s) I've levied towards others. What more could you ask for?
:-|
Stick to the rhetoric. Most people are moved more by it anyway...
;)
My criticism has been that your account, or something like it, could be more adequate, more comprehensive, if it allowed for more distinctions, as I have already explained. I haven't said it is fundamentally wrong. In any case I'm not interested in going over it all again.
The nuance isn't simple. Basic understanding comes first. The nuance is had in the consequences of the basics.
What does linguistic belief consist of?
What does non linguistic belief consist of?
Those two questions need to be correctly answered. If both kinds are to be sensibly called the same thing... "belief"... then it must be the case that they consist of the same basic elemental constituents. The same 'ingredients' as it were. Since belief is accrued, and at conception we're completely void of any and all belief, it must begin simply. Thus, whatever rudimentary belief consists of, so too must the more complex, but not the other way around, which is precisely what classic epistemology has done by virtue of conflating a report of one's belief with one's belief, and holding that the content of belief is propositional.
My reports about cat and chicken belief a few posts back were in propositional form. It quite simply does not follow that the content of the cat and chicken belief is propositional. The content was correlation and the formation thereof(the act of drawing the correlations) is existentially dependent upon an agent capable of drawing correlations between different things and/or itself.
Right, and as I explained, there is no justificatory grounds for denying that an agent believes everything which is happening in one's dreams. It's just a matter of how one uses the word "believe".
I think that for the sake of an epistemological investigation we need to place some restrictions on how we use the word "believe", we need to find a definition to agree on.
We're not even close. You think that belief consists of making mental correlations. I think that belief consists in maintaining the same thought for an extended period of time. Banno thinks that belief is something completely different. There are chasms between each of our opinions.
Then any objection you levy against that claim that you just agreed to renders your position incoherent.
All I agreed to, is that you have been using the word "believe" in a way which is different from what I would like. I see your usage as ambiguous and counter-productive. So it's completely consistent and coherent for me to object to the way that you use the word. And of course, you have objected to my requests to restrict your usage. Therefore no progress has been made.
What I am at pains to point out is that neither you nor I make the rules governing all mental ongoings. Seeing how both thought and belief are - in part at least - made up of mental ongoings, it only follows that neither you nor I make up the rules governing either thought or belief...
Now, off with your semantic twaddle.
If your notion of "belief" contradicts this, it's wrong.
Your notion of "belief" is a meaningful sense.
Your notion of "belief" consists entirely of mental correlations between things.
If you claim that all belief consists of propositional content, then either you deny the existence of belief prior to language, or you claim that propositions are not existentially dependent upon language. You've already claimed the former. Admitting the latter, for you, would force you to admit changing your claims in mid argument.
Neither of those necessary consequences are acceptable.
So, I've shown that your position suffers a number of different reductio ad absurdum, and yet you remain tried and true, tied to an argument that not only suffers such a fate, but more importantly it just doesn't have what it takes to take account of pre and/or non-linguistic mental ongoings.
You don't want to call pre and/or non-linguistic mental ongoings "belief"? Fine by me. You want to continue to believe these things. Fine by me.
You want to provide an example of anything meaningful that does not consist entirely of an agent drawing mental correlations between things?
All senses of both terms "thought" and "belief" consist entirely of mental correlations drawn between things. If you agree, I suggest you follow along and object to what you disagree upon. If you want me to continue to criticize your usage of the term "belief", then either you're not understanding the faults being shown, or your conviction outweighs overwhelming evidence to the contrary.
Belief such as Jack's is formed each and every time an agent is chasing something which hides behind the toaster. An everyday occurrence. So, there are cases of non-linguistic agents' forming and/or having thought and belief about that which is existentially dependent upon language. No language, no toasters.
But calculus... that is also existentially dependent upon language, and a non-linguistic agents' mental correlations cannot possibly contain and/or have any basis whatsoever in calculus.
So, some things that are existentially dependent upon language can be an elemental constituent of non-linguistic mental ongoings. Other things, not so much. Here, we need a distinction of some sort in order to further discriminate.
My report of Jack's belief is not equivalent to Jack's belief. My report needs only to draw the same or similar enough correlations to take proper account of Jack's correlations. If I accurately determine the content of the correlations being drawn in Jacks' mental faculty, I've offered a true report that is not attributing propositional content to Jack's mental ongoings.
I believe in free will. Therefore I assert that there is no such thing as the rules governing mental ongoings. Until you prove determinism, your pain is in vain. So go ahead, dismiss reality as semantic twaddle and suffer alone.
The premise that belief consists of mental ongoings does not validate your conclusion that mental ongoings consist of belief.
When an agent touches fire it learns that fire causes pain by virtue of drawing a causal connection between the touching and the pain that follows. That mental correlation is the agent thinking/believing that the fire cause the pain. The fire becomes meaningful to the agent as a result of this. The agent's thought/belief is true.
In Witt's view, the agent's belief cannot be justified, nor need it be for the behaviour is the end of justificatory regress. I do not think that Witt would admit that the agent knows that touching fire causes pain, and rightly so, for such knowledge is empirical and as such it requires justification, and the agent is incapable of reporting upon it's own belief.
On my view, that's all bound up in yet another flaw. A consequence borne of conflating a report of belief with belief. I think it's absurd to hold that knowing touching fire causes pain requires offering an account of it. All knowing that requires is an agent capable of touching fire, feeling pain, and connecting the two.
While the justification requirement makes sense when it comes to knowledge claims, it is a fatal flaw in one's position if s/he holds that making a claim is necessary for having knowledge. JTB came as a means to discriminate between those who claim to know something and those who can provide the ground for such claims.
The ground ends. The regress ends. It all begins at getting burned.
So, there are some Christian philosophers who are saying that there are very basic arational beliefs that support Christian conclusions. This would mean that the statements "This is a hand," and "God exists," are equivalent, neither require a justification in that they are arational. I don't see this as a correct interpretation of what Wittgenstein is putting forward in OC.
I don't see that Moore's statement, "I know this is a hand," is equivalent to "I know God exists," i.e., I don't agree that Wittgenstein's critique of Moore's statement would be the same critique of "I know God exists." In the former statement the doubt makes no sense. It's hard to imagine such a doubt. Note though, in the latter statement (I know God exists."), it makes perfect sense to doubt that such a being exists. It's not in any way equivalent to "This is a hand." Many Christians want to say that their inner sense of God is equivalent to having a hand, i.e., it's so basic that it's foundational to their beliefs. So, in this sense it's beyond knowing, it's a kind of arational belief that goes beyond the epistemological.
This to me is an attempt to escape the required justification for the existence of God. And, many Christians are using Wittgenstein's ideas to claim that many of their beliefs are this way. This makes me ill. :sad:
You may be querying the basis of the way in which Christians are using Wittgenstein's ideas but I find your claim that it makes you 'ill' as a bit extreme, even though I realise that you may be speaking metaphorically.
I have not read Wittgenstein in any way as much as I wish, and I do hope to read his writings more fully at some point. However, from some of what I have read I have wondered if there is some mysticism in his thinking insofar as queries the limits of language. So, what you have just written about Christians incorporating his ideas does seem to be one be one possible way of using his ideas, although it is possible that his ideas and statements have so much ambiguity that they could be interpreted to fit religious views or atheism.
No, I literally threw up. :groan:
Extreme or not, I find their interpretation of W. to be very problematic to say the least.
That is unusual, and I find it interesting, although horrible, because so far no particular idea or use of ideas has ever made me vomit literally. So, I am interested to know why it affected you so much. Was it because you think that it is a complete misuse of the basis of his own philosophy and intention?
I can see why:
“Aesthetics and religious belief are two examples - for Wittgenstein, of course, crucially important
examples - of areas of thought and life in which the scientific method is not appropriate, and in which efforts to make it so lead to distortion, superficiality and confusion.
In his lectures on religious belief he concentrates only on the first part of this conviction - the denial of the necessity to have reasons for religious beliefs. In their rejection of the relevance of the scientific mode of thought, these lectures are of a piece with those on aesthetics.
In seeking to answer the why and how of aesthetic
understanding, we are not looking for a causal explanation.
“Russell and the parsons between them have done infinite harm, . infinite harm.' Why pair Russell and the parsons in the one condemnation? Because both have encouraged the idea that a philosophical justification for religious beliefs is necessary for those beliefs to be
given any credence. Both the atheist, who scorns religion because he has found no evidence for its tenets, and the believer, who attempts to prove the existence of God, have fallen victim to the 'other' - to the idol-worship of the scientific style of thinking. Religious beliefs are not analogous to scientific theories, and should not be accepted or rejected using the same evidential criteria.”
Wittgenstein did not wish to see God or to find reasons for His existence. He thought that if he could overcome
himself - if a day came when his whole nature 'bowed down in humble resignation in the dust' - then God would, as it were, come to him; he would then be saved.”
It is clear from remarks he wrote elsewhere, that
he thought that if he could come to believe in God and the Resurrection - ifhe could even come to attach some meaning to the expression of those beliefs - then it would not be because he had found any evidence, but rather because he had been redeemed.
From Wittgenstein’s biography)
prepare to vomit
I don't know what Wittgenstein said or meant, but I think this approach provides a framework for a valid belief in God. If I have experienced God directly, I believe he exists. You have not, so you don't.
Quoting Sam26
There is no required justification for the existence of God.
So, what's your point, and how does this lead to me recanting or reconsidering what I said. I've read enough of Wittgenstein to know that he had a mystical side. All you would have to do is read my thread on NDEs, and you would know that I'm not against the mystical. And by the way, the "make me ill" comment could also easily be made against the materialists, naturalists, and many atheists who think that their way of seeing the world is somehow intellectually superior to any view that looks beyond the material world. So, to be fair I'll add that little bit to the mix. And, I don't think that Wittgenstein is some kind of god, i.e., even if you pointed to something W. said that contradicted my point, that somehow isn't going to make me think I'm wrong. I enjoy W., and I think he contributed some important things to philosophy, but I don't think he was correct about all his musings. I'm sure you don't either.
I don't know whether there is a God or not, but it seems to me that if you're going to claim such a thing, you need some kind of justification. And, I don't think anyone is warranted in believing in some kind of inner knowing or inner justification.
What makes me use the phrase "makes me ill" in relation to religious belief is the conviction that they have some special access to knowing that the rest of us don't; and where this kind of thinking logically leads.
Justification is a linguistic concept, and the use of the concept takes place within our epistemological language, viz., propositions. The idea that justification is something within us, is just anathema to me, and to my way of understanding W. If you don't get anything out of W. surely this would be the one thing that sticks out for most student of W., viz., that meaning doesn't arise from within. Meaning by its very nature, is public; and, recently this has been argued about in the many threads that have sprouted up about W.'s thinking.
Second, as I've mentioned in the first post that kicked this recent tranche of posts, comparing the proposition "I have hands," to "God exists," in terms of W's bedrock or hinge-propositions is a bit of a stretch (which is what Pritchard is implying). One can see this if you compare doubting that one has hands to doubting that God exists. Hell, even Christians doubt their belief in God from time to time, but I'd find it amazing if they doubted the existence of their hands in ordinary circumstances from time to time. The key, at least the way I'm interpreting W., to understanding what a basic belief (or Moorean proposition) is, is that doubting them doesn't make sense, at least generally.
Now of course you can retort and claim that you have direct experiences with God, and if this is really true, then you would have access to something most people don't. However, most of these claims are very subjective, and are open to many different interpretations. Not only that, but they tend to be self-sealing, you can make any experience you have conform to a belief in God in some way. I compare this to the way many Christians, not all, but many, think of answers to prayer. There isn't a non-answer, every event in their lives is made to conform with an answer, i.e., even if they didn't get what they specifically prayed for, it was an answer, specifically a no answer. It's a self-sealing view. It doesn't allow for counter-evidence. What would a non-answer look like? In the same way, if every experience you deem to be of God, is of God, how would you know if you're wrong. These kinds of experiences are even worse than pointing to something internal and saying, "There is my pain." Why? Because at least with a pain there is something external to latch on to, a cry or a scream. But, the experiences many religious people refer to as "an internal knowing" have nothing external to latch on to. There is no corresponding ouch or other kind of thing that attaches externally to the experience, other than a claim. Surely this is the proverbial beetle-in-the-box, maybe worse.
I claim that the Gettier problem is a philosophical non-issue, driven by the semantic confusion of conflating subjective certainty with objective justification. Far from undermining JTB, it exposes a misinterpretation of how justification works within language. I find the debate a waste of time, fixating on contrived cases that distort epistemic practices and offer no substantive challenge to JTB.
JTB is a practical working definition of knowledge. A person knows something if they believe it, it’s true, and they have objective justification (good reasons for supporting the truth). In everyday contexts, JTB works seamlessly: I know it’s 3:00 PM if I believe it (based on a clock), it’s true, and I’m justified (the clock is reliable). The Gettier problem claims to show that JTB is insufficient, but it relies on a misunderstanding of justification, not a defect in the definition.
People often conflate subjective certainty (feeling justified) with objective justification (having good reasons as required by JTB). For example, if I believe a clock shows the correct time because clocks are generally reliable, then I have subjective certainty. But if the clock is stopped, I’m not actually justified, my reason fails to connect to the truth. JTB demands objective justification and conflating it with subjective certainty creates confusion about JTB.
Wittgenstein’s language games reveal that justification is not a universal standard but a context-specific practice (or a practice that extends across our forms of life), varying across epistemic games like testimony, logic, sensory experience, and linguistic training. Each game has its own rules:
In the sensory experience game, justification comes from trusting perceptions (e.g., a working clock), but a stopped clock violates the rule.
In the logic game, justification follows from sound reasoning, but false assumptions (e.g., about Jones) undermine it.
Subjective certainty arises when a person follows a game’s rules (e.g., trusting a clock), but objective justification requires those rules to hold up (e.g., the clock must work). The Gettier problem misapplies these rules, treating subjective certainty as objective justification.
In Gettier cases, subjects have subjective certainty but lack objective justification, yet philosophers debate whether their true beliefs are JTB. This is a semantic error:
In the clock case, Smith feels justified (sensory experience game: clocks are reliable), but the stopped clock means he’s not objectively justified. His true belief is lucky, not knowledge, and JTB correctly dismisses it.
In the job case, Smith feels justified (logic game: strong evidence about Jones), but his false assumption undermines objective justification. The truth is coincidental, and JTB rightly denies knowledge status.
The problem arises when philosophers equate subjective certainty with JTB’s justification condition, then puzzle over the lucky truth. This is a linguistic trap, debating justification or knowledge abstractly, ignoring the contextual rules of our language games
The Gettier problem is unproductive because it’s rooted in this semantic confusion and disconnected from real epistemic practices:
Stopped clocks and coincidental coin counts are artificial, and they're unlike the everyday scenarios where JTB thrives (e.g., trusting testimony in court, and reasoning in science).
The debate hinges on misusing justification (subjective vs. objective) and knowledge (everyday vs. philosophical), turning epistemology into a semantic game.
Gettier cases fail as knowledge because the justification isn’t objective (due to poor reasoning or luck). JTB stands firm; the debate adds nothing.
Wittgenstein’s language games dissolve the problem by showing that justification and knowledge derive meaning from their use in our form of life (or language games). Philosophical confusion arises when we take these terms out of their natural games, seeking universal definitions. In the sensory experience game, a stopped clock isn’t a valid justification; in the logic game, false assumptions aren’t either. JTB works within each game’s rules, and Gettier cases are outliers that violate those rules. The debate is a philosophical misfiring, obsessing over edge cases instead of clarifying how we justify beliefs in practice.
Conclusion: The Gettier problem is a distraction, not a crisis. It stems from conflating subjective certainty with objective justification, misapplying the contextual rules of language games like sensory experience or logic. JTB remains a robust definition: knowledge requires a true belief with objective justification, which Gettier cases lack. Philosophers should abandon this semantic quibble and focus on real epistemic practices, viz., how we use testimony, reasoning, or perception in daily life. Let's leave the Gettier puzzles behind to the philosophers entangled in semantic quibbles and focus on the practical language games where knowledge really lives and thrives.
I don't see JTB as robust at all. It is simply filled with question begging. P is true? But how does one get to the truth of P being the case without assuming an epistemic connectivity? Someone like Rorty would say when is possessed by the assumption that someone has ten coins in his pocket, and makes a justified inferential move, then the actuality of there being ten coins in the pocket in question only makes a difference when thoughts turn to THAT language game, that is, talk about actualities and vis a vis beliefs. There is no truth that can be affirmed about P apart from the affirmations made about P, and these are hopelessly indeterminate. And so justifications: can a justification be pulled apart from ontologies?; that is, saying P is the case, a fact, but are facts independent of the affirmation? Is this an impossible question, because the only way to witness its validity would be to justify and affirm of deny. It is crazy to think P is true can be analytically detached from justification. And belief: a single term comprising truth and justification. So sure, JTB is robust IN common usage of language, but philosophically, it is a thesis that falls apart.
I think of JTB like I think of time and its "parts": a single term comprising past, present and future, yet the past can only conceived as a present event, and the future, in the conceiving of the past, is an anticipation bound to what is being anticipated, which is something from the past that seizes upon the occurrent event and tells us what it is; and then the present, apart from past and future, loses all meaning. JTB is, like all concepts, self annihilating.
Knowledge as Justified True Belief—Situated in Language and Life
(Merging with Wittgenstein)
I want to defend a classical claim of JTB with a contemporary twist. I hold that knowledge is justified true belief. However, I will claim that JTB only becomes stable when we embed it in Wittgenstein’s later philosophy: language-games, meaning as use, family resemblances, rule-following, the beetle analogy, the private-language argument, and the hinge propositions from On Certainty. Add to this an analogy I draw from Gödel’s incompleteness results: just as formal systems require unprovable truths to function, our epistemic practices require certainties that are not proved from within the practice but make proof possible. That, in a sentence, is my picture.
Let me restate JTB simply. To know that P is to believe P, to have P be true, and to have genuine justification for P. I emphasize genuine. Much of the literature treats Gettier as a mortal wound to JTB. I don’t. Gettier cases work only if we confuse seeming justified with being justified. If the support for a true belief essentially depends on a false ground, the belief fails the J-condition, full stop. I mark this with an anti-false-grounds constraint: justification must not essentially rely on falsehood. That preserves the classical core without endless epicycles.
Now, what do I mean by justification? In practice, we justify in five primary ways (the five ways are not exhaustive), each with its own standards:
1. Testimony—we lean on credible sources, expertise, honesty, and corroboration.
2. Logic—deductive validity and inductive strength.
3. Sensory experience—trained observation, intersubjective checks, calibrated instruments.
4. Linguistic training—competent grasp of concepts and criteria; knowing how a term applies.
5. Pure logic/tautology—truths true in virtue of form.
These are not abstract algorithms floating above life. They are language-games, rule-governed practices situated in our forms of life. “What counts as a good reason here?” is answered inside the practice: replication and statistics in science, chain-of-custody and cross-examination in law, careful term use in conceptual analysis. Meaning is use: we learn what “justify,” “know,” and “evidence” do by watching how they function in these games. And because concepts work by family resemblance, I don’t hunt for one essence of justification; I look for overlapping patterns that guide our reasoning.
Two Wittgensteinian reminders guard the gates. First, the beetle in the box: meaning isn’t secured by pointing to a private inner object, “my beetle;” it’s secured by public rules of use. Second, theprivate-language argument: without public criteria for correctness, the distinction between using a word correctly and thinking I’m using it correctly evaporates. The epistemic parallel is straightforward. Being justified is not the same as feeling justified. That distinction only survives if standards are publicly learned, shared, and, crucially, open to correction.
Related to this is a small but important grammatical point. We use “I know” in two ways. There is an epistemic use, truth, belief, and justification that meets public criteria, and there is a convictional use, an expression of inner assurance. Conflating them produces two classic mistakes: dogmatism (conviction masquerading as knowledge) and hyper-skepticism (demanding maximal proof where our practices don’t require it). Keeping the senses apart does quiet philosophical work.
So far, I’ve kept to the foreground of justification. Now the background. Following On Certainty, I hold that our practices of giving and asking for reasons presuppose hinge certainties, things that “stand fast” so doubt and proof can get traction. Hinges are not items of evidence. They are the conditions under which evidence counts as evidence.
I distinguish two kinds. Linguistic hinges are certainties embedded in how we talk and understand: that words generally retain their meanings; that others understand me; that our talk of the world hooks onto a world. Non-linguistic foundational beliefs are certainties carried in stable patterns of action, pre- or non-verbal, but still beliefs in my sense, acquired and held within a form of life. For example, our practiced confidence in a stable, manipulable environment, the way ordinary engagement presupposes a world with enduring objects and reliable regularities. We do not typically state these as propositions; they are expressed in what we unhesitatingly do.
Hinges also come in layers. At the base are bedrock hinges, largely immutable without collapsing inquiry: there is an external world; other minds exist; meanings are generally stable. Remove those and you haven’t revised a theory; you’ve disabled the language-games that make reasons possible. Above bedrock are cultural–historical hinges that can shift, think of the movement from geocentrism to heliocentrism, without destroying our capacity to inquire. And then there are personal–experiential hinges, what stands fast for a particular life, which can shape what one finds immediately plausible. One more point here: testimony functions as a social hinge at the general level. If we tried to doubt testimony wholesale, science, history, education, and ordinary life would unravel. We can and should scrutinize particular reports; but general trust stands fast.
This is where my Gödel analogy enters. Gödel showed that sufficiently strong formal systems contain true statements unprovable within the system. My claim is that epistemic practice works the same way. It contains indispensable certainties unprovable within the practice. These are not defects. They are structural necessities. Both systems contain an “outside” that enables the “inside.” Hinges sit outside the inferential game yet make the game possible. In this picture, the unprovability of hinges is not a concession to dogma; it’s a sober description of how our games of reason actually function.
Let me turn this into a method you can apply.
1. Fix the language-game. What practice are we in, experimental science, legal reasoning, ordinary observation, mathematics, or conceptual analysis?
2. State the proposition precisely and register the belief state.
3. Assemble the reasons via the relevant methods: testimony, logic, experience, linguistic competence, pure logic.
4. Apply the public criteria that govern the game: credibility rules, inference standards, observational protocols, and correct concept use.
5. Screen for defeaters and enforce anti-false-grounds: if a key ground is false, justification fails.
6. Identify the operative hinges. Does the claim tacitly require denying bedrock? Which cultural or personal hinges are active? Is general trust in testimony doing enabling work here?
7. Disambiguate “I know.” Reserve the epistemic use for claims that meet public criteria; mark convictional uses honestly as conviction.
On this method, the verdict “S knows that P” states something robust: P is true; S believes P; S’s justification meets the public standards of the operative language-game; it does not essentially rely on falsehood; and it rests on, without trying to prove, the relevant hinges.
Objections come predictably. “Isn’t this relativism?” No. Truth remains mind-independent. Practices differ in criteria, but those criteria evolved to track reality, replication, cross-examination, calibration, and proof. “Isn’t this dogmatic?” No. Bedrock hinges are not arbitrary commitments; they are pragmatic necessities. Deny them, and you do not tidy up your theory; you lose the very game of giving and asking for reasons. “Isn’t it circular to presuppose what you need?” No. I do not deduce hinges; I show their role. That is a grammatical elucidation in Wittgenstein’s sense, showing the conditions under which our concepts do what we use them to do.
Why prefer this to bare JTB? Because it clarifies what “justification” amounts to in real life, public, trained, practice-relative reasons, while hardening justification against Gettier with the anti-false-grounds constraint. It explains why justification can’t be private. It ends regress without skepticism by acknowledging hinges where they belong. And it integrates language and life: knowledge isn’t a disembodied logical state, nor a private feeling; it is belief and truth joined by reasons that count within the living practices of a community, standing on certainties that enable those practices to work.
This is the theory I’m offering: classical JTB disciplined by Wittgenstein, undergirded by hinge certainties, and illuminated by a Gödelian insight. It’s not an abandonment of rigor; it is a clearer picture of where rigor lives.
True - What is truth? If knowledge requires truth, then don't we run into a problem that we also have to know if something is true?
Justification - What is justification? Is it proof that something is true? Do we know what is justified? In which case, how do we justify our justification?
Belief is at least straight forward. "A claim that X is a real state." We can of course add "possibly real", but the "possibly" must be believed to be a real state vs "impossibly".
So how did Wittenstein tackle this? "Knowledge is a web of beliefs."
Justification - A whole bunch of people hold this web of beliefs.
Truth - Its true that this web of beliefs exists.
Belief - The web. And yes technically we've just create a whole other belief that's not really proven but it WORKS. And that's the key. As long as it works like science giving us thing we can use correctly in reality, we're all good.
Honestly...kind of a dodge around the issue with fancy wordplay as a lot of philosophers attempt to do. Wittenstein abandoned any formal analysis of knowledge and tried a descriptive approach. The problem with a descriptive approach is that it describes how we get along, and that getting along works, but avoids the larger question about why it works. Wittenstien wouldn't have an answer to a society that based their entire culture around a sky God that made it rain. This society would be largely functional and have enough common predictability with a scientific culture, so people would get what they needed out of it. Wittenstein wouldn't be able to answer why this culture was inferior to another if the outcomes were the same or even better, even though its clear this system lacks real 'true' knowledge by relying on a belief system of a sky God.
Its a very, "Live and let live" approach to knowledge and demands further questions and follow ups. I have my own theory of knowledge if you're interested Sam. Its basically a break down of knowledge into contextual deduction, and from there a way to rationally analyze induction through a hierarchy. I know I've critiqued your works in the past, feel free to do so in return if you're interested. Its intended to be approachable to even people without a philosophy background, but there is a summary below from the first poster that I approved if you need to organize your thoughts. https://thephilosophyforum.com/discussion/14044/knowledge-and-induction-within-your-self-context/p1
When I separate epistemic “I know” from convictional “I know,” I’m not being cute with language; I’m blocking a well-known error path where confidence is mistaken for knowledge. That has operational consequences (e.g., whether we act on a claim, fund it, publish it, or treat it as settled).
When I distinguish justification from proof, I’m not hedging; I’m aligning the concept with real practices (science, law, measurement, math) where we need defeater management and anti-luck conditions, not impossibly global proofs.
When I talk about hinges, I’m not inventing mysticism; I’m displaying the enabling conditions of the game, exactly the places where attempts at global doubt collapse the practice that doubt presupposes.
Philosophy earns its keep when it sharpens the rules of the game so that good methods win and bad ones wash out. That’s what I’m doing: specifying the norm-set that separates knowledge from confidence. If someone’s theory survives these gates, public criteria, anti-false-grounds, practice-safety, defeater screening, I’m happy to call it knowledge. If it needs us to blur meanings, relax standards, or ignore failure modes, then yes, I’ll call that wordplay.
I admire the clarity of this position -- many thanks.
As you no doubt know, there is a question about JTB concerning whether "true" and "(genuinely) justified" are independent criteria. How would your Wittgensteinian version of JTB respond to this?
Short answer: on my view, truth and genuine justification are conceptually independent but methodologically coupled. “True” says how the world is; “(genuinely) justified” says your reasons meet the public criteria of the relevant practice. They are not the same property, and neither reduces to the other, but my Wittgensteinian add-ons (public criteria, anti-false-grounds, practice-safety, and hinges) are precisely there to lock justification onto truth-tracking without collapsing them into each other.
Knowledge on my account = truth + belief + this kind of disciplined justification (public-criteria, no false grounds, practice-safe), all within the hinge-enabled framework. That gives you a clean separation of properties and a principled explanation of why good justification is not mere social agreement but a world-tracking practice aimed at truth.
I didn't mean you, I was commenting on Wittgenstein.
Good. So what we want to know is, does the coupling of the methodologies for determining what is true and what is genuinely justified result in a vicious circle?
That it is a circle seems clear, but that may not be a problem. We might start by asking, is it possible to determine what is true without using the methods that "lock justification onto truth-tracking"? -- that is, without engaging in justification?
I'm guessing not, but then how do we respond to the objection that we have "collapsed into each other" the criteria for truth and justification? Note that this objection doesn't depend on claiming that justification has been reduced to "social agreement," opening the door for some invidious form of relativism. The criteria for both truth and justification can be as "objective" as you please, but we still have the problem of whether they are indeed two separate legs of the tripod.
What do you think?
Great, this is exactly the pressure point to push on, and here’s my view.
There is a circle here, but it is a benign, hinge-supported feedback loop, not a vicious circle and not a collapse. Truth and justification remain conceptually distinct, two different “grammars” in Wittgenstein’s sense, even though, in practice, our only route to truth runs through justificatory methods.
Truth: how the world is (a world constraint on speech acts).
Justified: whether one’s reasons meet the public standards of the operative language-game (science, law, everyday perception, math).
We don’t reduce truth to justification, and we don’t pretend justification is free of truth. We couple them so that justification tracks truth (anti-false-grounds + practice-safety), and Wittgensteinian hinges stop the regress (and circularity) that would make any coupling impossible.
Why this isn’t a collapse (three quick tests)
I can be genuinely justified yet false. Example: at T1, I check the official schedule, the app, and the platform announcement, public criteria are satisfied. At T2, a last-minute disruption cancels the stop. Justification stands (by the practice’s rules at T1), truth doesn’t. They come apart.
Luck test (Gettier without false grounds; environmental luck).
I can be true yet unjustified: I guess, and I’m right. Or I form the belief by a method that would easily be wrong in nearby cases (Fake-Barn County). That’s truth without knowledge because it flunks practice-safety. Again, they come apart.
Methods that systematically miss reality (bad calibration, poor replication, unchecked bias) are revised or rejected. That asymmetry, the world’s recalcitrance, shows that justification is answerable to truth, not identical with it.
Conclusion: Different roles, different failure modes, no collapse.
Why the “circle” is benign, not vicious
You asked: “Can we determine what is true without the very methods that ‘lock justification onto truth-tracking’?” In practice, no, we have no non-method magic eye for truth. But that does not mean identity or vicious circularity.
It’s like a clear window and a landscape. You only see the landscape through the window, but the window isn’t the landscape. You can replace or polish the window; the hills don’t move with your squeegee.
The loop is externally constrained: prediction, intervention, replication, calibration, cross-examination, and defeater management are world-sensitive tests. When they fail, the world corrects us.
Hinges, bedrock certainties like “there is an external world,” “other minds exist,” “meanings are generally stable,” are not evidence; they are the conditions for evidence to count. They prevent regress without pretending to “prove” themselves from within. My Gödel analogy captures this logic: unprovable statements that enable the system are a feature, not a bug.
Why this isn’t “objective-in-name-only”
You’re right that objectivity matters, and I’m not smuggling in “mere social agreement.” Public criteria in this framework are geared to track reality:
Anti-false-grounds: your case for P may not essentially run through a false premise.
Practice-safety: given the domain’s recognized error profile, the same method wouldn’t easily have delivered a false belief in nearby cases.
Error-controls: replication, calibration, pre-registration, blinding, proper scoring (e.g., Brier), independent testimony, valid inference, and correct concept use.
These are norms with teeth. They preserve the independence of truth while bending methods toward it.
The tripod stays a tripod
Truth = world-constraint (not defined by our procedures).
Belief = our doxastic stance.
Justification = public rule-governed standing (anti-false-grounds; practice-safe).
Yes, the only epistemic way to reach truth is via methods, but method-dependence of access does not entail identity of property. The two legs, truth and justification, remain distinct, even as they are methodologically coupled and mutually calibrated by the way the world pushes back.
That’s my Wittgensteinian JTB: no collapse, no vicious circle, just a disciplined coupling inside hinge-enabled practices that keeps knowledge world-answerable.
Glad you agree.
Quoting Sam26
And this is the result we want. You make a strong case, which also has the advantage of replicating very closely what we actually do when trying to assess the validity of what we think we know.
I'll devote more time to this soon -- real life calls -- and focus on what may be the weak point: a somewhat cavalier acceptance of a "world" that is supposed to remain constant across multiple conceptions of justification. Is the "window/landscape" analogy good enough here? We can see the landscape, but not "the world" -- that might be an objection. But I need to think more about it. TBC.
Quoting Sam26
I would emphasize the ‘how’ more than the ’what’ in forms of life. Not just that the world has stable, reliable patterns. After all, all forms of life open up stable, patterned ways of engaging with the world. What is intrinsic to any particular form of life is how it opens up such a stable comportment. What is the qualitative nature of the way these patterns are organized, and when a qualitative pattern is transformed as one form of life becomes another, how does this change the way the world appears? It also seems to me that what is most significant about justified true beliefs for Wittgenstein is that securing the validity of a belief is not the reference
to a pre-existing fact, rule, picture, criterion or norm.
In his discussion of rule-following , Wittgenstein indicates that this is not enough for knowing what is true. Justification requires a creative, inituitive use of criteria, norms and facts that modifies them for the contingencies of actual situations.
I agree that forms of life are about the how of engagement, not only the what of a stable world. But I reject two further moves in your reply:
1) that “securing the validity of a belief is not the reference to facts/rules/criteria,” and
2) that rule-following requires a “creative, intuitive” modification of norms to count as knowledge.
On my account, facts still bite, and public criteria remain the arbiters of epistemic “I know.” There is skilled judgment in application, yes, but it’s judgment inside guardrails, not free-form creativity. That is a core difference.
Where I agree, and how I build it in...
Forms of life: the how.
Non-linguistic foundational beliefs aren’t just tacit endorsements of what the world is like; they show up in how we move, measure, compare, and correct. My framework already captures that “how” at the method level with practice-safety: a method counts as justificatory only if, given the domain’s known hazards, using the same method in nearby cases would not easily lead you to false. That is precisely about how we proceed in a form of life.
Transformations across forms of life.
When a qualitative pattern of practice changes (say, pre- to post-Copernican astronomy; pre- to post-germ theory), some cultural–historical hinges and method-norms shift. My layered-hinges view predicts that: bedrock hinges (external world, other minds, stability of meaning) remain; practice-level norms adjust; what counts as a good reason evolves publicly, not privately.
Where I disagree
1) “Securing validity is not a reference to facts/rules/criteria”
Wittgenstein’s later work denies that mere citation of a rule or fact settles anything, but it does not follow that justification floats free of facts/rules/criteria. His point is that application is shown in training, correction, and agreement in judgments, i.e., in the public criteria of the practice. So...
Truth remains a world-constraint (thin correspondence). If your model predicts rain and it doesn’t, the world corrects you.
Justification is publicly rule-governed: replication, calibration, valid inference, cross-examination, correct concept use, and defeater management.
Hinges are the enabling backdrop; they are not extra evidence but the conditions for evidence to count.
So, no: I don’t replace reference to facts/rules/criteria with “what works.” I discipline appeal to facts/rules/criteria by showing how they have epistemic force only in use, in the practice that allows us to teach, check, and correct.
2) “Creative, intuitive” modification of norms
What application requires is disciplined judgment, not creative norm-making. Yes, rules are “open-textured;" there is no decision-procedure that eliminates judgment. But that judgment is trained and answerable to public standards. If “creative” means improvisational within the practice (e.g., a physician integrating atypical signs without violating diagnostic criteria), I agree. If it means license to bend criteria ad hoc, I reject it: that collapses the difference between seeming justified and being justified. My anti-false-grounds and practice-safety constraints exist to prevent precisely that slide.
Bottom line...
I can happily emphasize the how of forms of life, indeed, I already do via practice-safety and my method-first account of justification. What I won’t concede is that justification floats free of facts, rules, criteria, or that it needs “creative, intuitive” norm-shifting to count as knowledge. In a Wittgensteinian JTB, facts still constrain, criteria still govern, and judgment still answers to the community that can teach and correct. That’s how we keep knowledge distinct from confidence while explaining how real inquiry actually moves.
Quoting Sam26
The question is whether justification is fundamentally a matter of rule-following within stable criteria, or of creative, situated responsiveness. You interpret “creative, intuitive” norm-use as “free-form ad hoc improvisation” unless tightly constrained. But I mean something more like Gadamer’s phronesis — a context-sensitive application of rules that inevitably alters their force.
As Joseph Rouse interprets Wittgenstein:
You emphasize that “facts still bite” and “truth as thin correspondence.” This is consistent with a realist bent, but I don’t see Wittgenstein as a realist. Wittgenstein sees “fact” not as a metaphysical anchor but as a role within a language-game. This is how “facts” remain practice-constituted and reality-constrained.
Quoting Sam26
Wittgenstein stresses that criteria gain their force through use, not through a fixed “guardrail” independent of practice. Are your guardrails themselves subject to evolution within forms of life, or do they function as transhistorical constraints? What does it mean to assert that some meta-level bedrock hinge remains? Why should it? Your inclusion of the concept of other minds and the external world as transhistorical reminds me that these are the very concepts that Husserl bracketed as part of his method of phenomenologically reducing presuppositions. I think Wittgenstein would be sympathetic to Husserl’s aim here. All hinges are ultimately contingent, because they are formed within ongoing historical processes of discursive interaction.
Here's a short answer:
Methods evolve; no, the core “guardrails” aren’t optional. The standards by which we employ justification (replication, calibration, Bayes, preregistration, etc.) are historical. However, the meta-level constraints that make any justificatory practice possible , publicity of criteria, other minds, an external world, and sufficient stability of meaning to teach/correct, are not optional add-ons. They’re what Wittgenstein would call hinges: not evidences, but conditions of sense for giving and asking for reasons.
Quoting Sam26
I think what you’re looking for is not some meta-level hinge, but the interwoven threads (family resemblance) that run though all hinges, not as a general overarching category (Wittgenstein never placed the general above the particular) but as that which emerges always in its own particular and unique way in actual use. Put differently, it seems to me what you’re talking about here is not itself a hinge, a belief, whether certain or not, but the condition of possibility for any hinge, any belief. For instance, the structure of temporality is a pre-condition for hinge beliefs, but we dont have to believe in time in order for it to make hinges possible.
Some further reflections on keeping truth and justification separate. . .
When we say, “The world pushes back,” what are we describing?
What if we changed the example from a prediction to an observation? I see a moist situation outside my window that appears to be rain; I offer genuine justifications for my belief, “It’s raining”; but when I go outside I discover that actually it had stopped raining quite a while ago, and what I saw from my window was the rainwater continuing to fall from the high trees in my yard.
What has happened here? Can I say that my belief in the rain was justified, but untrue? Shouldn’t I have taken into account the possibility of rainwater falling from the trees – a phenomenon I’ve seen many times before – when I provided my public-standard reasons for my belief? (the “defeater” criterion). That would make my belief unjustified; at best, I should have said that it was quite likely to be raining. But then again, my “JB” -- my assertion of belief plus justifications – was not offered as a piece of knowledge. Not if I believe in the JTB theory, anyway.
So -- at what point is justification only “genuine” if it indeed tracks the truth? You say, “I can be genuinely justified yet false,” and give the example of the cancelled train stop. Yes, it appears that you were justified in believing the train would come . . . but isn’t another analysis possible? Couldn’t we say, “We all know that train stops can be cancelled. You can affirm your belief that the train will come; you can give your genuine justifications for thinking so; but only the fact (truth) of the train’s arrival will turn this into a JTB, a piece of knowledge.”
I guess I’m asking how we should characterize a “JB” -- a belief that is genuinely justified, according to your criteria, but whose truth is still undetermined. Does a person who asserts a JB assert that they know it? Only the “know of conviction,” perhaps. If JTB is meant to be the definition of knowledge, we can’t say “I know X” until we discover whether X is true – we need all three legs of the tripod. So again, how should we describe “genuine justification” in a way that preserves some daylight between that concept and “true”? How carefully must we consider every conceivable defeater before saying that our justification is genuine?
These are reservations and puzzlements about the JTB concept in general, I think. I want to turn to your more focused version, with its use of Wittgensteinian hinge propositions, especially the idea that hinge propositions “stop the regress (and circularity) that would make any coupling [of methods for determining truth and justification] impossible.” But that will wait for a subsequent post.
BTW – I don’t think you and @Joshs have a serious disagreement about “creative, intuitive modification of norms.” Josh says:
As a third party following along, this seems to me quite compatible with:
Gadamer’s phronesis is not at all ad hoc, and I’m pretty sure Josh wouldn’t recommend that.
Amusingly, this is a case of not having rules for knowing when and how to apply rules! And as we know, the lack of “rules for rules” doesn’t make everything ad hoc and chaotic.
Quoting J
:100: :up:
In OC, Ludwig Wittgenstein sought to name these background conditions. He called them “what stands fast,” comparing them to the hinges on which a door turns. Hinges are not conclusions of reasoning but the enabling ground of reasoning itself. They anchor our language-games, steady our practices, and form the inherited background against which justification makes sense.
My thinking takes Wittgenstein’s insights as a starting point and extends them. Where he left fragments, I aim to bring structure. Where he hinted at distinctions, I will sharpen them. Where he suggested limits, I argue for expansion. Several themes stand out:
Certainty as enacted, not merely held. A hinge shows itself in seamless action before it is ever put into words.
The communal depth of hinges. Certainties are taught, imitated, and inherited; they belong to world-pictures, not to isolated individuals.
Doubt and knowledge as coin-faces. To doubt presupposes that knowledge is possible; to know is to stand in a space where doubt could, in principle, be raised. They are inseparable aspects of one grammar. “Certainty” here divides into two registers: subjective conviction (the psychological assurance of being right) and objective certainty (knowledge settled by public standards). Hinges make the coin itself possible, the background metal from which both sides are struck.
Memory and time as hinge-like. The continuity of self and past is not inferred but presupposed, anchoring knowledge and identity.
The limits of explanation. Every justification reaches a horizon where “why?” runs out; this is not a defect but a condition of intelligibility.
Rigid and elastic hinges. Some certainties are logically non-revisable (personhood, continuity of the world), while others can shift with practice (cosmology, measurement standards).
Language itself as a hinge. Grammar and meaning are not justified from outside; they are what make justification possible. Yet language is not bounded once and for all. As forms of life expand, so language expands with them.
The result is an epistemology that integrates Wittgenstein’s late philosophy with a broader framework of justification. I will argue that knowledge is not just justified true belief but Justified True Belief + Understanding. Understanding is not a private feeling but competence-in-practice: the ability to use words with public criteria, to handle defeaters responsibly, and to live within the background certainties that make doubt and knowledge possible.
My ideas are not a commentary on On Certainty, nor a retreat into quietism. It is an effort to extend Wittgenstein’s fragments into a coherent epistemology that remains faithful to his insight: that doubt has grammar, that knowledge is enacted within forms of life, and that ungrounded foundations enable inquiry rather than undermine it.
If Wittgenstein showed that the demand for infinite justification is misconceived, my aim is to show how his insight opens the way for a richer picture of knowing: one that begins with embodied certainty, grows through language, and reaches beyond supposed limits of expression. What stands fast before words is not a barrier but a foundation, the place from which our words can reach further than Wittgenstein himself allowed.
When I read Wittgenstein’s On Certainty, I can’t help but think about how it touches on questions we’re now facing with artificial intelligence. His remarks weren’t about machines, of course. They were about us, about the background that makes human knowing possible. But the more I’ve worked with his ideas, the more I see how they matter for thinking about the development of AI.
One of Wittgenstein’s simplest but most powerful points is that doubt only makes sense against a backdrop of certainty. I can doubt whether my car will start, but I can’t doubt that there’s a world in which cars exist. If I try to doubt that, I lose the very stage on which doubting makes sense. Now, think about AI. A system that treats all doubts as equal, as if “What is the capital of France?” and “Does the world exist?” were both just queries, misses something basic. Humans know how to sift idle doubt from meaningful doubt. For AI to be trustworthy, it will need something similar: a grammar of doubt, a way of recognizing which uncertainties are live and which are nonsense.
Another thought from On Certainty that strikes me is how much of our knowledge is enacted rather than stated. I don’t prove to myself each morning that the floor will hold me; I simply stand. Certainty shows itself in action. With AI, though, we tend to optimize for propositions: correct outputs, factually accurate answers. But there’s no hinge of action beneath it. Machines don’t “stand fast” in the way we do. That tells me we should be cautious about equating AI’s linguistic performance with human understanding. Without hinge-like certainties, embodied anchors, a sense of persons, continuity of the world — the words may ring hollow.
There’s also the question of inheritance. Wittgenstein says we are taught certain things without question. That’s our world-picture. AI, too, inherits a world-picture — its training data. What goes in as unquestioned background shapes everything that comes out. The danger, of course, is that we treat the dataset as neutral when it is already hinge-laden, already thick with assumptions. If we don’t examine that, the machine’s “certainty” may be nothing more than a mirror of our own blind spots.
Finally, Wittgenstein reminds me that explanations cannot go on forever. At some point, they end, and not because we’re lazy or careless, but because all justification rests on hinges that are not themselves justified. For humans, this is just how rational life works. For AI, it suggests that the demand for fully “explainable” systems may be a mirage. Like us, machines will have to rest on foundations that can be mapped, checked, and disciplined, but not explained away.
When I connect these dots, I come away thinking that On Certainty offers a kind of realism about intelligence, human or artificial. Knowledge isn’t just propositions strung together. It depends on hinges: embodied trust, inherited world-pictures, shared grammar, limits of doubt, limits of explanation. If AI is to grow into something we can genuinely trust, then what Wittgenstein saw about human knowing should not be ignored.
Returning to your 'raining' example, would you have said that you know it is raining? Justification is a slippery concept. It might be said that it would be natural to conclude that it is still raining if I see water falling. But then if I know there are high trees in the yard and that after sufficient rain water continues to drip from them, could I be said to be justified in my belief?
If it had still been raining would I then be justified in my belief, even though I didn't take into account that it could have been water dripping from the trees instead? If there had been no trees in my yard and I saw falling water and concluded that it was raining, would that have been a justified conclusion on the basis that events so unlikely as that the neighbor was spraying water over my roof with his hose need not be taken into consideration?
Assuming that we can say that some beliefs are justified, which might yet turn out to be wrong, and given that the truth cannot always be discovered, would it not be the case that sometimes we possess knowledge, but cannot know that we do? And doesn't that seem a little weird, that we might know something to be the case, but not know that we know?
I'm not sure, but you seem to think that if knowing isn't absolute, it isn't knowledge. This is a classic misunderstanding of what knowledge is.
We are not certain that language evolved separate of thought. The idea that thoughts are not dependent on lingustics, ignores that language does not need to be a complex chain of communication (internally or externally), it can also be argued that the thought itself has a linguistic dimension, a linguistic structure.
If we look back at what would arguably be a logical development of our cognitive abilities. Here we have an ape, using its instincts and pre-determined evolutionary knowledge of the surroundings and themselves, like any other species. But the demands of nature around this ape put so much pressure on him that his evolution starts to change through generations, demanding better and better ability to adapt to changing conditions. Slowly, evolution develops a more complex mental map of his surroundings, giving him the ability to understand context better, understand causality better. In order to adapt, the ape needs to utilize this understanding of causality and this is fundamentally an understanding of context over time.
Context over time is essentially linguistics, even if it goes on internally within the mental map of reality inside the ape. It is a form of understanding that requires a start and an end, like a sentence. It requires a context over time and a mental projection of possible context over time.
Add to that the importance of communication between apes, another result of evolution evolving the capacity for adapting to changing conditions. If the conditions are so complex that an internal context over time isn't enough to save entire groups of apes, the collective of apes forms the evolutionary trait to communicate this context between each other and thus language is spoken.
Beliefs require a context over time, it evolves out of the questions asked about reality around the ape. The question of why hunting the herd gives you food gives rise to the context over time being the herd giving you food. A belief forms of the herd's connection to you and your group of apes. And the need to adapt to changing conditions makes your context over time try to formulate a complex mental understanding of why the herd gives you food. A question, needing an answer. A language of forming more and more complex mental models of reality.
Language and our consciousness, our ability to reflect and create these mental models of reality might not be separable. I'm not in the camp believing that language formed cognition, but I do think that our complex language formed as part of the whole experience of the evolutionary trait to adapt to our environment. Without it, we couldn't form any context over time and thus we couldn't produce mental models that predicted our next moves, which is what separates us from pure instinctual planning or repeated behavior.
In my view, knowledge is more than just a correct guess or a strong feeling. I define it using a framework called JTB+U, which stands for justified true belief plus understanding. Let me explain this step by step in simple terms.
For something to count as knowledge:
It must be true: The statement matches reality, like saying "the sky is blue" when it actually is.
You must believe it: You accept it as fact, not just as a possibility.
It requires justification: You have solid reasons that anyone can verify, such as evidence from observation or reliable sources.
And it includes understanding (+U): You grasp the concepts involved and know how to apply them correctly, avoiding confusion in how words or ideas are used.
To build those reasons, I outline five main paths, though there could be others:
Testimony: Relying on what trustworthy people report, checked by seeing if multiple accounts agree, come from diverse sources, stay consistent, and can be confirmed independently.
Logic: Reasoning things out. Inductive logic looks at patterns, like expecting rain tomorrow because it has rained every cloudy day this week. Deductive logic follows strict steps, like knowing all squares have four sides, so this shape does too.
Sensory experience: What you directly see, hear, or feel, as long as conditions are normal and not misleading.
Linguistic training: Learning and using words accurately, so you do not mix up meanings.
Pure logic: Basic rules like "it is this or it is not," which help structure thinking but do not add new information.
A common issue is endless questioning: "Why believe that reason?" To handle this, I draw on ideas like "hinges"—basic certainties we rely on without proving them each time, such as the world existing or words keeping their meanings. These hinges fit into "language-games," shared ways we use words in everyday practices, and "forms of life," the broader patterns of how we live and interact.
I also distinguish two uses of "I know": One is factual and provable to others; the other is just a personal sense of certainty.
To determine if something is knowledge, I use a straightforward process:
State clearly what you claim to know.
Choose the path for your reasons.
List the supporting evidence.
Apply checks specific to that path.
Ensure no false information is included.
Confirm the method usually leads to accurate results.
Look for anything that might disprove it.
Decide based on that, noting what could change the conclusion.
This approach makes knowledge reliable yet open to updates.
How It Differs from Traditional JTB
The traditional view of knowledge, known as justified true belief (JTB), says it is a true statement you believe with good reasons. My framework builds on this but adds improvements for better clarity and strength:
Adding understanding (+U): Traditional JTB does not require fully grasping the ideas. I insist on it, so you demonstrate knowledge by using concepts properly.
Incorporating hinges and shared practices: Traditional JTB can get stuck in endless questions or tricked by coincidence. I address this with hinges (unproven basics) and language-games (group rules for words), providing a stable foundation.
Focusing on public checks and flexibility: Traditional JTB can seem personal. I emphasize reasons everyone can examine and allow knowledge to be revised if new evidence appears.
Providing a clear process: Traditional JTB is more of a definition. I offer a step-by-step method with rules against errors to make it practical.
These changes make the idea of knowledge more robust and easier to apply in real situations.
Sorry, the thread popped up and it's a long read to go through everything so I was just thinking I would address the original premises. Maybe the discussion has taken such routes already.
It was mainly my reaction to that premise of how language and thoughts/beliefs are separated, which I don't think is true. If it's already been addressed or if it doesn't add any dimension to the discussion you can ignore it.
Not if I accept JTB as the standard of knowledge. I can't say I know it's raining unless it's true that it's raining; truth is the third leg of the tripod. What complicates this is the justification part: Am I justified in saying "It's raining" even if I don't know it to be true? I'm not sure we have rules for this, or clear intuitions about what we would feel in every case. A slippery concept, as you say. In this case, I'd probably say "I believe it's raining" or "I think it's highly likely it's raining." But if you then asked me, "Is your belief justified?" the answer isn't obvious. I might say, "Yes, up to a point" or "I have good reasons." The crux is that, following @Sam26's thought, there needs to be some space between justification and truth in order for JTB to really be a three-legged tripod. I have to be able to be justified yet wrong.
Quoting Janus
A good question. Again accepting JTB, the answer has to be no, unless you're wanting to tweak how we understand "possess." If I don't know whether [consciously possess the knowledge that] X is true, then I can't claim to know X, according to JTB. It might turn out that "I knew it all along," but this is only a semi-serious use of "know," I believe. If Joe is revealed as the killer in a mystery movie, and someone says "I knew it all along" but during the film was guessing with the rest of us, we don't take the claim to knowledge very seriously.
Quoting Janus
This is the same problem as above, I think. What counts as "justified" is slippery. Also, your phrasing is a little ambiguous: Do you mean "turn out to be wrong that what we believed was justified" or "turn out to be wrong that what we named as a justification was incorrect"?
EDIT: Sorry, the last phrase should be "turn out to be wrong that what we named as a justification was correct."
The so-called “Gettier problem” rests on a sleight of hand. It trades on the difference between thinking one is justified and actually being justified. Gettier’s examples always contain a flaw in one of the three conditions of JTB: either the justification is faulty, or the belief is formed through a false step, or the connection between evidence and conclusion is too fragile to deserve the title of knowledge.
Take the stopped-clock case. A man looks at a clock, sees 2:00, and believes it is 2:00. By chance it really is 2:00, though the clock is broken. Here we do not have justified true belief at all. The belief is true, but the “justification” rests on a false ground: the clock is not functioning. That means the J (justification) condition fails. The man thinks he is justified, but he is not.
The same holds in other Gettier constructions. Somewhere along the line, one of the elements fails, usually the J. But if a case fails the J condition, then by definition it is not JTB. It is a case of apparent justification, not real justification. And if there is no genuine justification, then there is no knowledge to begin with.
When I speak of “real” justification, I mean justification that is not merely persuasive to the subject but actually satisfies the standards of knowledge: it must be publicly checkable, truth-conducive in the given context, and free of false grounds. Real justification is the kind of reason that anyone could in principle examine, replicate, and confirm, not just the kind of reason that feels convincing from the inside. Gettier’s examples work only by smuggling in defective grounds and then treating them as though they were genuine reasons. But if justification rests on a broken clock, a hidden falsehood, or a fragile inference that could collapse with the slightest change in circumstance, then it is not justification in the robust sense required for knowledge. It is a case of apparent justification: the subject thinks they are justified, but the conditions for knowledge have not actually been met.
This is why I see the Gettier literature as a long detour. It multiplies refinements to patch a problem that dissolves once we keep the standard for justification strong. By “strong” I mean publicly checkable, defeater-sensitive, and free of false grounds. If a justification fails those checks, it does not count as justification. Once that is clear, Gettier’s cases lose their force: they are examples not of knowledge, but of its counterfeit—instances where someone takes themselves to know but does not in fact know.
The dispute, then, is not a deep discovery but a confusion. Gettier showed that seeming to satisfy JTB is not the same as satisfying it. The lesson is valuable in its own way, but it is not the crisis it is often taken to be. The traditional JTB definition was never refuted; it was only misapplied.
I would put it this way: the real issue lies in how we understand justification. It is more than simply a person thinking they are justified. Genuine justification must be open to public testing, not just persuasive from the inside. Even so, it can fail—our best reasons are probabilistic, not infallible. But generally, these standards serve us well as guides to knowledge. And when a defeater arises that overturns what seemed to be justified, we recognize that the claim was never knowledge to begin with, but only something that masqueraded as such.
Maybe not “certainties”? So “proof” is aspirational, or ideal. But the metaphysic outlined - namely, proof sites within epistemic practice, and so proving cannot be applied to the grounds (certainties) underlying the epistemology - sounds right to me.
Quoting Sam26
I agree 100%. K=JTB remains instructive. Useful under Wittegenstein as it is under Plato, and for many others.
Quoting Sam26
Why isn’t the process of hunting for one essence the exact same process as looking for overlapping patterns that guide? I never understood the need to rebel against the notion of intelligible essence - whatever emerges and however it emerges that we call “knowledge,” it always still involves a “what it is to be.” K=JTB. Essence is what K speaks of. If K can ever be Justified as True, then Believing K is as much a possession of an essence as it is any other act that would demonstrate what one believes one knows. What is known, is what can be spoken; what can be spoken, distinguishes the essence of some thing spoken about. (But this may all be an unnecessary can of worms)
Quoting Sam26
I agree.
I see them each contributing to knowledge as like a verb and a noun contribute to an assertion. True and justified may seem to do similar work, but if we keep one as the verb and the other the a noun, we see the two functions they fulfill. “True” references “how the world is” - a truth, there in the world, like a noun is fixed in sentence. “Justified” is a the process of matching reasons with the public standards and quality of the game play - this is a process, like a verb.
So the ‘justified’ part of JTB is the process, and the ‘true’ part is an end goal achieved by that process.
This is why it makes sense that it is circular but not collapsing (it is sort of self-affirming, making something self-evident within the community).
And the reason ‘justified and true’ can seem unsatisfyingly circular comes from the sense that we can make nouns of verbs and verbs into nouns (I think). Instead of “justified” (verb) “true” (adjective for the noun) belief, we could abuse language a bit and talk about “truing up” (verb, process) a “justified” (adjective) belief. So as long as we keep process and target separate, justification and truth do not consume each other but are shown as distinct moments inside knowledge.
Yes.
Quoting Sam26
Yes.
Quoting Sam26
But doesn't this raise, again, the problem of the independence of justification from truth, and vice versa? If something can only be knowledge if it's true (along with J and B, and perhaps your U), what are the criteria for knowing when it is true, apart from those very justifications?
We have every (public and private) justification for believing the sky is blue (with all the usual qualifications about colors). If a defeater arose, such that we understood that the sky was not in fact blue, what has happened? You say, "The claim was never knowledge to begin with." But I say, "Yes, it was, on the JTB definition, because there was never an independent criterion for blueness apart from our justifications for believing the term applies to 'sky'. And that won't do, because we don't want an explanation of what knowledge is to leave room for that kind of error." This is a problem with JTB, not your very thorough argument that tries to rehabilitate it.
Here's another way to state the objection. How does a defeater work? It demonstrates that a previously held belief is untrue. How does it do this? By showing that the previously held justifications are inadequate to establish the truth of the belief. It can't talk about truth apart from the justifications. If we could know, or even think we know, truth apart from justifications, why would we need justifications to be part of knowledge? We could just "know the truth" and leave it at that.
In short, JTB is onto something important, but as formulated, it doesn't give us enough clarity about how truth and justification may be conceptually separated.
Quoting Sam26
Just curious: If I believe something without fully understanding it, and I'm asked to give an account of what I say I believe, can I do it? Or would this reveal that the B of JTB in fact doesn't apply? - that I literally don't know what I believe.
Hence, It seems to me, 's reservations.
We cannot know things that are not true. Despite what so many hereabouts supose.
___________
There is a tension in work on JTB.
On one side we have an account of knowledge as justified true belief, which we can treat as either a stipulation, or as a theory as to the nature of knowledge. If it's a stipulation, then that's mostly an end to the discussion. If it's a theory, then we should look to our use of "knowledge" to see how well the theory works.
Alternately, can go after account of the use of "knowledge" in our various language games - don't think, but look, as Wittgenstein extolled.
And when we look, we do find uses of "knowledge" that do not quite fit the JTB account.
But to be sure, at the core, we do not know things that are not true, we do not know things that we do not believe, and we ought be able to give an account as to why we know some proposal.
What might be problematic here is some expectation that there be no exceptions, no fuzziness as to what counts as knowledge and what doesn't.
The spectre of essentialism hangs over such expectations.
Yes. Though maybe more in my post directly above that one.
Quoting Banno
Right, there's something basically correct and useful about the JTB concept. I'd modify "an account as to why we know some proposal" to "an account as to why we believe or say we know some proposal."
Quoting Banno
I've objected to the unclarity around justification vs. truth, but this is important too. As you say, we can just stipulate what "knowledge" will mean, and get on with it, but that's not very satisfying. The fuzziness around "knowledge" and "knowing" is what JTB tries to de-fuzz. If we agree that we can know things that aren't certain, then there may be room for degrees of knowledge as well. If the justification-truth circle is indeed a vicious one, as I suspect it may be, then we may have to settle for a less-than-perfect conception of what it means to know something,
There are uses of know that don't fit the JTB account, but I would maintain they're not epistemic uses. Are you saying that there are epistemic uses that don't fit the JTB model? If that's what you're claiming, and I'm not sure that you're claiming that, give an example. There is a use of know, for example, that's just an exclamation of a conviction. In other words, it's just an expression without epistemic force behind it.
Quoting Banno
There is no one essence that fits JTB, there are just a series of language games that demonstrate how we justify beliefs in various ways. If we "look" as Witt would say, we can see these uses in practice via forms of life. I've added the +U because I think it captures the essence of this. The “+U” is what makes the difference plain. Traditional JTB can sound as if all you need is a true belief and some reason that looks like justification. But without understanding, justification can collapse into parroting words or leaning on a method you don’t really grasp. +U requires that the knower demonstrate competence in the concepts at play. That means being able to apply the idea correctly in practice, to handle nearby counterexamples without confusion, and to explain the checks that make the claim public.
It's an appeal to consistency, or perhaps in Davidson's terms, to holism.
"Knowledge" doesn't have an essence. Whatever an essence is.
Quoting J
There, perhaps, is the problem.
Sentences are true or they are false, regardless of any justification.
Again, Quoting Banno
You say that we have knowledge and that it may be overturned by new evidence. You say what we believed we knew is overturned, in which case it wasn't knowledge at all but belief.
Whether a belief is thought to be justified or not is a matter of how rigorous or extreme are the criteria we want to stipulate for our use that determine what counts as justification.
We have knowledge of how to do things, but that kind of knowledge is not true belief, whether justified or not, but rather understanding what to do and how to do it, and that kind of knowledge cannot be overturned but can be improved upon.
You know the saying "seeing is beleiving" well I prefer to say that seeing is knowing. If I am looking at a tree, I know I am seeing a tree (radical skeptical scenarios like I might be dreaming or being deceived somehow aside).
And I don't think any knowledge is absolute, it is all contextual.
Quoting J
Right, but I wasn't asking whether you would now, when you know it was not raining, say that you knew it was raining, but whether when you thought it was raining you would have said you knew it was raining. This relates to what I said above to Sam about the paradox involved in saying that we have knowledge, but that it may be overturned by further evidence.
On the strength of this paradoxical situation I would say we can only justifiably claim to have knowledge when we are certain that we do. I think this obtains when we can directly observe something to be the case, and also with analytic truths as in mathematics. But I am not saying any knowledge is absolute, so any certainty is contextual.
Quoting J
I agree. but then why say we have knowledge, rather than merely belief, if we are not certain? (And I repeat that I am referring here specifically to propositional knowledge, not to know-how).
Quoting J
I was thinking about it in the context of JTB. The idea was to question the idea of justification. I imagine a situation in which I believe something to be the case on grounds that would count as justifiable, but I am nonetheless not confident enough to think I know, and unbeknownst to me what I believe is actually true.
Quoting J
I meant the latter?that what we thought counted as a justification was not. The very idea of justification for a belief must rely upon other beliefs which we take to be knowledge, even certain knowledge, because if we took them to be mere beliefs it would then be belief all the way down, meaning no knowledge.
Quoting Sam26
This is a profound problem. Of course I acknowledge a logical distinction between feeling certain and being certain, and between feeling justified and being justified, and I have raised this very point many times before on these forums. The problem is that if we cannot be certain about being justified, if there is no observable state of affairs or logically self-evident criterion for justification then what we have is really a house of cards.
Then we can only be said to know something if we can be certain (as opposed to merely feeling certain
) that we are justified in counting it as knowledge. Whenever the truth is not obvious, then we cannot be certain that we know what it is.
Quoting Sam26
I come back to this because I'm not sure whether by 'absolute' you mean 'certain' or 'context-free'. No knowledge is context free because it is couched in language for a start, and language is obviously itself a context.
On the other hand, I say that within the appropriate contexts anything that counts as knowledge must be certain, because if it could be refuted then it could not count as knowledge. You might say that I'm showing "a classic misunderstandings of what knowledge is" but the reality is I would just be advocating a different understanding than yours, and I think mine makes more sense. You of course don't have to agree, but if you cannot see the possibility of different perspectives on this then you are playing the dogmatist.
I think that all your very pertinent questions come down to versions of the same issue, which @Banno has also picked up on, namely whether the T in JTB is doing any useful work.
Quoting Janus
Not if I was a proponent of JTB. Since, at that time, I had no way of knowing whether the "raining" statement was true apart from the cogency of my justifications, I would/should have said, "I believe I am justified in saying it's raining."
But this raises the deeper problem. When do I ever know something is true apart from having the right justifications? How can we make truth independent of justification -- make J and T genuinely separate criteria? Even the truth of analytic statements can be justified, indeed must be. Perhaps the idea is that some justifications cannot be insufficient or misguided. We can somehow know beforehand that there cannot be any defeaters.
And this connects with your questions about knowledge and certainty. I understand why JTB, taken rigorously, suggests that knowledge must be certain. Otherwise, how do we get "true" to do anything that "justified" isn't already doing? But if we decide to equate "true" with "certain," we get a possible answer.
The only issue with any of this is that it doesn't fit the way we actually think and talk about knowledge. I know the sun will rise tomorrow, in spite of being able to imagine defeaters. We'd have to say I didn't, on this view. Keeping J and T separate isn't worth paying this price, it seems to me.
There are some folk on TPF who do not actually believe in truth or knowledge, and you are the foremost. This has been pointed out quite a few times. So it's no coincidence that you wonder whether "the T in JTB" is doing any useful work, or, "When do I ever know something...?"
This is related to a recent discussion with @Relativist:
Quoting Leontiskos
Quoting Leontiskos
-
The objection to JTB seems to be this:
...That's a pretty wild understanding of JTB. The whole notion is incoherent, given that it presupposes that one can have knowledge of J independently of T and B (and knowledge of T independently of J and B, and knowledge of B independently of J and T). The "three independent ingredients" approach actually contradicts the whole epistemic notion of JTB.
That's kinda the right question and kinda the wrong question. The J in JTB is supposed to exclude cases of epistemic luck: the truth of your belief, if the belief was not formed in the right way, is not enough for us to count it as knowledge.
The issue isn't whether you know your belief is true — which in most cases amounts to knowing that you know — but whether your reasons for believing something is the case are connected in the right way to its being the case. That's what the J is meant to capture, and it leaves room for epistemic bad luck, where your belief turns out false but anyone would have formed the same belief, and it was a one in a million chance that in this case the evidence misled you.
The point about luck is not incidental: luck is not a strategy. In most cases, a strategy is only likely to produce the result we want, but it's not a guarantee. (Pareto dominance is the exception.) The question is the same with post-hoc justification, whether your strategy was likely to have produced knowledge; the question of whether it did in this case, is different, and must be judged differently.
The counterargument could be phrased this way:
1. Truth is always known via justification, and ensured by justification
2. Justification can never overcome the possibility of the one-in-a-million anomaly
3. Therefore, truth is never certain
This form of skepticism is a bit like the claim that epistemology is like a game of pool and no matter how good you are, there is always a chance that your shot will not pocket the 9-ball. Accidental contingencies are always involved, and therefore the best one can hope for is a good probability (or an ). Such a skeptic would say, "The only way to guarantee that the 9-ball is pocketed would be to pick it up with your own hand and place it into the pocket directly, but that would be cheating."
I think Gettier would just provide you with a case where the erroneous clock is publicly checkable and defeater-sensitive. For example: a case where multiple public clocks are all simultaneously erroneous.
Regarding the "false grounds," the key to the Gettier case is the difference between a material conclusion and a formal conclusion. So suppose we have two different cases:
Case 1:
J1. John looks at his clock which reads "2:00."
J2. John assumes that his clock is working but in fact it is not.
J3. John infers that it is in fact 2:00.
4. It is, objectively, 2:00.
Case 2:
B1. Ben looks at his clock which reads "2:00."
B2. Ben assumes that his clock is working.
B3. Ben infers that it is in fact 2:00.
4. It is, objectively, 2:00.
Case 1 and case 2 are identical except for the second proposition, and the Gettier case turns on the premise that knowledge should not be able to be had by accident or by sheer luck.
When I say "material" vs. "formal" conclusion I mean that both arguments "reach" (4) in a material sense, but only Ben reaches it in a formal sense. If we conceive of (4) as a kind of goalpost that someone must reach, and it doesn't matter how he reached it, then John has reached it. But if we conceive of (4) as a goalpost that someone must reach, and the reaching of which depends upon the means by which they arrived, then John has not reached it given the means in question. John has reached (4) materially but not formally, whereas Ben has reached it both materially and formally. ...Taken further we might say that a valid conclusion is different from a sound conclusion, and therefore John and Ben have reached different conclusions.
The same thing applies to propositions more generally, including J3 and B3.
I think what the Gettier case shows is that there are at least some conclusions which are material rather than formal, and knowledge of these conclusions is never certain. But his point isn't applicable to justification tout court. It is only applicable to those situations in which luck or accident plays a role. ...Of course the skeptic will argue that luck and accident play a role in every situation (i.e. that every conclusion is material), and that seems to be the crux.
Quoting Sam26
We could construe it as saying that every valid justification can be unsound, and that we can only know that a justification is valid, not sound. Such a perspective might simply argue that not all unsound reasoning has defeaters.
The problem is that you want to make sound justification and unsound justification identical, as if they were the same thing, as if they were interchangeable. You are assuming that the 'J' signifies justification regardless of whether that justification is sound or unsound. You want to say that the person who is justified yet wrong is justified with the same justification of the person who is justified and therefore right.
Quoting J
...And you think that if we distinguish between sound justification and unsound justification then there is no difference between 'J' and 'T', which is incorrect. This goes back to the "three separate ingredients" strawman.
Aristotle is rather precise on this point in the second chapter of the Posterior Analytics, where he says that scientia proper requires that one knows the explanation for the thing in question. One must know what explains it; why it came to be. One must not merely have an explanation that incidentally lines up with some particular aspect of its existence. One must have more than an unsound argument with a true conclusion in order to have demonstrative knowledge. If one's understanding of 'J' does not take these distinctions into account then they will not be able to make JTB workable.
Yes. I took that to be understood. My question -- the "right question" part, I guess -- was what sort of answer a person would give if they were asked why X was true but also told, "You may not give your justifications." We feel there should be some answer to this, since after all it isn't our justifications that make a state of affairs true.
But JTB is not about what makes something true, but how I can say I know it to be true. The truth or falsity of the proposition under discussion remains what it is, no matter what I know or don't know. But my knowledge, according to JTB, depends on three things, two of which -- J and T -- seem viciously circular in this context, which again is epistemological, not substantive about the world. (And I raised, above, the question of whether even B can stand up, if I think I have a justification for something I don't actually understand: "If I believe something without fully understanding it, and I'm asked to give an account of what I say I believe, can I do it? Or would this reveal that the B of JTB in fact doesn't apply? - that I literally don't know what I believe." This connects with @Sam26's proposed criterion of "understanding.")
We know analytic statements are true. Given competence we know that mathematical proofs are true. We know that true propositions about directly observable states of affairs are true (if we observe them).
The problem with relying on justifications is that we would need to know the justifications are true in order to be valid as justifications, which would seem to introduce an infinite regress.
I'm not sure this is right.
If we say, a person S knows that P when P is the case, they believe that P, and their belief that P is "justified," in whatever sense we give that word, then what S says or is entitled to say about their possible knowledge that P just doesn't enter into it ? unless you tie justification directly to (even to the point of identifying it with) what S says about how they know that P. That's not crazy, for a lot of reasons, but it's also not forced on us.
And there are cases where we wouldn't want to do that. You might know that the capital of Arkansas is Little Rock, but not even remember how you came to believe it, much less provide an account of that process that would convince a doubter. (Looking it up now in a source trusted by the doubter only proves that you were right, not that you weren't guessing.) There are all sorts of cases.
In general, what you say is going to reflect what you think you know, so sometimes that'll be spot on and sometimes it won't. Just as your confidence is an indicator of the truth of your claims, but a somewhat limited one, so what you offer in the way of reasons and justifications ? what you say ? is likewise only an indicator. Putting too much weight on it will lead us to include cases we oughtn't and exclude cases we oughtn't.
The reasons people say what they do might be somewhat more loosely coupled to what they know and how they know it than philosophers would prefer.
No, that's not right. JTB is not meant to provide you with a recipe for knowledge-cakes. JTB is a descriptive theory, not a normative theory. It is something like an attempt at a definition of knowledge, not an attempt at a recipe for knowledge. It is a set of conditions that is supposed to track when knowledge is present, not a strategy for gaining knowledge.
Like, someone cannot sit down and say, "Ah, I have ten minutes to spare. I'm going to get me some knowledge. I'm going to know that Jupiter is the largest planet in the solar system. So for 'true' I will ask ChatGPT. Check. It is true that Jupiter is the largest planet. Now I need to check the justification box, so I'll look up some arguments for the idea. Check. Now I need to believe it. I think I do believe it, but to make sure I'm going to sit here and repeat to myself the mantra, 'I believe Jupiter is the largest planet, I believe Jupiter is the largest planet...' Okay, well it looks like I now know that Jupiter is the largest planet, given that I have checked all three boxes. Four minutes to spare... what else should I learn today?"
JTB creates so much confusion that I think it may be more trouble than it's worth.
Must I again point out the difference between "P is true" and "I know that P is true".
These are not the same.
The link between them is that one cannot know things that are not true. Quoting J
Of course it is doing useful work.
Quoting J
See how, again, this asks how you know that P is true, and not whether P is true?
But the T in JTB is dependent on P's being true, not on the circularity of your knowing that P is true.
Am I misunderstanding you in some way? You seem to miss this very obvious point.
The distinction between something's being true and our knowing it to be true is of necessary and useful?it is useful to know whether we do know something is true or not? it's better than thinking we know something is true if we don't.
A question remains though? what use is something's being true if we don't know it.
Do you think you can maintain that distinction? The truth doesn't care about what is useful.
No, I didn't mean that. I don't know how you got to that conclusion.
For example, we don't know whether there is sentient life on other planets, and it is good to know that we don't know that. The other day I was at a local market and one of the stalls selling aloe vera and other herbs displayed a Raëlian poster claiming that we need to prepare for the return of the Elohim. Raëlianism is the belief that humanity was created by an advanced extraterrestrial species known as the Elohim.
It is good to know that we don't know whether there are advanced extra-terrestrial species, but the actual truth or falsity regarding that is meaningless to us, since it cannot be (currently) determined.
Quoting Banno
Actually the truth presumably doesn't care about anything.
Well we could ask whether the 'T' in JTB is "accessible" truth or "inaccessible" truth. Isn't it pretty obvious that it is "accessible" truth? Or is there some JTB proponent I am unaware of who thinks "inaccessible" truths are per se important and also central to the JTB approach?
Again, the JTB approach does not claim that truths are known independently of justification and belief. The whole point of JTB is that nothing is known independently of justification and belief.
(This is why 's concern that one must be able to explain why X is true without giving any justification is a kind of ignoratio elenchus.)
If we know something is true we must know it is not false. That's not the same as that it cannot* be false. It's not knowledge that is defeasible, but belief. Everything we know is true - just like every fact is true. Some things we think we know, are false - and therefore we do not know them.
If we think we know it's true, but it turns out it is false, then we didn't know it was true in the first place.
See how it works?
*Are we going to look at modality again? Let's not.
1). I cannot know false propositions a priori.
2). I can have known false propositions a posteriori.
This is because I cannot distinguish the truth from my beliefs a priori, and yet I do make the distinction in hindsight. My concept of truth is in flux, so there is no contradiction here, even if this position isn't compatible with common grammatical usage of the verb "to know" or "to have known".
Quoting Banno
But ‘caring’ seems to go along with truth. Pesky concepts like mattering , relevance and significance are baked in whenever we ‘use’ the word truth. And those words dont care about universal meaning abstracted away from contextual sense.
What does it mean to know a false proposition?
Is your concept of truth in flux, or is the set of true propositions in flux?
You say that if we know something is true we must know it is not false. But is not knowing something is not false the same as knowing that it could not be false (aside from switching contexts or changes over time)? Was it something like the caveat in brackets that led to your mention of modality?
Why the modality? Are you asking if ~K~p?K~?~p ? Well, no, since p does not have the same truth value as ?p.
Drop the modal operator, do you have ~K~p?Kp? That's also false. There are things we don't know we don't know and that's not the same as knowing those things.
If you indeed know that p, then p is true.
Right, and if p is true then it cannot be false, no? Likewise if you know that p is true then you cannot know that it could be false, or so it would seem.
Sort the ambiguity. p?~~p, but not p?~?~p.
If p is true then it is not false. But not, if p is true then it cannot be false.
Think on it a bit.
If we think we know something and it turns out to be false, then we didn't know it.
That's right. So, if we know p could be false, then we don't know that it's true, but we may well believe that it's true. Thinking we know something is not the same as knowing something.
No. I know the cat is on the chair but it could have been on the mat. Hence "the cat is on the chair" is true but could have been false.
Quoting Janus
Better to use "believe". Believing we know something is not the same as knowing something.
'cause amongst other things it needs also to be true.
Ah, I see the problem now, it seems we've been talking at cross purposes—"could have been false" is not equivalent to "could be false".
This is correct, and it is the crux. Someone like @J thinks that for every proposition or claim, we know that it could be false (and therefore we cannot know that any proposition is true). Put differently, @J thinks that every belief should include the caveat, "This could be false."
"Could have been" is a different question. You are asking the more central question, which is, "Could be false."
When Aristotle talks about this he basically talks about the possible alternatives, where the case where we know there are no possible alternatives is a case of proper knowledge. Thus if we know that something could be false then we do not have proper knowledge that it is true (scientia).
Quoting J
Quoting Janus
But do we know this apart from the right justifications? I don't see how. Even something as clear as modus ponens can and must be explained and justified; we don't say "I just know it."
Quoting Srap Tasmaner
You're quite right. My use of "I can say" was loose talk, borrowed from a certain style of discussing these problems. More precisely: "what I can say" = "what I can think or believe to be correct or reasonable, and hence assertable in this sort of discourse." The actual saying or asserting isn't necessary, or even the point, as you show.
Quoting Banno
Right. As I wrote, above:
Quoting J
Quoting Banno
Yes, I think we're a bit at cross-purposes here. The T in JTB is absolutely about something's being true. My question is about how we'd know it to be true. You seem to be saying that there's an independent way of determining whether X is true -- a pre-qualification, so to speak -- that will allow us to import the T into JTB, and then talk about our justifications. That's what I find confusing.
The entire question falls inside the scope of human activity, not ontology. Truth, as I know you firmly believe, is a property of propositions, not objects. If X is true, then X is a proposition. Yes, this proposition describes something else (fact, state of affairs, call it what you will), but that is a different matter. "The T in JTB is dependent on P's being true" -- yes, but if we don't ask "How can I know this?" then I don't understand how we'd ever be able to use T in JTB.
Having said all that, it's entirely possible that I've misunderstood you. :smile: So feel free to clarify.
Quoting Janus
That's more or less what I'm wondering too, though I'd limit my wondering to the use of "true" in JTB.
I can conceive of other contexts for claiming that the concept of truth is useful, even if we don't know whether a given X is true.
Quoting Banno
Yes, that's the right question, and returns us to the issues around JTB. JTB proposes that only true propositions can be known, AND that there is a way to determine truth apart from justifications. Crucial here is "determine truth," not "make X true." X will be true (or false) regardless of whether we can determine it to be so, but if we can't determine it to be so, how are we supposed to construct the T leg of JTB?
I don't think a JTB account is committed to this. You can, and I think this is quite common, simply be a realist (with whatever restriction). That is, it suffices for the proposition to be true or false, whether there is any way to determine its truth value or not.
If I justifiably believe that P, then if P is the case, I am in a state of knowledge that P, and if not then not. Whether anyone knows or can know that I know that P, is a separate issue.
Quoting Joshs
Quoting Banno
My point is that the word ‘truth’ doesn’t have any aspect of its meaning that transcends the context of its actual use. It’s not just that truth is affected by contextual relevance, it’s that there is no categorical meaning of the word ‘truth’ that exists outside of the grammar of its use. I’m not just saying that our access to truth is contextual, but that the very concept of truth is nothing over and above how we actually use the word "truth" in particular language games. There's no essence of truth waiting to be discovered, only the diverse ways we employ the concept in different contexts.
When you say “truth doesn't care about what is useful," you seem to be treating truth as something with its own independent nature. But this very statement only makes sense within a specific language game where we contrast truth with utility. The meaning isn't pointing to some metaphysical feature of truth itself, but emerges from how we've learned to use these concepts in opposition to each other. Our concepts don't get their meaning by corresponding to independent realities, but through their role in our forms of life. So "truth," "relevance," "significance", these aren't mapping onto features of the world so much as they're tools we use for various purposes in different contexts.
But that's the part I find incoherent. Is the idea that P need only be truth-apt in order for "P is a JTB" to represent knowledge? That can't be right. We need to know if it's actually true. So if we can't determine T in some way independent of J, how are we supposed to use JTB as a test for knowledge? What is the criterion that allows us to import "T" into the formula, if we can't know whether X is T?
Quoting Srap Tasmaner
Yes (leaving aside the earlier questions about "good justifications"). But if JTB can't help us tell the difference between being in a state of knowledge that P, and not being in that state, what good is it?
Indeed.
Quoting J
Apparently we can't.
Is that what JTB is for?
Take a step back. Is there any prospect for any kind of theory that would pick out all and only true propositions? That would in every case distinguish true beliefs from false ones — or even justified beliefs from unjustified beliefs?
I think we can be skeptical any such theory is possible, either on general grounds of human fallibility or even on logical grounds (the problem of the criterion),
So what are we about?
@Sam26 does seem to want to say, "My claim to know certain things is justified because I used a really good epistemology." I don't think it works that way.
Again, if you think the T in JTB can be known apart from the J and the B then you have rejected the JTB account. You have claimed that there is knowledge apart from J and B.
Quoting J
If JTB thought there were a way to know truth apart from justification, then there would be no J in JTB. You are effectively objecting to a 'T' account of knowledge, not a 'JTB' account of knowledge.
You are still doing your "JTB as a recipe for knowledge-cakes," noted from my very first post.
Quoting J
JFB fails the test for knowledge, and we know P is F rather than T due to a "justification," namely a justification separate from the particular J in JFB. If someone offers a claim and we have no reason to believe it is false, then we cannot claim that it is false (i.e. not true).
You are always searching for a magic bullet that will allow us to get behind the scenes and infallibly distinguish JTB from JFB according to some "God's-eye view." There isn't one, but that doesn't mean JTB is incoherent.
(The trouble is that you hijack every epistemological discussion and make it about this pet question of yours, in much the same way that an atheist will hijack every theological discussion and make it about the existence of God.)
Agreed. I'd be much more interested in a theory that could show how, in practice, we're able to make pretty good distinctions among degrees of likelihood, knowledge, certitude, etc. The case of analytic knowledge is perhaps special, but I won't open all that up in this context, since even a piece of analytic knowledge must have some justification.
I think JTB is intended as a test for knowledge, yes, not merely a description (to which no one has access!).
Quoting Srap Tasmaner
Maybe not exactly, but I think Sam is nonetheless on the right track. We do know certain things, and we are justified in claiming we do, and without a really good epistemology (or epistemological practice), we'll make mistakes. I think a flexible JTB(+U) schema can help us understand how all this is possible. We just have to avoid some sort of essentialism or "definitionalism" (as @Banno has pointed out) about what counts as knowledge and justification. There are just too many uses, contexts, and practices.
Quoting Srap Tasmaner
What is JTB for?
It is not a "test" in the sense that we have a machine that allows us to practically run any knowledge-claim through it and know in fact whether it is or is not knowledge.
But it is at the very least supposed to provide a set of three necessary and sufficient conditions for knowledge.
@J's objection could be that the T in JTB is otiose, but this is obviously false. The objection could also be premised on the idea that JTB is a kind of automatic knowledge-testing machine and that J, T, and B are three separate and reliably verifiable properties of every knowledge-claim. This is also false, as is the sub-idea that the three properties are supposed to be separable: as if we could have knowledge of each of them separate from the others.
JTB is a tripartite schema, which means that the three components are not separable vis-a-vis knowledge. Beyond that, every epistemological approach will fail to provide a knowledge-guarantee-machine. If one is looking for a knowledge-guarantee-machine, then it is not only JTB that will let them down.
That seems accurate. But so does this:
Quoting Leontiskos
I agree with Leon, but then, because of the possibility of error, what is happening when we think we know something but we do not? Wouldn’t we have to be able to separate J, T or B from the others to think we know something when in fact what we know is missing J, T or B? Or are all three destroyed, along with K, when we are in error?
I think the first thing is this:
Quoting Leontiskos
So on JTB we will only know we have failed when we know that one of the three conditions is absent. And we cannot know that T is absent unless we know that the knowledge-claim is not true. And we cannot know that the knowledge-claim is not true if we are not justified in so knowing, which means that we must have reasons or grounds (whether or not we can articulate them). More simply, it means that knowledge-claims are never invalidated except in light of some other, opposed knowledge-claim. So contrary to @J's thinking, one would never know or even claim that T is absent without reasoning/justification.
This means that if John claims that Ben's knowledge-claim is false, there is the presupposition that John's claim involves JTB. John believes Ben's knowledge-claim is false; it is true that Ben's knowledge-claim is false; and Ben has the proper justification for knowing that Ben's knowledge-claim is false. Nowhere arises the idea that John must know whether Ben's knowledge-claim is true or false apart from justification (or belief, for that matter).
Quoting Fire Ologist
I don't see how belief would be destroyed, but there is at least one sense in which justification and truth rise or fall together. But that gets us back to @Sam26's questions about Gettier's objection.
JTB sets out criteria for a sentence to count as knowledge. It is not a method for determining the truth of some sentence.
Quoting J
That the sentence is true is one of the criteria for the sentence being known. This says nothing aobut how we determined if the sentence is true.
Quoting J
I don't agree with the second part of this. There is a difference between a sentence being true and a sentence being determined as true. You again seem to conflate these. There is a difference between "P is true" and "J determined that P is true". JTB specifies that the sentence must be true, not that the sentence must be "determined to be true".
This seems to me to be the source of your confusion.
Quoting Srap Tasmaner
Yep.
Quoting J
Well, maybe not. Perhaps it's just about the grammar of the use of the term "know" - that we use the term for sentences that are justified, true and believed, and that a use contrary to these would be infelicitous. It's not a method for determining which sentences are true and which are not - which is what you seem to want it to be.
You seem to have an image of an investigator looking at a sentence and saying "ok, Criteria one: I believe this sentence; criteria two: this sentence is justified by such-and-such; but criteria three: how can I decide if the sentence is true?" But that's not how the idea would be used - there's an obvious circularity in such a method, surely. If you believe the sentence (criteria one), then you already think it to be true and criteria three is irrelevant.
Do you see this as something with which might disagree, or which is incompatible with what has been said?
Quoting Joshs
Not at all.
Quoting Joshs
How can they be tools if they do not in some way "map" onto the world?
That's right. So, anticipating your investigator image, using JTB would go something like this:
Q1. Do I have knowledge of X (a proposition)? Depends on . . .
Q1a. Do I believe X?
Q1b. Can I justify my belief in X?
Q1c. Is X true?
Q1b is problematic, as we've noted, but let's allow that we understand what a "good enough justification" would look like. So we can go down the list:
Q1a. Yes.
Q1b. Yes.
Q1c. ????
What can we say about Q1c that doesn't involve an appeal to knowledge? We want to say, Yes, X is true. But we would have to know that, just as we know the first two answers, and we can't, because that begins the vicious circle.
I think what you're suggesting is that instead we should say, "I don't know if X is true. Such knowledge is impossible without circularity. But if it's true, then I know X. And if it isn't, then I don't." So, as you say, a strictly descriptive or criteriological formulation. However, I maintain that this is not only useless, but contrary to the spirit of JTB. JTB is supposed to help us evaluate knowledge claims -- keep us epistemologically honest. And on this construal, it can't.
Quoting Banno
That's right. But then what should we use JTB for?
Quoting Banno
Well, I think it's JTB that's confused, not me. Because as I said to @Srap Tasmaner, what use is JTB if it can't show us how to tell whether we know something or not? Being told, "Well, you would know it, if it was true" is pretty thin gruel and, as I said, not to the purpose of JTB as I understand it.
Quoting Banno
Good, this is a helpful image. And if we set it up like this, then it's another way of showing how JTB is faulty. Because it's absolutely right that the T criterion becomes irrelevant; that's what I've been arguing, using a different approach, all along. I would emphasize the justifications rather than the belief, but it comes to the same thing.
You are right that there is at least one sense in which justification and truth rise or fall together. But Gettier's argument assumes that they do not, that is, that it is possible to be justified in believing that p and for p to be false. In that case, the link between JTB and knowledge rests entirely on the T clause. But if I'm evaluating whether someone knows that p, I must make my own evaluation of the truth or falsity of p, which re-introduces the entire process.
Quoting Banno
I agree with you. But does that mean that the definition must take the truth or falsity of the sentence as given, in some way?
Quoting Banno
Considering the process of applying the definition is interesting. I don't often see it raised. It seems just obvious to me that it must be my evaluation of the knower's justification (NOT my justification), my evaluation of the truth, and the knower's belief. That means, IMO, that I have to take a position on whether the sentence is true or not. This has the awkward consequence that I can never learn anything from anyone else. That seems to make the concept of knowledge a bit limited and rules out the possibility of standing on anyone's shoulders, giant or not.
I think it's just meant to express what we mean by know, especially if we're knowledge internalists, which means we believe knowledge requires access to justification. A knowledge externalist doesn't require that.
So if we say Bill knows that Carrie was written by Stephen King, it's implied that the proposition is true. We aren't worried about how we know it's true.
Given that we believe the sentence, we believe that it is true. Do you mean more than that?
It's not enough, for the sentence to be known, that we believe it to be true. It must also be true.
Quoting Ludwig V
Our evaluation might be better.
Okay, suppose that we took JTB as a criteria for interpreting the use of the word "knowledge". So we have Jim over there who says that he knows a certain sentence to be true, and we wish to determine if he is using "I know that..." correctly. First, does Jim believe the sentence? Second is the sentence actually true? Third, does Jim have some justification for his belief? If any of these fail then we can conclude that his use of "I know that..." is problematic, and how.
Q1a. Yes.
Q1b. Yes.
Q1c.Yes - follows from Q1a: if you believe it, you believe it to be true.
But if we are considering Jim's case, not your own, then it is open to us to say that while Jim believes the sentence is true, we do not, and so Q1c is false, and presumably conclude that Jim does not know what he claims.
Well, I think Gettier creates a strange division between justification and truth, but the Gettier cases I am familiar with involve a proposition that is true, not false.
Quoting Ludwig V
Yes, quite right.
Quoting Ludwig V
Why think that?
---
Quoting J
Again, that's not what JTB is for. It doesn't give you a recipe for knowledge, and it is not primarily meant to allow you to see if your own beliefs constitute knowledge. If one thought that JTB was meant to allow you to see if your own beliefs constitute knowledge, then the T and the B would be otiose, as you keep saying.
Quoting J
Right, because if something can't show us how to answer your pet question then it must be of no use at all. :roll:
No. We do have knowledge - we know things.
Quoting J
It doesn't tell us if they are true or not, so much as if they are known or not. Quoting J
Above, it told us that Jim was mistaken. He claimed to know something that was not true.
Quoting Fire Ologist
As I said earlier, knowing we are justified in believing that some purported piece of propositional knowledge is true, and that we can thus be said to know it is true, also involves knowing that are other things apart from the piece of purported propositional knowledge are true.
Quoting J
If something is true by definition or if something is logically self-evident, or if the proposition concerns something being directly observed, then I would say we need no further justification.
I agree. But all three of these things -- truth by definition, logical self-evidence, and the reliability of direct observation -- are ways of demonstrating justification. To understand this, imagine explaining any one of them to an intelligent child. They all involve steps, cogitation, judgment, insight. We don't simply see why they are true, or at least not usually. In fact, as you know, the reliability of direct observation can be challenged, and the challenge is precisely for a justification as to how such observations lead to truth.
I think life itself teaches us to trust our observations?animals do, so why shouldn't we? You are right that understanding definitions and logical self-evidence are taught, but all such teachings rely on the capacity of the student to "get it", which I think shows that the truth of things which are true by definition and logical self-evidence is simply obvious, and just needs to be pointed out to be established in conscious understanding.
Direct observation is challenged only by what I think of as trivial and ridiculous "mind in a vat", Evil Demon" or "you might be dreaming" scenarios, and I don't think those are to be taken seriously. That's why I say that what we know we know certainly, but only within contexts, not absolutely certainly.
Logical possibility allows any knowledge whatsoever to be subjected to radical skepticism, but I don't see a need to concern ourselves with such vacuous considerations.
This is yet another thing from the prolific David Lewis, contextualism, the short version of which used to be that we do know things in everyday life that we don't know in the philosophy seminar room.
So, does Bertrand Russell's famous turkey, who knows from a whole lifetime of experience that every morning—without fail—the nice man comes to feed him, also [I]know[/I] that it is about to be fed when it sees the nice man coming to his pen on Thanksgiving morning?
It's not all that strange. A standard use of "justify" does indeed assume that if P is false, then there is no justification for believing that p. But this has the consequence that I can only be said to know P if I have a conclusive justification for P. That means that I do not know, for example, that the earth goes round the sun. So that definition can be said to be too strong. So many people believe we should relax the criterion and allow that I do know that the earth goes round the sun, even though I only believe it on authority. It is tempting to say that it follows that I can be justified in believing something even though it is false and Gettier explicitly says that is his assumption.
There's a wrinkle here that Gettier does not mention. It is clearly wrong to believe something that is known to be false and conclusive proof over-rides any non-conclusive justification. But where there is no conclusive evidence, one has to go with the evidence one has, and that does mean that one can be justified in believing something that turns out later to be false. That's a weakness in most of the cases. However, most people seem to go along with his (unstated) assumption that we must continue to call him justified when we know, but he does not, that his belief that Jones will get the job is false.
The proposition in question, in his first case, is
Smith wrongly, but not without justification, believes that Jones is the man who will get the job, but the truth is that Smith will get the job. So Smith is using "the man who will get the job" to refer to Jones, but we (and Gettier) are using it to refer to Smith. That makes two different statements expressed in the same words. There is no problem. (This solution does not apply to all Gettier cases).
Quoting Leontiskos
JTB requires me to accept a claim to knowledge only if I know it is justified and true (and believed). But that means that I have to know p as well as the person claiming knowledge.
That's not an unreasonable idea. Nonetheless, if it turns out that we are wrong, we are expected to withdraw the claim to knowledge. I may be said to know that my car will be safe in the car park, and that may be well justified. But it is is stolen, I have to admit that I was wrong.
Quoting Janus
It is obvious to us. But we have learnt how to do reasoning as part of learning language and interacting with people.
Quoting Banno
What bothers me is the interface between belief and reality. "It must be true" is the something more that is required. But once I have assessed the evidence, what more could there be? so I have difficulty in seeing what this amounts to. The best I can come up with is that claims to knowledge, like any other claim, have to be withdrawn if they turn out to be false. There may be cases in which the truth or otherwise of the proposition in question is finally and conclusively determined, but most of the everyday stuff doesn't come up to that standard. So the caution remains in place.
Quoting Banno
They’re not tools for mapping onto objects, but for enacting new forms of sense in our material and discursive interactions with the world. A hammer doesn’t “map” onto nails. Its usefulness lies in how we employ it to drive nails.Truth is a tool that in some contexts we use to check agreement with facts. In other contexts, we use it to contrast honesty vs lying; in others, to resolve disputes. In addition to the sense of truth as empirical/factual, one can think of grammatical/conceptual truth, performative/expressive truth, aesthetic/evaluative truth, narrative/interpretive truth and many other senses of meaning of that ‘same’ word.
Wittgenstein would emphasize that these aren't competing theories of truth but different tools serving different purposes in our linguistic practices. The mistake is assuming all these uses must share some common essence.???????????????? There’s no one metaphysical object “truth” that the word latches onto.
But Q1c was not about belief, but rather truth. Yes, it follows from believing something that I also believe it to be true, but that's not a reply to Q1c, which asks "Is it true?" Nothing I believe can supply the answer; it depends on the facts.
Quoting Banno
That's what I don't see how to separate. We both agree that only true things can be known. So if JTB tells us that X is known, it must also tell us at the same time that X is true.
Okay, that is an interesting way to approach the problem. The reason I don't think it works is because if Smith were using "the man who will get the job" to refer to Jones, then there would not be an entailment involved. In that case rather than there being an entailment, Smith's two propositions would just be saying the same thing with different words. But Gettier is explicit that an entailment is involved ("Let us suppose that Smith sees the entailment from (d) to (e), and accepts (e) on the grounds of (d)"), therefore what is at stake is not a mere matter of reference.
Quoting Ludwig V
I don't think this is right. Someone can "justify" a claim to you and thereby show you that it is true. Thus one can learn from another on JTB precisely through the other's justification.
Not that it matters, but this just seems intuitively right to me. What is it that prevents this view if truth being more widely accepted.
Well, yes.
Well, yes, You seem to be expecting something from the JTB account that it does not provide. It's not a theory of truth.
Quoting J
I find that it helps out a lot to differentiate between the ontological and the epistemological in these matters:
Whether or not a belief is in fact true, and (given our ability to justify it) furthermore known, is a purely ontological issue. The occurrence of a truth—be "truth" defined as a correspondence to that which is actual, a conformity of belief or psyche to what is actual, or in some other such way—is either ontically actual or it is not.
Yet our only means of appraising what is ontological (or else ontically actual)—in this case, the reality of a truth—will be via some form of epistemology; and our utilized epistemology can, in at least theory, be either infallible or else fallible (with no other possibility being available to us).
If our epistemological appraisal of what is ontological happens to be infallible, there then is no possibility that we could be in any way wrong when we appraise a belief to be either true or not.
If—as any fallibilist will maintain—all possible epistemological appraisals can only be fallible, then our appraisal of a belief being either true or not will always be liable to some possibility of being wrong (with the likelihood of this possibility varying by degrees). And this is where (fallible) justification becomes paramount to our appraisal of what is (ontically) true: The quantity of justifications we can engage in can only always be temporally limited: There will always remain some yet awaiting potential “why” which goes unanswered in all that we justify—granting that we do not somehow obtain infallible justifications; our justifications are thereby always good enough for the purposes at hand, but can never be perfected in infallible manners.
Then, if we believe X, entailing that we thereby uphold our “belief that X” is in ontological fact true, and we can justify the X in question which we believe (at least with the epistemological honesty to recognize when our justifications no longer are sound, if they ever so become unsound), then we hold no grounds by which to presume that the truth of X is not in fact an ontologically occurrent given.
Again, in fallibilism, no justification (which is always epistemological in its nature) can guarantee the ontological occurrence of some given truth in question. One would need to have an infallible epistemology to do so. But, so long as one can soundly justify X at will as time permits irrespective of the data and possible counter-reasonings that might eventually surface, one then has no reason to suppose that one’s "belief that X" is not in fact ontologically true.
In short, when a truth occurs, it occurs ontically—and that which ontically is is not subject to the possibility of being wrong, i.e. fallibility. But we can only appraise what ontically is epistemologically, which will always be to some extent fallible.
As with the issue of truth, so too with the issue of knowledge as JTB. Knowledge can be ontologically had: if one’s belief is (ontically) true and one can justify it, one is then ontically in possession of knowledge (which can never be untrue and so can never be mistaken). But figuring out whether or not this is so will always be epistemological—and one’s applied epistemology, again, can either be infallible (in at least theory) or else can only always be fallible. So long as we can soundly, but yet fallibly, justify our “belief that X” to be ontologically true, we then have fallible justification for our “belief that X” to in fact be ontologically occurring knowledge.
To try to reduce possible confusion, how this works in practice: “I know that the planet is physical and roughly spherical,” is a claim of JTB. The justification—although always only good enough for the given purpose and always in some extreme philosophical sense yet fallible—for the belief that I hold being in fact ontologically true has so far always been sound. I thereby have no epistemological reason to presume that this belief which I can soundly justify at will is untrue (ontically). I thereby then have all the reason I need to conclude and uphold that my proposition is an (ontically) true belief I hold which I can (soundly) justify at will—and that it is thereby something I know as an ontological state of affairs, this in the JTB sense of “know”. Still, because this appraisal of what is ontically the case is wholly epistemological and not infallible, I can yet acknowledge that my appraisal of what I in fact know to be the case could in principle—at least hypothetically—be someday discovered to no longer be soundly justifiable, say due to new data. If this day ever arrives such that this proposition cannot at that point be honesty justified, then this belief will be evidenced to in fact be untrue (ontically): it will not in fact conform to that which is actual. And if in fact untrue, then I in fact do not (ontologically) know that which I so far deem to be knowledge.
You can replace the proposition given with any other, and the same will hold. For one example: “I know that 1+1=2”. If pressured, I might not be able to justify why this belief must conform to what is ontically actual in all possible cases (including all possible worlds), but if I can honestly justify it regardless without inconsistencies and if it does indeed happen to conform to that which is ontically actual in all possible cases, then this proposition will yet ontically be knowledge I hold. Same with “I know that I am not a brain in a vat”. Or else more trivial things, such as “I know that tomorrow it will rain”.
But Smith is using "the man who will get the job" to refer to Jones. Since Jones will not get the job, Smith's deduction is based on a false premiss and the conclusion is not justified (but not refuted either).
Quoting Leontiskos
I don't follow this at all. Smith is not considering two propositions, but only one, and that proposition is false and so does not entail that the man who will get the job has ten coins in his pocket, so Smith's belief is justified only in a weak sense. It might be sufficient for the J clause in the JTB, but it is certainly not sufficient for the T clause.
Let me try again:-
It all depends on how you interpret the sentence "The man who will be appointed has ten coins in his pocket". As it stands here, the reference of "the man who will be appointed" is not fixed, or rather is fixed differently in the context of Smith's beliefs (where it refers to Jones) and in the context of the God's eye view of the narrator (and the audience) of Gettier's story (where it refers to Smith). In the context of Smith's beliefs (e) is justified but false, and in the context of the narrator and the audience, it is true. I don't know what criteria you have for "same proposition", but it seems to me that if a given sentence is true in one context and false in another, that sentence is expressing different propositions in each context. Certainly the same proposition cannot be true and false at the same time.
Quoting Leontiskos
Yes, perhaps I was a bit hasty there. Though if someone tells me that the earth goes round the sun, I can demand their proof and they can, no doubt, provide it - the data exist and the interpretation can be explained to me. But I would have to trust the data, or, perhaps collect a fresh set of data.
Quoting javra
That's a bit sweeping, isn't it? Certainly, an absolute guarantee of an empirical truth seems to be built in to their definition as contingent. But, if the conditions are met, surely we can guarantee the truth. Then there are the embedded or hinge propositions, which seem beyond the possibility of any coherent or rational doubt. Perhaps our choice is not between fallibilism or infallibilism across the board. After all, not all propositions (candidate truths) are of the same kind.
That's true (sorry!), but it's a theory of knowledge that includes, as one of its criteria, that a statement be true. So if JTB tells us that X is known, it must also tell us at the same time that X is true.
But see my response to @javra, below.
This is a very helpful analysis. It sharpens the question, Are we meant to take the knowledge guaranteed by JTB as infallible or certain (@Janus's question)? You argue convincingly that we can't -- that this can't be the point of JTB. So if we're happy to substitute "has no reason to suppose that one’s 'belief that X' is not in fact ontologically true" as a synonym for "knowledge", then all is well. I don't know whether every proponent of JTB would be happy with this, though.
Quoting javra
Here, I wonder whether you misstated your target sentence. Are you talking about a JTB claim for "The planet is physical and roughly spherical" or for "I know that the planet is physical and roughly spherical"? A great deal depends on this, so I'll wait until you reply before going on.
I did provide some justification for the claim in my previous post. That justification can either be infallible or fallible presents two alternatives that are mutually exclusive and collectively exhaustive. Or can anyone show this wrong by producing a third alternative alongside that of infallibility vs. fallibility?
Also, why would “seeming to be beyond the possibility of any coherent or rational doubt” completely/absolutely guarantee the truth of the matter such that there remains no possibility, irrelevant of how small, of being wrong?
As one banal example, why must something which by all accounts appears to all everywhere to be a vase on a table in fact necessarily be a vase on a table—such that it being a vase is true—rather than, say, being an extraterrestrial alien which is camouflaged as a vase, or else an advanced hologram (which maybe operates on all senses, such as that of touch, rather than only on sight), or some such alternative to the truth of it being a physical vase? Despite these possibilities, that it is a physical vase remains beyond the possibility of any coherent or rational doubt (given all the data and justifications available to us).
As I previously said, and as far as I know, all our justifications are always only good enough for the purposes at hand given the time limitations for the justifications we engage in—but they do not ever obtain a state of perfection wherein all possible questions or else issues have been consistently accounted for. And this thereby makes our justifications (here, implicitly understood, justifications for that which is true) less than infallible. They are thereby fallible in the strict technical sense of the word (i.e., liable to some measure of being wrong, irrespective of how small the possibility might be).
I’m very glad to hear it was helpful at least to some.
Quoting J
I know (in the JTB sense) that some out there are quite uncomfortable with the implications of fallibilism for issues of JTB.
Quoting J
Trying to save some space, what I intended by what I wrote is that the proposition of “the planet is physical and roughly spherical” is taken to be an instance of knowledge, thereby being JTB claim (the first option you present). But, yes, it could have been better written.
If there were only one proposition, then how could there be an entailment? Gettier's argument depends on the entailment, and entailments involve at least two propositions. "The man who will get the job" does not refer to either Smith or Jones. It is a descriptor. What this means is that, contrary to your view, Smith is not uttering a tautology when he says, "Jones is the man who will get the job." Such an utterance is not the same as, "Jones is Jones," even for Smith.
Your theory amounts to the idea that when Smith says, "The man who will get the job has ten coins in his pocket," he is saying something false. But when someone else says the exact same sentence, such as the hiring agent who knows that Smith has ten coins in his pocket, he is saying something true. This goes back to what I said here:
Quoting Leontiskos
So I think a material conclusion can differ from a formal conclusion, for example when both say the same thing and yet the "therefore" of the first is merely valid whereas the "therefore" of the second is sound. This may even go further and apply to propositions themselves rather than mere conclusions, as I surmised in that post. But I don't see that what is at stake is a simple matter of reference, as if there is only one proposition and no entailment occurring.
Quoting Ludwig V
Yes, and I would go farther and say that you can see that their argument is correct. It's not so much a matter of trusting them.
There is an interesting meta-question here. Given that you don't actually believe in truth or knowledge and therefore are forced into an intersubjective notion of truth, here in this thread we have an example where you are at an intersubjective loss. What you are saying in this thread is simply false on an intersubjective approach to truth, given that literally everyone is disagreeing with you. Does that mean that you should accept that what you are saying is false and give up this strange line of argument (given that you yourself think truth is an intersubjective phenomenon)? Or is there something more to truth than intersubjectivity? Are you allowed to hold that although your claims about JTB are intersubjectively false, they are nevertheless not false?
Right, and I think this is the more central piece for @J, along with what has said. It goes back to this:
Quoting Leontiskos
Put more simply, for someone like @J every knowledge-claim involves guessing, and therefore there is no knowledge that is qualitatively different from a guess. Everything he is arguing about JTB is dependent on this form of skepticism that is so foundational for him. Truth is going to be a problem for him in any circumstance, JTB or otherwise. He will make (and has made!) the same objections to anyone who talks about truth as if it is a meaningful category, whether they hold to JTB or not.
You make repeated mention of skepticism. Of a Cartesian or of a Ciceronian variety? (the latter being a good example of an Ancient Skeptic—in both his theories and his lifelong praxis) The two versions staunchly contradict. But maybe that’s a separate issue.
As to this,
Quoting Leontiskos
Item #1 I find blatantly wrong in so far as, for example, I know the truth of the color of an object as it appears to me not by justification but by brute awareness/experience. But yes, successful justification wherever needed validates that what we take to be (ontically) true in fact so is.
Item #2 might be a less cordial way of saying that all justification is to some extent fallible. As per my posts here and here, I do uphold this.
Lastly, item #3 clashes with what I’ve stated in my posts. When differentiating the ontological from the epistemological, ontically occurring truths (which are absolutely certain and not possible to be wrong) do occur all the time. But our epistemic appraisals of what are and are not ontic truths (the latter, again, do occur) will be fallible to some measure.
Therefore, ontic truths are always (completely) certain, and are that toward which we (at least some) ideally aspire. This by optimally (which is different from “perfectly”) justifying our beliefs (by my count, with each belief being in essence a psyche’s ascent (conscious or otherwise) to that which is in fact actual—such that to believe that X is to believe that X is true, i.e. corresponds/conforms to what ontically is).
Hence, in one possible summation of what I previously expressed: Ontic truths are, and are always certain. Our epistemic appraisal of what are and are not ontic truths, however, will always be to some extent liable to being wrong. Call the latter "epistemic truths". And it is for this reason we then honestly seek to justify our epistemic turths whenever required: if our justifications remain consistent given all available data and reasoning, there then is no reason to conclude or even assume that our beliefs of what is ontically true are in fact mistaken, thereby allowing us to maintain that our beliefs are ontically true (only when our justifications become inconsistent with data or coherent reasoning, and are thereby endowed with contradictions, can the honest person conclude that their belief of what is ontically true is in fact mistaken and, hence, ontically untrue).
Ontic truth is always certain, in the sense of "completely assured, fixed, and unvarying". Epistemic truth, while aspiring to be one and the same with ontic truth, is however not "completely assured, fixed, and unvarying", for it might in time change with new data or reasoning.
No worries, I'm not always a model of precision myself.
Quoting javra
OK, good, so on this construal, JTB becomes a reasonable description of our ontic and epistemological requirements. We're not saying that "The planet is physical and roughly spherical" is known to be true, pre-JTB. Nothing is known to be true, in that non-fallibilist sense.* Rather, we bring our belief and our (presumably pretty impressive) justifications, and fill in the "T" with some such formula as you used above. The result is knowledge. This should make us suitably modest about what knowledge actually consists of, but at the same time extremely confident that the target statement is knowledge if anything is.
* The monkey wrench is logical and other putatively analytical truths. I think such statements require a different series, and type, of arguments to explain what knowledge of them would mean. Historically, was JTB proposed as being useful for determining that kind of knowledge? I'm used to thinking of it as an attempt to evaluate knowledge claims about the world, but I don't know the back-story. There's something odd about asking whether "If A, then not (~A)" is a belief, or how we might justify it. But I'll leave that for others.
Quoting javra
And this:
Quoting javra
Is there a contradiction?
Consider this proposition as if it were itself a truth:
Is this "truth" an "ontological truth" or an "epistemological truth"? Because if it is an "epistemological truth," then it is not certain, and if it is an "ontological truth," then your appraisal is not fallible. This is why I'm not sure the way you are dividing up this territory is ultimately coherent. You are speaking as if your knowledge-claims about ontological truths are themselves ontological truths and not epistemological truths, and your theory seems to preclude this.
A prime example of this (and it does regard what can well be considered hinge propositions) are those who take dialetheism to be true. We thereby now have an inconsistency between the principle of noncontradiction being true and dialetheism being true. And this inconsistency as to which in fact conforms, or else corresponds, to the actual states of affairs can only be resolved via optimal justifications. Yes, maybe for now these are lacking, but, short of aggressions of each camp toward the other such that “might makes right”, what other avenue is available to us toward discerning what is true in respect to this aspect of ontology (what might possibly be termed the ontology of valid reasoning or of valid logic … or, maybe more esoterically, of logos)?
Not as far as I know.
Quoting Leontiskos
To be clear, I'm not here writing a formal philosophical thesis but a forum post intended to address a specific issue. That mentioned:
The truth of the proposition here quoted would of course of itself be an epistemic truth. One which I so far find thoroughly justifiable: To keep things short, I so far find that there can be no epistemic truth in the absence of an ontically occuring truth it aspires to express. Can you, or anyone else, cogently justify the occurence of an epistemic truth that does not claim to be or else intend to conform to an ontic truth?
If not, then it remains cogently justifiable that ontically occuring truths do occur. Conversely, it then becomes unjustifiable that ontically occurring truths do not occur. (The "all the time" part I'll cut off for now, for it would require a great deal of further justification.)
That's a fair argument. It is similar to a comment asked me about, and which could perhaps be folded into this thread:
Quoting Leontiskos
You seem to be saying that "epistemic truths" presuppose the existence of "ontological truths"; we all believe ourselves to be uttering "epistemic truths"; therefore we are all presupposing the existence of "ontological truths"; and because of this the belief in "ontological truths" is justified.
I think that's a good account on the "game of pool" approach, but I would prefer an account that provides for knowledge of at least some "ontological truths," rather than mere justified belief. Or in other words, if we take up your idea of fallibilism via Janus' conditional:
Quoting Janus
Then on the premise that we know that every p (epistemological truth) could be false, we cannot know any p.
has forwarded a theory where all (or almost all - this is contentious) beliefs are inferences to the best explanation, and are thus probabilistic.
On all of these conceptions certain knowledge is impossible, and yet knowledge is traditionally understood to be certain.
(It should again be noted that none of this has anything special to do with JTB. The one who thinks JTB does not understand JTB.)
Here is a different approach to the same conclusion:
Can it be in any way validly justified that no ontologically occurring truths occur? If one believes that this is the case, what does one intend to express by the proposition of “no ontically occurring truths occur” if this proposition is not meant to conform/correspond to the actual states of affairs of the world and, thereby, of itself be an ontic truth? Thereby contradicting the very proposition made. Therefore, there is no justifiable alternative to the proposition that ontic truths occur.
As to providing knowledge of some "ontological truths", this, again, is what our ability to honestly and cogently justify offers us the possibility of. It just that our JTB knowledge will not, by a fallibilist account, be infallible. (Fallibiilty does not equate to being wrong.)
Quoting Leontiskos
Remember that the JTB model of knowledge was presented by an Ancient Skeptic. If one presumes knowledge to be infallible, then this quote holds. If one presumes knowledge to be fallible, then it does not.
Quoting Leontiskos
By everything I've so far stated, there then can occur ontically true beliefs which we can justify at will. These then will be instances of ontic knowledge, which is certain. Because we can only hold epistemic appraisals of what is ontically true, though, everything we uphold as knowledge will be epistemic knowledge, rather than ontic knowledge - which, as with epistemic truth, is less than "completely assured, fixed, and invariable."
I'll be back tomorrow.
That's correct, but I don't claim that most such inferences are rigorous. It's often just what seems most likely to the person making the judgement at the time he makes it.
Example of non-rigorous IBE: a Presidential candidate* loses the election; based on his belief that he was overwhelmingly more popular than his rival, and he judges that this is best explained as the election being stolen from him by illegal means. (* Any resemblance to any person, living or dead, is purely coincidental.)
More rigor enters into the analysis when one open-mindedly considers additional evidence that was previously unavailable or overlooked, often in the face of being challenged on the initial judgement.
__________________________
Regarding "probablistic" - do not mistake this with orthodox Bayesian epistemology, which depends on the absurd assumption that we can attach a consistent set of epistemic probabilities to every statement we claim to believe. Rather, I embrace Mark Kaplan's* "modest Bayesianism", which makes the modest claim that we can attach a relative confidence level to SOME pairs (or small sets) of statements of belief. If there's a reasonable basis for the ranking.
* source of this theory: Mark Kaplan's article "Decision Theory and Epistemology", in the Oxford Handbook of Epistemology.
That's also an intelligible argument, but I think it's weaker than the other one. This is because it seems to commit the error of applying the LEM to justification, so to speak. It seems to say, "If you don't think one is justified in affirming the existence of 'ontological truths', then you must have some justification for affirming their non-existence." I don't think this works because I think that someone could reject all particular justifications on offer in either direction, even if they do not affirm the truth that there can be no justification in either direction. One example of this approach would be the ancient skepticism that you mentioned, but in a more general sense I think an agnostic stance that does not affirm either of the two "ontological truths" is coherent.
Quoting javra
But if "fallibility" means that we cannot be certain, then the same problem arises.
The words "infallible" and "fallible" are often used by "fallibilists" but never by "infallibilists," which makes me think they involve contentious presuppositions. I would say that what is at stake is the certainty of knowledge, not the infallibility of knowledge. Actually the object of in/fallibility is a faculty or power, not a piece of knowledge, which is another reason I don't find those terms helpful. It is understandable that one would use them, but given that no one accounts themselves an "infallibilist" the distinction's usefulness is questionable. More simply, I see no reason why someone who affirms the certainty of some knowledge must be a so-called "infallibilist."
Quoting javra
...and since no one presumes knowledge to be infallible, and yet pretty much everyone holds that knowledge is certain, @Janus' conditional must apply more generally than you allow.
Quoting javra
Well you're walking a tightrope with these sentences. For one thing, I would want to ask what it means for "ontic knowledge" to "occur" or be "certain." And why is it "certain" that there are instances of ontic knowledge? Couldn't someone of your persuasion hold that there are no ontically true beliefs, even though every epistemological belief aims at ontic knowledge?
I would take the more traditional approach and agree with a great deal of what you have said, but add that sometimes "epistemological knowledge" and "ontic knowledge" coincide, and can be known to coincide.
Quoting javra
Okay, and if I don't manage to post tomorrow then I will be out for a few days.
Okay good, and therefore let me try to answer one of your questions from a different thread here, in part because I will be out for a few days:
Quoting Leontiskos
Quoting Relativist
Not a tentpole, but a pole such as the North Pole. If some things are more North and some things are less North, then something must be most North.
So if knowledge is probabilistic, then it would seem to be asymptotic towards "100% probable." If someone doesn't know what it means to be 100% probable, then they cannot know what it means to be probabilistic at all. And if you admit IBEs or probabilistic knowledge without admitting traditional knowledge, then it looks like you have no pole to orient your IBE.
The phrase itself, "inference to the best explanation," presupposes the idea of an explanation, and an explanation is not merely probabilistic.
The general idea here—which will apply to a large number of the epistemological theories on offer—is that if we abandon the possibility or notion of certain knowledge, then the replacement form of uncertain knowledge will cease to make sense. If all knowledge is uncertain, then no knowledge is uncertain, so to speak. And if there is to be a spectrum of certainties, then one must account for what makes the more certain knowledge more certain and what makes the less certain knowledge less certain, and this accounting will itself reinstate the traditional view of knowledge that one was trying evade in the first place.
The problem I think you see is of your own creation. Or so it seems to me.
Quoting Leontiskos
The issue I posed had nothing to do with the Law of the Excluded Middle but with contradiction and consistency, hence with the LNC. The proposition that “no ontic truths occur” can’t help but contradict itself upon analysis—for it intends to covey that which is actual and thereby specify an ontic truth. If it happens to be (ontically) true, this then directly contradicts what is affirmed. And if it’s not (ontically) true … what viable alternative can there be obtained other than that it is an untrue, and thereby a false or else erroneous, proposition? Else, how can the proposition of “no ontic truths occur” be interpreted to in any way convey a partial truth? The proposition is either completely true or it is not.
The justification provided for the proposition that ontic truths occur then serves to evidence that the stance is held knowledge. The contrarian, if they cannot provide cogent justification, then cannot claim to have knowledge in the form of JTB that no ontic truths occur. This then results in (yet fallible) JTB that they do vs. blind belief which is in no way justifiable that they don’t.
Quoting Leontiskos
As pertains to this and a good portion of the remaining comments in your post:
As you might already know, “certainty” is a very difficult semantic to adequately define. For my part, I’ve so far tried to define it as being “completely assured, fixed, and unvarying”. But since you place so much emphasis on the issue of certainty in respect to knowledge, please define what you yourself mean by the term. For example, the SEP article on certainty specifies a distinction between psychological certainty (as one example, being certain that X due to a gut feeling one cannot consciously justify) and epistemic certainty (i.e., the highest degree of certainty possible). And I presume you are here referring to epistemic certainty. You will find the article further addresses four different possibilities of what epistemic certainty might signify, with infallibility being formally introduced as one of these four possibilities addressed. If you disagree that epistemic certainty equates to infallibility (this being something that I myself disagree with), then, again, please specify what it is you believe certainty in relation to knowledge equates to.
Quoting Leontiskos
As I understand it, fallibility (simply: the possibility (but not the plausibility) of being mistaken) does not equate to a lack of certainty, neither to lack of psychological certainty nor to lack of epistemic certainty. For one example, I can find no “higher degree of certainty possible” than applies to, for one example, the proposition that the ontic is, i.e. that being is. In then upholding this affirmation to be epistemic certainty, and because I don’t equate epistemic certainty to infallibility (i.e., the impossibility of being mistaken), I then can yet intellectually acknowledge the possibility (but not the plausibility) of being mistaken in so upholding. And, thereby, of the proposition being technically fallible. But this does not in any way diminish the fact that I hold the occurrence of being to be epistemically certain. No psychological uncertainty whatsoever involved here. Again, this even though I don’t take this epistemic certainty to be infallible, i.e. impossible to be mistaken, and thereby yet deem it fallible.
Quoting Leontiskos
I might better address this after you specify what you mean by "certainty". For the time being though, to toot my own horn: perhaps I am, but, if so, I so far find this tightrope walk to be steadfast, secure, and successful: Ontic knowledge obtains, hence occurs, when one can justify a belief which is, in fact, ontically true. A belief which in fact is ontically true is certain in the sense that it conforms or else corresponds to an actuality that is itself ontically (rather than psychologically or epistemically) certain - and, hence, is ontologically assured, fixed, and unvarying given its context, or else limitations, of space and time. For example, if a cat is on a mat at that location and at that time, this will be ontically certain, i.e. completely assured, fixed, and unvarying ontologically. If my pronouncement that "the cat is on the mat at that location and at that time" is ontically true, then my pronounced truth is as completely assured, fixed and unvarying as is the cat being on the mat ontologically. And lastly, no, I cannot conceive of there being no ontically true beliefs. If you can, please elaborate on how that might be possible.
First of all, I have never claimed knowledge is impossible. I said it is rare. Is this sufficient for uncertain "knowledge"* to make sense, on your terms?
*(if it's uncertain, it's not knowledge - by most definitions)
Secondly, I suggest that TRUTH is a well defined concept, and the ideal that we strive for is: TRUE BELIEFS. Just this one aspect of "knowledge" is needed to make sense of what we're doing.
Turning to the other qualifying factors for knowledge...
Justification is relevant, but only because it relates to the means by which we pursue truth. Some justifications are better than others; the best are the ones that achieve certainty (=confidence we have found truth).
The existence of Gettier problems would seem to suggest that 100% certainty should almost never be claimed (there's nearly always some remote possibility that a strongly justified belief is false). However- IMO, remote possibilities doesn't and shouldn't shake our complete confidence in a strongly justified belief.
This segues into my view of epistemic "probabilities". I don't think the term should be used, because our attitudes toward statements aren't developed in any remotely mathematical way. As I said in my prior post, we can often rank one justification stronger than another, but that doesn't warrant assigning fine-grained numbers. Now back to Gettiers...
If fine-grained "probabilities" can't be assigned to beliefs, remote possibilities should not be a factor in judging confidence because they would reflect only fine-grained difference. This removes Gettier problems from real-world epistemic considerations.
So...if the Gettier issue is included in the definition of knowledge, then it renders true knowledge a rarely obtainable objective. But this should have no bearing on the rational pursuit of truth.
I agree that when it comes to claims of knowledge, justification is required. On the other hand I know many things with certainty that require no justification simply because they are directly known?in these cases justification just doesn't enter the picture.
Quoting Ludwig V
Right of course, but I think it is also the case that some things that are self-evident are already so before their self-evidence becomes reflectively conscious. In other words I think there are basic logics inherent in perception itself that forms the primordial basis for reasoning, and can be seen in the kind of basic reasoning revealed in animal behavior.
Quoting Leontiskos
Strictly, allowing for radical skepticism (Brain-in-vat, might-be-a-dream, Evil Demon) I think that is true, and we should not speak of knowledge (except in the know-how sense) but, more modestly, of belief?so not 'knowing that' but 'believing that'.
But I also think that is too strong and that we do know some things with certainty, because I don't think skepticism based on the bare logic possibility of error should be taken seriously.
I think we are still talking past each other. I take your point that there is an entailment involved and that this must involve two propositions. I also take your point that "Jones is the man who will get the job" and "Jones is Jones" are not equivalent, even though A=A.
Let me try again:-
I think we agree that (d) and (e) are two distinct propositions, and (d) implies (e).
That's right, because (e) also follows from (s) "Smith is the man who will get the job, and Smith has ten coins in his pocket." Now we know that if Jones gets the job, (e) will be true, and if Smith gets the job, (e) will be true. So it also follows that (e) is true, because whoever gets the job will have ten coins in his pocket.
But Smith only knows that if Jones gets the job, the man who gets the job will have ten coins in his pocket. So Smith is justified in believing (e) if "the man who gets the job" refers to Jones. He is not justified in believing (e) if (e) refers to Smith. So he is not justified in believing (e) if it refers to "whoever gets the job".
Quoting Leontiskos
No, I would not say exactly that. I do say that, given what S believes, when he asserts that the man who will get the job has ten coins in his pocket, he is asserting something that he does not know to be true. But when the hiring agent says the same sentence, that needs to be interpreted in the light of their knowledge and beliefs, and the hiring agent does know that the man who will get the job has ten coins in his pocket. Are we to say that Smith's belief is false? It depends whose point of view you regard as the appropriate context.
The "exact same" sentence may have different meanings if it is used (asserted) in different contexts. Suppose that A is 20 years old, and B is 40 years old. If A says "I am twenty years old", A is saying something true. If B says "I am twenty years old", B is saying something false.
I say that "I am twenty years old" said by A is a distinct statement from "I am twenty years old" said by B. A statement is a sentence as it is used in a specific context. Whether it is the same proposition or not, I do not opine, because, IMO, the concept of a proposition is not sufficiently clearly defined.
But if you are thinking of a proposition as something like the meaning of a sentence, I think you will still have trouble saying that "I am twenty years old" expresses the same proposition in both contexts, because it is true in one context and false in another. But you might say that "I am twenty years old" said by A means "A is twenty years old" and similarly for B. In that case, you still get two distinct meanings for the sentence and therefore two distinct propositions.
"The man who will get the job has ten coins in his pocket" has different references in different contexts. In the context of Smith's beliefs, it refers to Jones. In the context of our knowledge, it refers to Smith. There is a third context, and so a third meaning for this sentence, and that is the context before anyone knows who will get the job. As it happens, in that context, we know (but Smith does not) that whoever gets the job will have ten coins in his pocket.
Quoting Leontiskos
Could you please explain to me the difference between a material conclusion and a formal conclusions? I'm not familiar with it. I may have forgotten what it is.
Quoting Leontiskos
I would accept that. But I do have a reservation about the data. Unless I can make my own observations (or experiments), I have to trust the report of them. In order to pass on knowledge, we have to be able to assume a common context to at least some extent.
Quoting javra
It depends what you mean by "necessarily". I suspect that you have in mind logical necessity, and that is not possible, because "there is a vase on the table" is contingent. In one way, I'll accept that we can imagine that the vase on my table is an alien or a hologram. But there is not a shred of evidence for either possibility, so there is no rational basis for an actual doubt. It is and empty possibility. In fact, when I try to imagine it, I cannot imagine how that possibility might have come about, except by a further fantasy which has little or no connection with reality. Contrast the possibility that the vase on the table is actually a listening device with a camera, planted by an evil agency to entrap me. But then, I can rule that out, so it is in a different class.
Quoting Janus
Quite right too. (I sometimes wonder what distinguishes Descartes' evil demon from a paranoid fantasy.)
And this resembles the "A or ~A" case, where it's difficult to see it in terms of justifications. Still, I think the conclusion we ought to draw from this is that we're not quite sure what a justification is. What sorts of reasons may play a part in justification? (We noted earlier that a "good justification" is very unclear, in many cases.) If you ask me for my justification in believing "I am having thought X right now" and I reply, "I am directly observing this occurrence as we speak," have I offered a justification? Perhaps so; that's one way of understanding what reasons count as justification, though I'd probably also need to say something about the previous reliability of my direct observations. Or we might conclude that "directly observing" and "having" are two ways of saying the same thing, so no actual reason has been offered. Then, if "I am having thought X" needs a justification, we'd have to look elsewhere.
Quoting Banno
You may well be right. But I haven't yet satisfied myself one way or the other. Your input, as always, is appreciated.
Quoting J
In his final piece of writing, On Certainty, Wittgenstein describes how G.E. Moore asserts something quite close to what Janus claims, that we can know things with certainty that require no justification simply because they are directly known?in these cases justification just doesn't enter the picture. Moore uses as an example holding up one’s hand and stating ‘here is my hand’. He believes one can be certain of this without a need for justification. But Wittgenstein disagrees with Moore’s depiction of this form of certainty as a kind of empirical knowledge. He asserts instead that it is a matter of our enmeshment in a “form of life”, a hinge on the basis of which to organize facts rather than the ascertainment of those empirical facts by themselves.
Yes, that's a good link to Moore and Witt. In this context, I'm not so concerned to ask whether there is such a thing as direct knowledge -- or rather, I take it as given that there is. The problem is to explain what we mean by that, and what can count as a justification for our confidence in it. Witt, as I understand him, is raising a doubt not about the "knowledge" part, but about whether it is empirical. That's also what I was moving toward, in saying "If 'I am having thought X' needs a justification, we'd have to look elsewhere." Hinges and forms of life are good candidates.
Yes, and, again, that was the entire point of the example given. One can intellectually acknowledge the possibility (not the plausibility) of being mistaken in a maintained proposition without in any way finding any rational, coherent, or else sane means of doubting anything about the proposition maintained. As I was saying to @Leontiskos in my last post, the epistemological stance of fallibility does not equate to uncertainty, of which doubt is a variant of. Same will then apply to BIV hypotheses, the hypothesis of solipsism, and so forth: "I can't prove that there's no possibility of being wrong in upholding that we are not BIVs but, all the same, I can find no rational basis whatsoever to in any way doubt that we are not."
Quoting J
At least the last example overlaps knowledge by acquaintance, which is not contingent on justification, with knowledge by description, which is.
Quoting https://plato.stanford.edu/entries/knowledge-acquaindescrip/#Dis
Say an intoxicated person is seeing a pink elephant. The person’s knowing that they are seeing a pink elephant is knowledge by acquaintance; it is non-inferential and so not contingent on justifications; this knowledge thereby does not equate to or else require JTB. Knowledge that the pink elephant seen is either real or not, on the other hand, will require some form of inference and, so, will be contingent on justification; thereby equating to the JTB sense of knowledge.
The dilemma is either
A. a belief merely refers to the coexistence of a believer's mental state and an external truth-maker, where the external truth-maker is decided by the linguistic community rather than the believer. In which case the intentionality associated with the believer's mental state is irrelevant with respect to the belief that the community ascribes to the believer as a matter of linguistic convention rather than of neurological fact.
or
B. Beliefs refer to the actual physical causes of the believer's mental-state - in which case the believer's intentionality is relevant - so much so, that it is epistemically impossible for the believer to have false beliefs. (Trivialism).
So you either have to sacrifice belief intentionality or you have to accept trivialism. There is no "inbetween" alternative IMO. Either way, the naive conception of beliefs as binary truth-apt intentional states is untenable and ought to be eliminated from discourse.
I'm afraid I didn't realize that. Fair enough.
Quoting javra
Does that mean that you are thinking of seeing the pink elephant as introspection and so immune from mistake? I can't help feeling that applying the description "pink elephant" to whatever I am seeing is not immune from mistake.
Quoting sime
I don't quite understand this. Our community ascribes false beliefs to people all the time and that's why they are called "intentional"
Quoting sime
I don't understand this either - apart from the first part. If beliefs did refer to the actual physical causes of the believer's mental state, we could never ascribe them to each other, since we mostly have no idea what they are.
If the pink elephant happens to be a hallucination or mirage*, then hallucinations and mirages are not introspections (aka, self-examinations of one’s own being, thoughts, etc.) … but imaginings (such as can occur in daydreams) seen with the mind’s eye that a) are not willfully produced at a conscious level and b) which the person does not, at least momentarily, realize are merely imaginings seen with the minds eye. Do you disagree with this?
If you agree, then what is seen with the mind’s eye remains known-by-acquaintance as that which one so sees (here, again, with the mind’s eye): here, then, the person sees a pink elephant and knows this (thereby knowing it isn’t a pink snake or else a green elephant, etc., which is being seen). And this is so known-by-acquaintance without any inferences involved - it is brute data of experience with presents itself to the person (in contrast, most introspection that I know of is inferential in some capacity or another).
Introspection is not immune from mistakes, because it is most always inferential. That one experiences what one presently experiences is, on the other hand, a brute given. One would need to delve deep into hypotheticals (e.g., the possibility that there in fact is no "I" and hence no perceiver) to grant room for possible mistakes in the affirmation of, "I am currently seeing X" when one is in fact so currently seeing (be it with the mind's eye as is the case with imaginings or else with one's physiological eyes).
--------
* Otherwise, the intoxicated person could conceivably have seen a real elephant covered in pink powder, such as occurs at times in India during certain celebrations, in which case it would not have been a hallucination or mirage but an externally existing elephant which was physiologically seen.
That sounds right -- but it also means that we can't say the drunk saw a pink elephant. Seeing with the mind's eye is a metaphorical extension of what it means to see something.
Quoting Ludwig V
I'd say the mistake is in the use of "see".
But in any case, this is about choice of terminology. We could say to the drunk, "No, you didn't," and mean either "You saw nothing" or "What you saw wasn't a pink elephant." Neither one is obviously correct, apart from pedantry. But we're all three dividing up the conceptual territory the same way. (And I think @sime is getting at this too, with their A and B analyses of beliefs.)
Although “the mind’s eye” is indeed metaphorical, that doesn’t seem right to me. As one very common example, visual experiences that occur during REM periods of sleep are all seen with the mind’s eye. So then people can’t say, “I saw X in a dream last night”? Yet this is common practice. Or else, someone instructing another to visualize such and such and then asking the person, "what do you see?" (this too obviously being visualizations experienced via the metaphorical mind’s eye).
For a large class of sentences, the truth of the sentence is decided by how things are, not by how the community thinks they are.
Quoting Banno
I'd suggest that here truth is foundational, and knowledge derivative.
From "We know that A" we can conclude that A is true, but only because that is how "We know that..." works; this is a bit of grammar only.
Did you mean correspondence? I don't see what coexistence does there.
No belief is an island. Any particular belief implies a web of associated propositional attitudes, much of which is worldview, the present generation's heritage. Being wrong involves miscalculation, misinformation, misconception. What's wrong with that account?
Quoting J
If I am conscious of entertaining some thought or other, then I cannot be wrong about that awareness. So, I can say that I know I am thinking X, when I am aware that I am thinking X. I cannot justify that I have that knowledge to you, if you believe me you take it on faith.
Quoting Joshs
We can only organize facts, or even generate the concept of a fact because we have symbolic language. On the other hand we and the other animals observe many things without necessarily self-consciously or reflectively conceptualizing those observations, and of course it is only we (as far as we know)m that can verbalize facts as statements.
This is spot on. But I don't think it is just pedantry.
Quoting J
I don't think there is any mistake at all. You are presenting a tediously familiar philosophical "problem" but in a way that makes us to look at the problem in a different way. The conceptual resources in your presentation do not allow a satisfying description of the situation. As you say, two contradictory answers seem both to be true. If you say the drunk saw nothing, you are not taking into account what they say and what they do - they do in fact behave as if they saw a pink elephant. If you say, what the drunk saw was not a pink elephant, you invite the question what they did see, and there is no answer, apart from nothing.
Quoting J
I take it that the three of us are 1) someone who says the drunk saw nothing, and 2) someone who says what the drunk saw was not an elephant and 3) the drunk who says that they saw a pink elephant? ln which case, you are quite right. But your description is excluding the "straightforward" answer that the drunk is hallucinating a pink elephant.
So we can see that the concept of a hallucination resolves the problem - it squares the circle of three answers, none of which is satisfactory. I'm irresistibly tempted to say that it was (in some sense) designed to do just that.
In a sense, of course, it just kicks the can down the road, because the puzzle about what a hallucination actually is remains. Many philosophers have "resolved" it by distorting our concept of experiences, appearances, images or inventing a yet more puzzling concept like "sense-data" to explain the phenomena. But that is not a solution. It just kicks a much bigger can down the road. Common sense doesn't do that, but moves towards an explanation why all this is happening. So we needn't go down the philosophical road, but simply say that Macbeth's weird behaviour is the result of his guilty conscience or possibly a vision sent by God.
I'm not sure whether you are talking logic or child development here. But it seems to me that, from a child development perspective, this must be right. The development of empathy in small children has been much studied - admittedly the primary focus is on emotional empathy, but awareness of the different perspectives of other people (emotional and cognitive) is included. The philosophical relevance is that this is where the concept of knowledge becomes necessary for understanding what people do - or don't do. (Belief, it seems to me, must come later.)
Logic. But I'm thinking of Davidson here, too - interpretation and the principle of charity fit in with your comments regarding empathy...
Belief only makes sense against a background of truth; it is, after all, what is thought true as opposed what is actually true.
H'm. I can see that one might use the words in those ways. But I would have called what you call the brute given, what I know by introspection, and called what you call introspection ordinary knowledge. But there is a fuzzy line between the experience of pain and the interpretations of pain (as caused by falling down or whatever). My doubts about what you are saying are around the fact that what you call he "brute given" is only by extension something that I know about. That requires me to distance myself from the experience itself and think about it in a way quite different from the simple reaction ("Ouch!"), which does not mean "I am in pain", which requires conceptualization.
Quoting javra
I think the practice is all right. When I say "I saw X in a dream", I defuse the standard meaning of "see" by adding "in a dream". That signals that I'm aware that I didn't "really" see X. (Contrast the small child who wakes up in the middle of the night terrified by the wolves all round the house.)
Yes. That's not an accident. But what I'm especially interested in is, put it this way, the glitches in natural language that require us to develop or learn conceptual dodges that enable us to cope. My reply to @J earlier (bottom of last page) is a nice example. It's in a grey area between logic and psychology, but it is where, IMO, the later Wittgenstein is operating. The Blue Book is an excellent example, just because he is developing his methodology.
Quoting Banno
That's true. But it requires, not just introspection, but an awareness of other people as different in certain ways. Arguably, that awareness is even essential to self-awareness and introspection beyond what Wittgenstein calls expressions in his discussion of pain, as in " the verbal expression of pain replaces crying, it does not describe it" (PI 244) and "How can I even attempt to interpose language between the expression of pain and the pain?" (PI 245.
And that is the idea I am attacking. Supposedly, Intentionality refers to "The quality of mental states (e.g. thoughts, beliefs, desires, hopes) which consists in their being directed towards some object or state of affairs." - Google Gemini
So according to this definition of intentionality, the intentionality of a mental state has nothing to do with the opinions and linguistic biases of a community, and concerns a genuine, real relationship between a believer and an object that his beliefs are directed towards. But if this relationship is a causal relationship between the object of the belief and the mental state of the believer, then how is a false belief possible?
Notice that we don't attribute false beliefs to a glitchy measurment device - rather we refer to the device as uncalibrated or not functioning in accordance with its specification. And so we don't consider measurement error as as an attribute of the state of the measuring device; rather we consider the device as not functioning in accordance with our wishes, in that it is us who chooses the "truthmaker" of what we want the device to be measuring. And hence we do not attribute intentionality to the state of the device with respect to our desired truthmaker.
The situation isn't different with humans as measuring devices. And hence as with the example of a thermometer, either humans have intentional belief states, in which case their beliefs cannot be false due to the object of their beliefs being whatever caused their beliefs, else their beliefs are permitted to be false, in which case the truthmaker of their belief is decided externally by their community.
On the one hand, a radical translation of a speaker's utterances in terms of truth-conditional semantics, interprets the speaker's utterances as denoting statistical correlations between his mental state and his external world (charity). But on the other hand, the radical translator gets to decide the cases when the speaker's utterances are supposedly "false" (uncharity), in accordance with the translator's personal agenda, as opposed to in terms of the actual causes of the speaker's utterances when he said the "wrong" thing.
Davidson's proposal is scientifically useful but non-philosophical and aligns with how the concept of "beliefs" are used practically and non-seriously in AI and machine learning, especially in the case of Bayesian reinforcement learning when we callibrate a neural network's responses to the external states of the environment and call the resulting neuron activations "beliefs" (which denote our wishes). But Davidison, like machine learning, ducks the philosophical question as to how to rehabilitate epistemology, given that any realist notion of beliefs seems untenable.
Do I have to know that X is true in order to use it as the T in a JTB statement? Is that knowledge the result of a previous application of JTB? etc. I know you think this can be dissolved, but I still don't see how. Truth is certainly foundational to the whole set-up, I agree, but the question seems to be whether I have to know that X is true. We can loosen that requirement, and say that "X is true" is pre-JTB and therefore not a knowable instance of truth. This seems to resemble more closely our actual practice.
Quoting Janus
Agreed. I think we're speaking of self-justification here. Can you justify to yourself that "I am thinking X" is necessarily true? This starts to become merely verbal, depending on what sort of thing you think a justification is. Self-evidence, on some accounts, requires a justification, or at least an explanation. On other accounts, it's the very thing that obviates justification. Does it much matter which construal we pick? What matters is the concepts in play, not our terms for them.
Quoting Ludwig V
That was kinda deliberate. For what is a hallucination, and how do we talk about it? Is there an obvious consensus? Some would describe hallucinating as "seeing something that isn't there"; others would describe it as "thinking you see something that isn't there". Is there a meaningful difference, apart from choice of terms?
Quoting Ludwig V
Precisely, as I just described. But the can isn't important, in my opinion, so this shouldn't bother us.
Under the strongest possible interpretation of truth-conditional semantics (the principle of maximal charity), the meaning of your use of a sentence S refers to the actual cause of your use of S; in which case, the answer to your question is vacuously yes, because the truth of your utterance of S is necessarily true when your utterance of S has been correctly understood.
On the other hand, if the community gets to decide the truth-maker of your use of S irrespective of whatever caused you to utter S (the principle of minimal charity), then you cannot know that S is true until after you have used S and received feedback. In which case, the truth of S isn't a quality of your mental state when you used S.
John points to the white board, which has the figure 2 written on it. He says, "That is a prime number." We'll call the sentence he uttered S.
The cause of his use of S is a factor in determining the truth conditions. That cause is not the truth conditions, though. Or if it is, how?
Quoting sime
"Truth-maker of your use of S" doesn't make sense to me. What are you talking about?
Quoting J
If he read Descartes' Meditations, he would be cautious about knowledge claims. If he asserts things in spite of Descartes, he could say he's secretly prefacing the assertion with "If the Evil Demon isn't tricking me right now, ..."
Infants and nonhuman lifeforms do not have the conceptual power to articulate “I am in pain”. Yet, I so far presume, we’d both agree that they can yet experience pain. It is this which is knowledge-by-acquaintance, this for any awareness-endowed being, which, again, is in no way JTB: it is a known that is neither dependent on any type of justification nor does it require an upheld belief (a belief of what one experienced can follow the experience itself, but one does not ubiquitously first believe X in order to next experience it). It is merely a true immediate experience. One thereby knows what one directly and immediately experiences consciously—such as pain or pleasure, or color, size, and shape, or tactile texture, or such and such thought, and so forth—only by direct acquaintance. Not by conceptualizations utterly devoid of any direct acquaintance. We non-infant humans then make use of conceptualizations to express these instances of knowledge-by-acquaintance via words, which embody concepts, and can then further cognitively manipulate these concepts. But the knowing that one is in pain rather than in states of pleasure, for one example, remains a JTB-devoid knowledge-by-acquaintance—this just as much for an adult human as for a nonhuman animal.
As reference to the philosophical usage of the term, as previously provided, here is the SEP article on knowledge by acquaintance.
Quoting Ludwig V
I understand this, which is why the second example was provided. Just checked, and “to form a mental picture of” is an official definition of the term “see”. So as far as I can tell, in standard English, one can really see an imagined object. Besides, when the drunkard sees a pink elephant, the drunkard supposedly does not yet know in a JTB sense whether the elephant is a mental picture or else a real aspect of the external world. He merely witnesses via visual phenomenological means a pink elephant—one which, as previously expressed, might not be real or else might in fact be real, depending on context. (For example, I’m fairly sure there are drunkards in Indian festivities where pink power can be thrown on top an elephant, thereby resulting in the drunkard seeing a real elephant which is pink in appearance.)
I'm not convinced that Wittgenstein accepted JTB, in the way @Sam26 seems to think. I read him in On Certainty more as pointing out that if we do accept JTB then these are the consequences - there are for instance things that we might casually say we know that are rules out as knowledge by the JTB account. We can't know how a dog that has been run over feels.
No. But it has to be true. This was my first reply to you in the present conversation:
Quoting Banno
When I think X or feel a sensation, there can be no doubt about it. So, I see no need for justification. Justification is only for beliefs, not for those things known with certainty. (Note: I leave out of consideration the kind of radical skepticism that Descartes feigned, simply because I think it is always a matter of feigning.
OK, that seems like a good way to look at it, with perhaps the caveat that it's reasonable also to ask, "Why are you certain?" or "What makes you rely on this experience?" (similarity to previous ones, presumably). These aren't requests for justifications in the same way that asking for a justification of a belief is, but their aim is to ask for an account, a rationale. I can't simply reply, "Well, I just do." This rarely comes up, of course, but it's worth noting.
Also, you can say that Descartes "feigned" skepticism, but he wasn't trying to fool himself or others. He wasn't just being annoying. He was trying to pursue a method he believed would lead, by elimination, to clear and certain knowledge.
Cheers, that's a fair question—and I hope I can answer it to your satisfaction. I take it that possession of knowledge obtains when there can be no doubt. For example, when I am looking at something there can be no doubt that I am looking at that thing. When I am doing something there can be no doubt that I am doing that thing. Same with feeling and thinking.
The problem that I have with the idea of knowledge being defeasible is that if it isn't true it isn't knowledge, so if what I think I know is possibly false, then I don't really know it—so I say instead that I believe it and that it is belief, not knowledge, which is defeasible.
As to Descartes, I understand his skepticism to be methodological—an attempt to determine what it is possible for him to doubt. The problem I have is that he doubts things on the mere logical possibility that he might be deceived by an Evil Demon. I think such doubt is absurd. I agree with Peirce:
"Let us not pretend to doubt in philosophy what we do not doubt in our hearts" .
This may seem like quibbling, but he doesn't actually doubt things. He points out that it would be possible to doubt them. Of course he knows that no sane person is going to doubt most of their own experience, but that doesn't satisfy his Method. He wants the grand prize -- absolute certainty, beyond even the possibility of doubt. I personally feel that we don't need that in order to do metaphysics and epistemology; Descartes disagreed, hence his Method. But we really shouldn't see him as raising "philosophers' doubts" for the sake of skepticism. He detested skepticism and believed he had refuted it. (And we have a perfectly good modern version of the Evil Demon: the "Matrix hypothesis.")
Example: X is "Taurize is a village in France." My justifications for believing X would be, let's say, "I've looked in a reliable atlas, and spoken to someone who's visited Taurize and confirms this." (And we could tighten this up ad infinitum, but you get the idea.) Now suppose I want to find out whether X is true -- whether Taurize really is a village in France. Would the facts necessary to do this be the exact same ones cited as my justifications for believing X? Are the two sets completely congruent?
It isn't. Which is why the relationship between the object of the belief and the mental state of the believer is not a causal relationship.
Quoting sime
That's a very good point. But the object will be framed in a language, and that language will be the framework will have been learned from the community.
Quoting sime
Well, the first option is not an option, so it must be the second. But it's not quite right to say that the truth-maker of specific beliefs is decided by the community. The community teaches us about truth and falsity and how to determine it in general. Individuals then apply that framework to specific cases; disagreements will be discussed within the community and, often but not always, an agreement will be reached. (Sometimes the belief will be one that is not determined by the shared rules.)
Quoting sime
Not quite right. Given that I have learned how to determine truth and falsity, I can make a decision. I don't need feedback on each case. Nonetheless, the feedback that I receive is important in maintaining the framework that we have all learned. (It is not impossible for the community to be wrong.)
Quoting J
Yes and no. I think it is more accurate to say that the requirement of truth is a kind of absolute liability. I make my judgements, but they may turn out to be wrong later on. In that case, I have to withdraw my claim.
Quoting J
It's true that we rarely consciously and specifically apply the JTB. It's a formalization of what (normally) we actually do in a messy, informal way. I don't understand what it would be for something to be "pre-JTB".
Quoting J
Asking the question "what is a hallucination?" in the sense that you seem to mean it presupposes that a hallucination is an object. It leads us to posit various other pseudo-objects as if they could magically explain away what puzzles us. But they can't. The whole point is that there is no object. But if you ask what leads us to say that someone is hallucinating, we look at what someone says and does - attributing a hallucination to them presents what's going on in a way we can understand. It is still puzzling and we look for explanations - there's no way round that.
Quoting J
Very true. It is odd that there seem to be no philosophers who actually accept scepticism. They all try to explain it away or neutralize it. Mostly, other philosophers accept the destructive moment, but reject the constructive response.
Quoting J
The problem is that he does not consider what actual limitations there are on doubts, and reduces it to the possibility of saying "I doubt that..." in front of almost any proposition. But if we ask what the content, the reality, the significance, of the doubt is, we find nothing.
Quoting J
I think that the justifications are mostly the same sorts of facts that would show whether X is true or false. But there can be justifications to the effect that I am in a position, have the skills, to know - which are of a different kind or level.
Quoting Banno
I don't think that JTB is the kind of thing that the later Wittgenstein would want to accept or reject - pointing out the consequences of acceptance and rejection and leaving us to make up our own minds is much more his style.
Quoting Banno
I get the point. Applying JTB to a dog seems inappropriate, because the dog doesn't speak. As always with animals, applying our descriptions of what we know and feel to them needs to be done quite carefully. But I think we can attribute beliefs to dogs - and other animals, and we can ask how why they believe what they believe and assess whether their beliefs are true or not. The same applies to experiences - there's no doubt, IMO, that they feel pain, sometimes less and sometimes more. So I don't understand why you say this - unless you are thinking of our inability to know what it's like to be a bat.
Yes, I think so too. Let's see what @Banno says, and then I'll try to show where I'm going with this.
Quoting Ludwig V
By pre-JTB I mean that we would enter the "JTB situation" already believing that X is true. Our belief in X is not a result of what is about to happen if we successfully apply JTB, hence not knowledge. The difference between believing and knowing is important here. If, in trying to determine whether I possess a piece of knowledge, I ask myself, "Is X true?" (a JTB requirement for knowledge), I can only reply, "I believe so." I can't say, "I know it is," because this initiates the vicious circle.
Quoting Ludwig V
I didn't mean it to. It can just as well be an activity or an event. We can still ask what it is, taking "is" in one of its many familiar usages. The question was whether there's a "correct way" to describe the activity of hallucinating using the word "see." I'm saying, no, it's terminological; "see" can work either way.
Quoting Ludwig V
We've talked about this in the context of Williams' book on Descartes. I think you're being too harsh. If it should turn out that I am really a brain in a vat or a Matrix-bound person, then my doubt about the objective references of my experiences is well-founded. It's not merely a linguistic construct. Indeed, this possibility seems much more plausible to me than the Evil Demon! -- though still pretty unlikely. In any case, perhaps we've just set different "limitations on doubts," and what seems doubt-worthy to me, doesn't to you. But surely this kind of doubt signifies more than nothing, wouldn't you say? It's a thinkable thought, and not nonsense.
I'm a bit confused by all this. Someone passes on to me a piece of information. Normally, I would just accept what I'm told because this informant is very reliable. But for some reason I decide to examine this claim more closely. So I set aside my assumptions including my belief that what I have been told is true. Then I ask myself the questions... Short story, anyone with any sense entering a "JTB situation" would and should set aside any assumptions that have already been made.
But there is a problem about the T clause. It is clear that it is not about what my informant knows or beliefs and ot about what I know or believe. Yet any verdict I give on the truth or not of the information is inescapably only what I know or believe. The effect - the significance - of the T clause, so far as I can see, is to require me (and not just my informant) to take responsibility for the truth of the information - to endorse it, in other words. As a result, my claim to knowledge continues to be vulnerable after I have made my decision; if it should turn out to be wrong, I will have to withdraw my claim. On the bright side, if my informant's justification was a bit dodgy, my claim will stand so long as no refutation appears.
Quoting Janus
I think one defeats a claim to knowledge if it is false. Possibly false is far too strong and leads to us abandoning swathes of what we know quite unnecessarily. "possible" does not imply "actual".
Quoting J
Hallucinating isn't usually something that I do; it's something that happens to me. I think of it as an event or process. The point of the concept of hallucination is to allow us to recognize Macbeth's behaviour ("Is this a dagger I see before me?" etc. etc.) as what it is, the behaviour of someone who is seeing a dagger, but cancelling the actual dagger. Compare pretending or acting.
I think it is true that we can equally say that Macbeth is seeing something that isn't there or Macbeth thinks he sees something that isn't there. I would say that the first alternative suggests that there is some thing that he sees that isn't there and so I prefer the second option. `
Quoting J
Oh dear! My memories of that are, I'm afraid, a bit vague. Perhaps I am being too harsh. I would accept that there is a balance to be struck. But I am quite sure that not all possibilities are equally possible. The awkward bit is that the dividing line between them is not at all clear. There's possibilities like the ones that Eliza dreams about when she sings "wouldn't it be loverly" in My Fair Lady or we can be fascinated by like "Battle Star Galactica". I classify these as fantasies and I think they have only have significance for psychology or the philosophy of psychology. There's other possibilities like whether there is still honey for tea or the cream is still fresh. They do have significance for epistemology. Possibilities can change their status. Something that is a fantasy at one time can become a dream and ultimately a reality.
Quoting Ludwig V
This is the nub, I think: It can never be what you know, only what you believe. Never, that is, without raising the specter of the vicious circle. Because to already know that the piece of information is true, that knowledge would have to have been verified via JTB. (This all assumes you think JTB is a good yardstick for knowledge, of course.)
Quoting Ludwig V
Good. Seems that way to me too.
Quoting Ludwig V
Harsh on Descartes, not me, I hasten to say; your forum manners are impeccable. As for vague memories . . . don't get me started. Aging is a fog, obscuring near and far.
Quoting On Bullshit Harry Frankfurt
Notice that knowing is an attitude towards the proposition, hence the requirement that we set out who it is that is doing the knowing. So we want to get to "J knows that p".
According to the JYB account, we must have it that the following are all true:
1. J believes that p
2. p is justified
3. p
Notice that it is the belief that brings J. into the scope of the knowledge statement.
This, at least in part; since it is arguable - and I would argue - that the justification is also an attitude.
Notice that the last, "p", is not justified in any way, nor is it believed - it's just true. It is not about your "finding out" if p is indeed true.
Quoting J
Notice that you are not asking if p is true, but how you find out if p is true, and so again asking about an attitude. The facts that help you decide on your attitude are irrelevant to whether p is true or not.
So, is the idea that we can possess knowledge (i.e., possess beliefs that are justified and true) but we can never know that we possess knowledge (unless perhaps the object of knowledge is our own beliefs or experiences)?
If so, I suppose the idea that the act of understanding involves knowing that one knows what is understood would have to be abandoned. Presumably though, belief is still reflexive in this way. If one believes x, then one believes that one believes this.
Here is a wrinkle perhaps: if Macbeth cannot be certain about the (seemingly external) truth of what a knife is, how can he be certain that he sees a knife (regardless of if it is a hallucination or not)? If he cannot know that he knows what a knife is, then he can, at best, merely know that he believes he is experiencing a knife.
I think absolute certainty is as impossible as radical doubt. You simply cannot doubt everything—some things need to be taken for granted in order to doubt. I agree with you that we don't need absolute certainty in order to pursue metaphysics and epistemology—in fact in the case of metaphysics I would say there can be no certainty at all, that it all comes down to plausibility, because we are dealing with the non-cognitive.
I wasn't saying Descartes raised doubts for the sake of skepticism. Quite the opposite—he was after a degree of certainty which I think is impossible. The Matrix Hypothesis I think is absurd, because it posits that there is a real world in which the virtual world we inhabit is sustained, and this means the need for explanation is just pushed one step further back.
Quoting Ludwig V
I would say that it we determine that something is possibly false then we don't at all need to "abandon it" but merely to abandon the pretense that we know it to be so, for the more modest claim that we believe it to be so. Why do we need to talk in terms of 'knowledge that' when nothing is lost by talking instead of 'justifiably believing that'?
If knowledge were a matter of accumulated atomic pieces, then you are right. But it isn't. We learn how to do colour and at least some of the colours at the same time, and elaborate from there. We learn about solid objects as we encounter them before we can even conceive of them. Then we can deal with individual solid objects as they crop up, whether we have encountered that specific kind before or not.
Quoting J
Have you got a better candidate? I don't recall encountering one.
Quoting Count Timothy von Icarus
Knowing what a knife is is only partly a question of knowing that it has a sharp edge and a handle. It also involves having the know-how to identify knives and distinguish them from spoons and swords. That requires input from other people, who have been teaching me what objects are and how to classify them since before I could speak.
It seems to me that he cannot know that he knows on his own. "I know that I know ..." is pure pleonasm. But it is an important feature of my attributing knowledge to someone that, by passing on the information that he knows, I endorse the knowledge. So "know" not only has space for endorsement by other people, it is built in to the concept as an unavoidable commitment. If I want to avoid commitment, I say that they believe that p. (If I actually disagree, I can say that they think that p.)
Quoting Janus
If metaphysics is about the non-cognitive (which needs a bit more fleshing out), are we sure that certainty and plausibility even apply?
Quoting Janus
Yes, that's right. In the case of the Matrix, it turns out that the real world is the same kind of world that the simulation places us in, so the fundamentals haven't changed. In fact, as we know, there is a case for saying that we already know that the real world is radically different from the world as we know it. No solid objects, everything consists of wavicles. What a nightmare!
Quoting Janus
Well, if there were something to be gained, it might be a change worth making. But so long as we distinguish between true beliefs and false ones, the issues remain. But what are the issues? As I sit here, it is possible that a meteorite or similar is hurtling towards me and will land on my head. I could move and so avoid that disaster. But the possibility applies to anywhere else I might move to. So not only is the probability uncomputable and vanishingly small, but there is nothing I can do to avoid it - apart from living a mile underground, which would have its own limitations and dangers. So I take my cue from my society and ignore the possibility. I haven't been wrong yet.
I think these discussions usually leave out half the issue. If it is wrong to believe something that might not be the case, then, presumably, it is equally wrong not to believe something that is the case. The more cautious you are in avoiding false beliefs, the more you risk not accepting true beliefs. There's no safe territory. But surely to worry endlessly about possibilities that make no difference does not look like a particularly beneficial or even entertaining occupation.
Quoting Janus
We can only pretend something that is possible. So if something is possibly false and we can pretend to know it, then it must be possible to actually know it.
This comes out in an anecdote related by Fania Pascal[/quote]
Thanks for the link. I shall read that soon - possibly today!
It sent me down the rabbit hole, wondering what it is to know what anything feels like and whether it is appropriate to read philosophical significance into what he said. He may have meant the remark simply as a kind of "buck up" reminder. That's something that is, perhaps, rather out of favour nowadays, but at the time, it was common place. I was brought up on "Worse things happen at sea". Once I grew up enough to wonder what the relevance was, it stopped working.
If it does have philosophical significance, we're in the territory of private experiences, aren't we? Wittgenstein doesn't think I know about them - at least not in the same sense that I know about the pain of others. Not because the truth is elusive, but because it is not clear that truth really applies to my responses to my own pains. So the idea that I can know what someone else knows when they are in pain seems - inappropriate. A topic for another discussion sometime.
Quoting Banno
I take your point. Whether I believe that p and on what grounds is a matter that is entirely distinct from the question whether p is true. That distinction is important when I am considering the beliefs of other people. But when I ask myself whether I believe that p, surely I need to consider whether p? When I have decided whether p, I know whether I believe it or not. From my point of view, there are not two questions here, but only one.
Quoting Ludwig V
That's the part I'm questioning. What does it mean to you that something is true? I'm guessing it would be some version of Tarski truth. So how could that possibly be independent of the grounds of justification? That seems to be setting up truth as some quality or property that just is. But we all know that's not right: truth is a property/attribute/quality/judgment/or whatever of propositions, not objects.
Quoting Count Timothy von Icarus
Not quite. I'm saying that this would be the unwelcome conclusion if this way of construing JTB is adhered to. To avoid this conclusion, I'm suggesting we alter or abandon JTB, not our confidence that we can know we have knowledge.
Quoting Janus
But Descartes' doubt isn't about explanation. He believes it's possible to doubt whether my experiences are veridical -- that is, of the things they appear to be of. He's not questioning experience in general. The Matrix hypothesis would represent such a doubt.
Yes!
And thanks for introducing me to "pleonasm".
Quoting Ludwig V
There's a tension in his writing that it might be best to acknowledge rather than to try to sort out. This is an issue I;ve raised a few times with @Sam26. I read Wittgenstein as saying, for instance, that if knowledge is justified true belief, then we don't know we are in pain - becasue the justification just is the pain - but he also insisted we "look, don't think", and so that nevertheless he would note we do use "knowledge" in this way. There was a time, when cars became commonplace, were the corpses of slow-witted dogs littered the streets, their mangled remains a common sight that might well be used to explain how one felt after surgery. Wittgenstein understood Pascal's use, and so her meaning. In his own terms, he was being obtuse. The conclusion, perhaps unpalatable to Sam, is that we do use talk of knowing in ways that are not only about justified true beliefs.
Quoting Ludwig V
How does asking oneself whether one believes that p differ from asking oneself if p is true? The response here must be much the same at the one you just gave to Tim... "I believe that is it true" is pure pleonasm.
Now it's tempting to think that therefore the JTB account amounts to only justified belief. But this fails to recognise that there is also a difference between somethings being believed and its being true. That difference is what allows error.
The "T" is JTB is not about deciding if the proposition in question is true - that's the prerogative of the "B" - it is about insisting that we cannot know what is not true.
Hold truth steady. Then belief that p is holding p to be true, even if it isn't. And knowing that p excludes p being false. The structure is consistent.
That's an interesting question. If everything we cognize is counted as "physical", then would not metaphysics, thought of being what is beyond the scope of physics, or any other science, be thus taken to be dealing with the non-cognitive?
Quoting Ludwig V
I want to note that I'm not saying we don't know anything—I'm saying that in those cases where we can be said to know something, we know (again, radical skepticism aside) that what we know is true. It seems to me if we do not know that, then it doesn't count as knowledge but as belief. It could be justified belief, and then it would that its truth is highly plausible, but that still falls short of knowing it is true.
It seems to me that your meteorite example with the conclusion that you should "take your cue from society" and ignore the mere possibility just counts as an example of a justified belief—you don't know that a meteorite is not going to strike you on the head, but you could be said to know that the chance of its happening is miniscule, so knowing that it is highly unlikely means that believing it would be to believe in an extremely implausible event.
Quoting Ludwig V
I don't know...perhaps you are misunderstanding me—I'm not talking at all about being cautious in trying to avoid false beliefs. but about avoiding thinking and saying that I know something if I cannot be certain about it.
Quoting Ludwig V
I'm not certain what you are saying here, but the question that comes to mind is whether it is possible to know something without knowing that know it. The very idea just seems wrong to me. JTB does seem to make this possible, and for me that is to its detriment.
Quoting J
I'm not saying that Descartes considered the Matrix hypothesis at all—I don't think he did— because as I said I think the Evil Demon scenario is really very different, apart form the idea of being radically deceived in both scenarios.
In the Matrix scenario there is no skepticism about the real world—in fact that is what those who see through the virtual illusion are trying to get back to. If Descartes considered this he would still be faced with the question of being able to doubt the purported real world just as much as he can doubt the virtual world of the Matrix.
By introducing "explanation" I meant to refer to the question as to how we could be certain of the reality of anything. We can doubt the virtual world, but how can we be certain of the reality of the world within which the Matrix is sustained?
.
It's VR all the way down...?
Here we must ask if John's understanding of mathematics is relevant to the mathematical truth of his utterance:
From the perspective of the mathematics community other than John, the answer is clearly no; for whether 2 is a prime number is not decided by John's understanding of prime numbers but by a computable proof by contradiction written down on paper and simulated on a computer, that bears no necessary relationship to the hidden causal process of John's neuro-psychology, even if the two are correlated due to John being a trained mathematician.
On the other hand, from the perspective of John, who isn't in a position to distinguish his personal understanding of mathematics from our actual mathematics, the answer is clearly yes. So we have two distinct notions of truth in play: Intersubjective mathematical truth, for which the truth maker is independent of Johns judgements whether or not his judgements are correlated with intersubjective mathematical truth, versus what we might call "John's subjective truth" in which the truth maker is identified with the neuropsychological causes of John's utterances. If John is a well-respected mathematician, then we might be tempted to conflate the two notions of truth, but we shouldn't forget that the two notions of truth (causally determined versus community determined) aren't the same notion of truth.
H'mm. Maybe. But I think you may be getting into an unnecessary tangle because you (seem to be) focused on the special case of "I know that I know.." Anyone who asks themselves the question whether they know that p is to ask themselves the question whether p. When the latter question is answered, the answer to the former question is also answered. (Of course, this can't be generalized; it does not follow that S knows that p follows from p. That's the first person case is a limiting case.)
I recognize that in certain circumstances "I know that I know that p" might have a point. But it doesn't add any cognitive value to p asserted by me. (So long as p is true.)
Quoting Banno
Yes. Things are often not quite straightforward with Wittgenstein. I don't know what he would say. But I stick to the view that "I know I am in pain" is a non-standard use of "know", based on the similarity that it would be very strange to assert of anyone that they are in pain and do not know it. Such cases as there are emerge from the fact that other people can tell whether I am in pain or not, so they can't be used to support pain as a logically private experience - which, after all, is his main target.
Quoting Banno
H'm. Survival of the fittest. But I suggest that that use would be an expression of pain, rather than a description. In which case, not knowing would not be the issue.
Quoting Banno
Well, yes. Knowing how and knowing by acquaintance might be examples. But that's a restriction of the scope of JTB, not a refutation. JTB may be a mess in many ways, but the lack of any articulate competition suggests to me that it does capture something important.
Quoting Banno
Yes. That's why we would need to invent the concept of belief if we did not already have it.
Quoting Banno
Am I right to take you as saying the B clause reports the view of the knower/believer, but the T clause reports the view of the speaker and commits them to changing their mind if it turns out later that they are wrong.
Quoting Janus
Yes. But I reject the antecedent. We cognize many things that are not physical. Mathematics for a start.
Quoting Janus
I take the point. But a lot depends on how you define certain. If you define it as something that's not possibly wrong, I would have to take issue with you. Something that is possible can possibly be actual and can possibly not be actual. So the strongest definition of certain is too strong.
Quoting Janus
Maybe I'm confused. In general, I think that "S knows that S knows that p" is not ungrammatical, but is empty. The only kind of case that would give it some content is a situation in which S knows that p, but is confident that they know that p. (Someone who answers questions correctly and can justify their answer, but is hesitant, for example.) But their hesitation is not about whether they know, much less whether they know that they know; it is about whether p.
Quoting Janus
I suppose you are right. If he did find some convincing evidence that he is being fooled by an evil demon, he would have to doubt whether he is being fooled by an evil demon. Before he could accept this alternative view about reality, he would have to subject it to his methodological doubt.
Quoting Banno
Quoting Janus
I have sometimes wondered whether we should not start by accepting that we are all already brains in a vat.
Alternatively, we could accept that some things are self-supporting structures and do not require foundations.
Quoting sime
But causal processes aren't true or false - except when we have determined a suitable interpretation of them, or set them up in such a way that an interpretation of them can be derived from them.
Quoting Ludwig V
Upon reflection, I think you might be right (at least in the JTB context that isn't committed to fallibalism). We can "know that we know" just by believing that we know, and it being true that we know.
However, if we pair JTB with a sort of fallibalism that denies any certitude to beliefs, or at least most beliefs, which seems to be a position that JTB lends itself to, then I do think it follows that we can never know that we truly know anything, as opposed to merely believing it. Another way to say this is that, if we believe our own belief might be wrong, we don't seem to believe that we know it, since knowledge is necessarily true, and we can hardly believe that something that is true might also be false.
I see. I think JTB is flawed but figuring out just how is tricky. JTB seems very thin and portable, but I think an investigation of the metaphysical context in which it was developed is helpful for diagnosing it.
One solution here, that I'm sure no one will like, is to simply do what analytic philosophers have done for "evaluative" knowledge claims. We could suppose that statements of knowledge and statements of fact should simply be reinterpreted the way evaluative statements are, such that:
"P" is "hurrah for asserting P!" or "I believe P," or "from my perspective, P."
And then, if we don't like this solution, it's on us to show why we think there needs to be something of the sort where "P is *really* true," and that we must be able to assert that this is so, or even "know" it, and how exactly that is supposed to work, since it seems one could function "pragmatically" whilst only speaking to one's own beliefs without "knowing" that any other beliefs exist. After all, others' first-person experiences and beliefs are generally accepted to be ineluctably private, so prima facie there can be no empirical support for them, whereas there can be no empirical support for anything outside of such experiences for us. And so in the end, what difference could it make that would warrant rejecting the suggested translation here? One can, and in fact must, constantly be making pragmatic decisions without knowledge, and so it seems superfluous.
Quoting Janus
Well, physicalism is a metaphysical position, so we could quibble that the label here is a bit biased. I see no reason why a strict empiricism should be positing anything like physicalism or "the physical," which would be metaphysical speculation. For instance, causes, of which "other minds" would simply be a special type, are a sort of additional metaphysical posit above and beyond regularities in experience.
Excellent. My concerns with JTB are all about how the truth of P is supposed to be established. @Banno recommends just starting with that truth, which seems similar in spirit to the pragmatic approach you describe. I'm still thinking it over.
Quoting Janus
I don't think so. Descartes' skepticism is not about the real world. It's about whether my experiences are veridical. He's not saying that, if these experiences are not veridical, then there is no real world. He's saying we can be deceived. Presumably the Evil Demon can be undeceived, just as the Lords of the Matrix can be.
Quoting Ludwig V
I can see how you would think that. I probably could have expressed it better. But the "know that I know" issue comes up within JTB itself. If it's right that we can't know X is true via JTB (since it's an element of JTB, not a result, and would require a previous demonstration of knowledge), then we might never know whether we know a given X, since we wouldn't know if X was true. So "know that I know" is really meant to express "know that JTB is satisfied."
I don't know what you mean by "John's subjective truth." S is either true or false. Having a limited, subjective perspective just means there is fallibility that, for instance, Laplace's demon wouldn't have. John and Laplace's demon have the same conception of truth. John has to live with the possibility of being wrong. The demon obviously doesn't have that problem.
I see doing mathematics as a physical activity, involving pencil and paper, computer, or neural activity.
Quoting Ludwig V
Perhaps we are speaking at cross-purposes. If say I am certain that something is the case, then I mean that there cannot be any doubt about it. Then I would say I know it to be the case. If I think something is the case but there is any possible doubt it, then I would say that I believe it to be the case, but do not know it to be.
In the first case, if someone pointed out that there was some real possibility of doubt, and convinced me of that, then I would say I had been mistaken in thinking that I knew whatever it was to be the case.
Quoting Ludwig V
Say I believed that something is the case, and for very good reason, despite thinking that there was some small possibility which could cast a doubt about it—then I would say I believed it, but did not know it, to be the case. Then say I found out that the small possibility of doubt had been unfounded—I would then say I now know it to be the case.
But if I had justifiably believed it to be the case previously, despite thinking there was a small possibility of doubt and the small possibility of doubt turned out to be a mistake, then according to JTB I would have already known it to be the case despite the fact that I didn't think I knew it to be the case. That would be knowing despite not knowing that you know. And that just seems weird to me.
Quoting Count Timothy von Icarus
I would say that everything cognizable via the senses as well as our bodies and the act of cognizing itself, if a neural activity, all count as physical. Causation may not be directly perceived, as Hume asserts, but causes and effects are always physical phenomena.
Quoting J
Surely skepticism about the veridicality of experiences just is skepticism about the external world? I'm not sure what you mean by saying the Evil Demon or the Lords of the Matrix can be undeceived.
I'm sort of wondering what context people take JTB to be coming from. That some are referencing Plato and others are referencing Ayer is a pretty significant difference!
The problem with J's objection, as has been pointed out...
Quoting J
...is that it is an objection to any theory which says that truth is supposed to be established prior to justification and investigation, and it is also linked to J's belief that truth and understanding are, properly speaking, impossible. The first problem is that there is no theory which says that truth is supposed to be established prior to justification and investigation. That is a strange strawmen that has persisted for page after page. The second problem (which is related), is that if you are opposed to truth and knowledge, then why single out JTB as if it has some specific difficulty?
I think the core problem here is J's Humean "game of pool" epistemology. If every belief is reducible to a guess and the mind never merges with its object in reality in the way that Aristotle describes, then J's conclusion that truth and knowledge do not exist is foregone. All of this meandering and ignoratio elenchus is just a working out of that Humean presupposition.
Quoting Count Timothy von Icarus
As noted earlier, I think the problem with the way people are here conceiving of JTB lies precisely in seeing justification as material rather than formal. In seeing an unsound justification and a sound justification as equivalently sufficient conditions for knowledge. In conflating a false explanation with a true explanation, and inferring that someone who possesses the false explanation possesses the requisite justification.
JTB declares that we possess knowledge when our justified beliefs are true. The problem, as I pointed out earlier, is that if we don't know whether the justifications for our beliefs are themselves true then where does that leave us? How do we know they are adequate as justifications?
Or looking ta it the other way around, take the Theory of Evolution, for example. It seems we are amply justified in thinking it is true, but we don't really know whether it is true. Can the justifications for thinking it true be themselves true even if the theory is false?
Quoting Leontiskos
Hume was skeptical of what cannot be observed as "matter of fact". If I know you well, and I see you fall off your bicycle, there can be no doubt in that moment that I see you fall off your bicycle, so I can say that I know you fell off your bicycle because I saw it happen. How long does the "no doubt" situation last, though?
That would be down to the accuracy of my memory. I might say my memory is very good and has been well-tested over the years and hardly ever fails me, and even when it does only in small matters, not significant ones like you falling off your bike, but that doesn't logically entail that my memory remains reliable, or even that my memory of the results of my memory being tested is accurate.
I do accept that there may be some qualifications and caveats and that it seems very hard for fallibilism to escape from the problem that we can't be said to know p if p is false.
Quoting Count Timothy von Icarus
To be honest, those kinds of fallibilism seem incoherent to me. Something that might be false may in fact be true. To put it another way, the possibility of p being false seems to me to be irrelevant to the question of knowledge. What is relevant is whether p is or is not false, on the assumption that if it is not false, it is true.
Quoting Count Timothy von Icarus
In one way, you are pushing at an open door. "Know" is one of a large group of terms that express an attitude to, or an evaluation of P. But such an approach would need to include assertion as part of their meaning, as well as an attittude towards what is asserted. But it's very complicated. "Know that p" includes an evaluation of p as true, so it indirectly asserts p. "S thinks that p", on the other hand, includes an evaluation of p as false and therefore denies p. Supposing that p is more complicated; it doesn't assert or deny p, but asks to treat p as true (usually for the sake of an argument. And so on.
Quoting Count Timothy von Icarus
Well, my approach would be to explain that certainty and doubt, possibility and impossibility, etc. are meaningless without a concept of truth.
Quoting Count Timothy von Icarus
You are treating those philosophical ideas as if they are true or make sense. If they don't make sense, we need not bother with them when defining knowledge.
Quoting J
But we don't know that X is true via JTB, but via whatever the truth conditions are for X.
Quoting sime
This is a false dilemma. John's subjective truth will be conditioned by his understanding of what mathematical truth is, which he has learnt through interaction with others who teach him. Unless that has happened John may have a subjective opinion, but it doesn't count as a mathematical opinion.
Quoting frank
Sure. He also has to live with the possibility of being right. But he can live with neither possibility unless he knows what it is to be wrong - or right.
Quoting Janus
OK. Is there any activity that you see as a non-physical activity? Unless there is, you've deprived "physical activity" of its meaning.
Quoting Janus
There is a difference between the possibility something might not be the case and it actually not being the case. You are treating mere possibilities as if they were actual.
Quoting Janus
That seems reasonable. I'm still doubtful about your "small possibility".
Quoting Janus
Why? Where does it say that it is not possible to know something but not to know that you know it? It isn't like a pain or a taste, where what I say determines the truth. I suspect that you are thinking of the first person "I know that I know..." But it is perfectly possible for me to say "Janus knows that p, though he thinks that he believes it."
Quoting Leontiskos
No, you are quite right. Justification and investigation are how we determine the truth.
Quoting Leontiskos
The issue here turns on justifications that provide evidence, but not conclusive evidence. In the context of JTB, such justifications can work, because the T clause denies claims to knowledge based on partial justification when their conclusions are false.
Quoting Janus
Yes, if the justification is not conclusive - i.e. not sufficient.
Well, but there's the rub -- we do. There are two ways of knowing that X is true, on this construal of JTB. We can verify the truth conditions of X (and remember, this a convenient phrase that contains its own puzzles and disagreements), or we can deduce, from the fact that we have JTB of X, that X is true. If you tell me, "I know X, because I have JTB of X," and I believe you, then I know, or at least believe, that X is true, without knowing anything about its truth conditions. Can this work in the first person? Can I myself have JTB of X without knowing the truth conditions of X? This puts us back to justification, and what counts as a good one. Is personal verification of the truth conditions the only truth-guaranteeing justification? Or, if "guaranteeing" is too strong, the only good-enough justification?
Quoting Janus
I see why this is attractive. "Possible doubt" is the question, though. Is it possible that the sun will not rise tomorrow? (and of course I mean "sunrise" as shorthand for what actually occurs). Well, yes. An alien civilization inimical to ours might choose tonight to destroy our solar system. That is not impossible, or incoherent, or against the laws of physics, etc. Yet I, and I think all of us, would be happy to say that "The sun will rise tomorrow" is a piece of knowledge. As I say, I'm sympathetic to why you'd want to tighten up "knowledge" so it equates to "certainty" but is that really what we mean when we say we know something? Or would you want to argue that solar death by alien attack is impossible? On what grounds?
Mm, not so sure on this.
https://en.wikipedia.org/wiki/Mirage
To go toward the mirage is Justified True Belief (if one is not familiar with modern day science). And who knows, it might lead to water. Eventually.
It certainly is better than nothing. And sure, to your credit, only a fool would not follow such. But... not all who survive to live good lives are wise men, and not all who perish foolish deaths were fools. Something to keep in mind. :smile:
I'm not clear why this would be JTB. Even the ancients knew about mirages, judging from classical literature. And, in the unlikely event I had the presence of mind to ask myself, there in the desert, whether "That is an oasis" is a JTB, I would answer no; I don't have a good-enough justification, or an independent fact-check, to include it as a T in the formula. But a guy can hope!
I would think it isn't. We just act like it is true until we are prompted to reconsider.
Quoting Ludwig V
Doesn't that have to answer the possibility question. If P is true, it cannot possibly be false.
But the question isn't whether P is itself possibly false. Rather, it is, do we think P is possibly false. If we think P is possibly false, then it hardly seems that we can know that we know P, since to know that one knows P is to have the justified true belief that P is itself a JTB (which presupposes that P is true, in which case it is impossible for it to be false).
Quoting Ludwig V
What sort of concept though? Rorty's move to redefine truth as "what our peers let us get away with is [I]a[/I] conception of truth.
I do think this is one of the key problems for JTB. What is meant by T is generally thin, and by being thin it is opaque. It doesn't avoid having to posit a certain metaphysics of reality versus appearances/belief, but it often isn't clear about what this metaphysics is.
As for affirmation, I think the "retranslation " approach would just redefine affirmation. To affirm P, rightly understood, doesn't mean "P is the case, regardless of what we all believe." We've redefined truth, so affirmation is different now too. Affirming P is a sort of endorsement. "It is good to believe P," where "good" is also "hurrah for..."
Well, I was going to respond to you before about "infallibalists," but I figured it might be beside the point of the thread. The classic examples of infallibalists are first and foremost Descartes, but then also generally the "Neoplatonists." But the "Neoplatonists" generally have it that even creatures are inexhaustible, and so we can always be wrong about particular judgements related to them. Likewise, we can always be wrong about the mutable world around us to the extent that it is always changing and not wholly intelligible in itself (e.g., there are no perfect triangles or circles in nature).
To understand something is to understand its context, which is, exhaustively, to understand everything. Likewise, to understand something exhaustively is to understand its causes, which would mean fathoming the First Cause and Principle. But this is deemed impossible. Eriugena denies any sort of exhaustive (and so infallible) knowledge in the opening pages of the Periphyseon, drawing on Dionysius the Areopagite and Saint Gregory the Theologian as authorities. Saint Maximus makes a similar point in the Ambigua.
What then in infallible? Well, one can hardly understand a triangle and have actually understood nothing (understanding is not created ex nihilo). Illusion is parasitic on being on their view. Appearances cannot be arbitrarily related to reality (or else they wouldn't even be properly "appearances," but rather free standing acausal apparitions). I suppose the phenomenological distinction between the object of knowledge and intentionality and the knower is important here too.
I think the difficulties for truth and knowledge crop up when the metaphysics of reality versus appearances is ignored, and so we default into this thin idea of "p is true if p." There is no explanation of how the being of p relates intrinsically to the thought of p. Appeals to cognitive science or the physics of perception don't end up being able to bridge this gap if they themselves are viewed as largely a matter of pattern recognition within appearances. Fallibalism will be unavoidable, except perhaps within the realm of our own experiences (a sort of solipsistic tendency).
What is odd to me is that, rather than going back to the drawing board on the metaphysics in question, the historical move has generally been to instead equivocate on "truth" and "knowledge" such that we can be led to epistemic nihilism, but that's ok because truth and knowledge are really just these other things (e.g., useful behavior). But epistemic nihilism never resulted in people poofing out of existence, or going catatonic. They always continued to act "pragmatically" anyhow, so it's unclear what the value of such a rhetorical exercise is supposed to be. Although I will add that the fact that people are incapable of living like they believe nihilism is true is precisely what you would expect if their intellects were being informed by the world around them; they would be unable to shake off their understanding. No matter how hard they reasoned about the groundlessness of their own knowledge, they would still run from rabid dogs like Pyrrho or climb a tree to get away from raging bull elephants like Sanjaya.
I have trouble with that; surely the justifications matter? Can we act like P is true -- that is, assert that we have the T for JTB -- if the justifications aren't strong? I come back to the question, What is JTB for? Is it a theoretical, criteriological account of what it would mean to know something? Or is it supposed to actually help us evaluate a given piece of putative knowledge?
Right, and to restate my point, @J's objection holds against any theory of knowledge which takes truth to be a necessary condition of knowledge, and this is not just JTB, it is pretty much every theory of knowledge. "Truth can't be a necessary condition of knowledge," is not merely an objection against JTB; it is an objection against the traditional understanding of knowledge in toto.
Quoting Janus
As I have said in the past, I would want to use the words valid/invalid and sound/unsound for justifications, and true/false for propositions. That itself clears up part of your conundrum, albeit not all of it.
Going back to my earlier point, if we read JTB as referring to "justification" materially, then in my opinion it fails. If we read JTB as referring to "justification" formally, then in my opinion it does not fail. But the first option seems uncharitable and strawman-ish.
Regarding Evolution, I think it is clear that the theory of Evolution is not knowledge in the strictest sense (scientia), and therefore it is not demonstrable. The theory of Evolution involves precisely the sort of probabilistic guesses that some take all knowledge to be bound up with.
Again, part of the problem here is that some want JTB to offer a recipe for knowledge, as if we could know that we know with perfect certainty via JTB. Whether this is possible is an interesting question, but even if some kinds of knowledge could fit into that category, Evolution cannot. Note though that if we can know that we know some things with perfect certainty, then the J and the T will be inextricably bound up with respect to those things. Contrary to @J's claims, this does not mean that the J and the T are indifferentiable, but it does mean that a biconditional holds between them in the case of demonstration.
Quoting Janus
If we take Hume's theory to its logical conclusion, then it is not permissible to trust your eyes because there is no valid argument to the effect that your eyes are trustworthy, or that your eyes are providing accurate information in that moment when you see me fall.
The way that this would manifest in @J's thinking would be to say, "My belief that you fell off your bicycle could be false, therefore it is not knowledge." He would just offer the possibility of, say, unreliable faculties, hallucination, etc.
Quoting Janus
Right, but Hume would say that even if you've pocketed the 9-ball in this identical situation 1,000 times in the past, it doesn't follow that you will pocket it this time. Even if we grant that your memory has been accurate in the past, it doesn't follow that it is now accurate.
---
Quoting Ludwig V
Right.
Quoting Ludwig V
I think there is a problem with this account, and I think the problem is precisely what Gettier points up. Gettier shows that someone can have belief, truth, and inconclusive evidence, and still fail to have knowledge. (But I am going to come back to your earlier posts in this vein. I am still catching up.)
---
Quoting Count Timothy von Icarus
Right.
Quoting Count Timothy von Icarus
As I said earlier, I think it is a tangent. The crux is certainty, not infallibility. You can get to certainty via infallibility, but the claim that the only way to get to a certain judgment is through an infallible faculty is at best contentious.
Quoting Count Timothy von Icarus
Sure, but going back to Aristotle, if the identity of mind and object is true, then you do not have global uncertainty. If, on the other hand, like turtles it is "probabilities all the way down," then uncertain guesses are all we are afforded. The question here is whether the intellect is capable of certain knowledge, given its relation to the objects of knowledge. If there is a Humean severance between mind and its object then Aristotle is wrong and we are playing a game of pool where everything is an extra-mental collision that cannot be grasped by the mind with certainty.
Quoting Count Timothy von Icarus
Yes indeed. So one ends up professing to believe something that they simply do not believe, given their actions. And whether what one cannot-but-believe is also known will depend on one's epistemology (and metaphysical anthropology).
I so far take it that justifications always come in degrees of strength. And that this corresponds to the strength of knowledge had.
For knowledge that “one rock and another one rock will equate to two rocks” the justification is, or at least can be, extremely strong. Such that one cannot find any justifiable alternative to the contrary, much less any credible alternative to the contrary.
For knowledge that “one will exercise later on today (because one so intends to exercise)” the justification is by no means as strong as the aforementioned. (Or else knowledge that one’s airplane will arrive at such and such time.) For this knowledge claim there are alternatives which can be justified, only that one does not find any such alternative to also be credible. (For example, the alternative that one possibly won’t on account of spraining an ankle can be technically justified, even if one doesn’t find it in any way credible.)
Yet they both are, or at least can be, knowns in the JTB sense. Just that the first is a much stronger known than the second, precisely due to the justification for it being of such nature as to far better assure the truth of the matter no matter what.
BTW, I get that the first known doesn’t address a future event in the same way the second does. These varying degrees of knowledge are not strictly limited to future events though. Consider that the same can be said of knowing that a certain memory one has is true rather than being, at least to some extent, a false memory—this even when two or more people share the same memory.
The ontological truth of the matter involved yet remains determinate, fixed, this even if the given truth hasn't yet occurred. It’s the justifications for this truth that provide the structures needed to epistemologically validate the truth maintained via belief.
The only time that knowledge doesn’t come in degrees of strength but instead is a strict binary is when one considers there either being absolute knowledge or else no knowledge at all. The latter being an outlook I disagree with.
As to why a weakly justified true belief can be deemed knowledge rather than mere belief: it depends on the amount of risks one is willing to take in assuming a weakly justified belief to be ontologically true and thereby knowledge. If one is OK with the possibilities (but, again, not the plausibility) of being wrong and the consequences of so being, one then can choose to declare this weakly justified belief to be a known one is endowed with. If one instead prefers to remain on the safe side, one can instead simply declare it as a belief one has.
Hence, in most ordinary circumstances, one will affirm knowledge of what one will do later on in the day (or else of when one’s airplane will arrive), this serving as one example among many.
--------
p.s. For example, it would be odd for a typical westerner to say "though I believe it, I don't know whether I will eat anything tomorrow".
To elaborate:
Quoting Leontiskos
@J is basically saying, "We must reject JTB because it makes truth a condition for knowledge."
"We must stop drinking milk because it contains water."
I would respond, "There my be good arguments for rejecting milk, but this is not one of them. This is an argument against water more than an argument against milk. Or rather, it is an argument against water dressed up as an argument against milk."
What is at stake here is an argument against truth dressed up as an argument against JTB.
I think the central argument is as follows, and you have been wrestling with it throughout your posts:
1. If something could be false, then we do not know it
2. Everything could be false
3. Therefore, we do not know anything
Most rejoinders in this thread have attacked (2) by trying to point to certain beliefs that could not be false.
As for your other argument:
Quoting Janus
First I would say that justification and truth are not altogether separate notions. The telos of justification is truth. If there is no truth then no justification is doing what it attempts to do. Thus it is a mistake to conceive of justification as this animal which has no intrinsic relation to truth.
Second, the Aristotelian way to develop such an idea is to identify different kinds of justifications or arguments or explanations. Once we can see that justifications come in different shapes and sizes, we can see why some are better at obtaining the aim of truth than others, and what makes for that difference. Once this is established we are no longer faced with the problem of all justifications being equal (equally sound or unsound).
The offer certainly is not mere pragmatism. That one rock and another rock is two rocks is not a question of practicality so much as of grammar. The suggestions that there are different types of truth, as opposed to different true sentences, is hopeless.
Tarski's theory of truth is the most we can do here without falling into error. Truth is a logical device, setting out the move between a sentence and what is says.
The "T" in JTB is that move.
That's circular. You can only satisfy the JTB if you know that X is true.
Quoting J
That is indeed a problem. But we can't solve all the problems at the same time. For the purpose of defining knowledge, we can assume that we have a concept of truth and worry about what it is on another occasion.
Quoting J
Well, that seems a bit radical. Most people, I think, believe that knowing at least the outline of the truth-conditions as part of understanding the meaning of what one is signing up to.
Quoting J
So you accept knowledge based on authority. I'm a bit surprised - it is quite unusual for philosophers to accept that. They usually, if only by implication, seem to believe that only first-person verification is satisfactory. That's a very strict criterion and cuts out most of what we (think we) know.
Quoting J
That's fantasy, not a real possibility. On the other hand, the possibility that one of our superpowers will make that decision and actually try to do it. That's a real possibility.
Quoting Count Timothy von Icarus
I'm a bit puzzled about you are getting at here. It's my move in a chess game. I have various possibilities with the rules. Many of them have little or no strategic or tactical value. I decide on one and make it. All the other possibilities are ruled out. They were possibilities, but are no longer. Similarly, when I set out to decide whether P, there are (barring complications) two possibilities - that it is true, or that it is false. If I decide (correctly) that it is true, then the other possibility is ruled out.
Quoting Count Timothy von Icarus
I don't think we have to develop our understanding of knowledge to be compatible with every theory of knowledge. If we are not committed to a theory, we take for granted our existing concept, whatever that may be. It we are committed to a theory and it makes a difference to the epistemology, then, of course, we need to take it into account.
Quoting Count Timothy von Icarus
For me, the question whether P is true and the question whether I think that P is true are the same question - or rather, the answer to whether P is true determines whether I think that P is true. Something similar would apply to a question whether we think that P is true.
Quoting Count Timothy von Icarus
Quite so. Asserting P is a speech act, and it has various effects, which are usually called forces. The standard taxonomy has three, as I'm sure you know. The difficulty is to utter P without some sort of illoctuionary or perlocutionary force. The ground for thinking that the content is distinct from the ancillary forces is that we can utter the same proposition with different illocutionary forces. We can assert, deny, suppose, know, believe and think that p.
Quoting Count Timothy von Icarus
Yes. Though that formulation of the point leaves open the possibility of claiming special status for the theoretical context that is philosophy. It is probably better to point out that such sceptical beliefs have no significance.
On the other hand, one might give up on digging oneself into ever deeper holes in pursuit of grounds and admit that knowledge, in the end, is a self-supporting structure. If it's good enough for the planet, it is surely good enough for knowledge.
Quoting javra
Knowledge of what one will do later in the day is not quite the same as having intentions or plans for what one will do later.
Quoting javra
There is no safe side. One may prioritize avoiding believing something false, but that raises the risk of failing to believe something true. Both are wrong.
Quoting Leontiskos
OK. You know where I stand on Gettier. Though I would like to add that the analysis I gave earlier of his case 1 is not a model for other examples. The point of attack is the same, but the analysis has to be worked out in each new context.
Quoting Leontiskos
No, of course. Though as Hume points out, you are going to believe that you will succeed next time because you have succeeded before. Who's to say that's wrong, given that deductive logic doesn't apply.
Quoting Leontiskos
If that's what Aristotle or Aristotelians say, I can see a certain sense in it. But there is the tricky problem how I avoid being burnt to a crisp by the sun.
Quoting Leontiskos
You may well be right.
Yep. I pointed this out a couple of times previously. Quoting J
Again, there is a difference between P being true and it being established that P is true. @J still hasn't taken this to heart.
Tim is playing pretty loosely with "possible". It's not the case that if some sentence is true, it is not possible for it to be false, in any but a very limited way.
One knows one will go for a walk later today if and only if one does indeed go for a walk later today. that is, if "I will go for a walk later today" is true. Otherwise, one was mistaken in thinking that they know they will go for a walk.
I hope that's pretty clear. Seems it is to you, Ludwig, but not so to others here.
Of course it's circular. But doesn't it follow? If "My aunt lives in Denver" is a JTB, it must be the case that my aunt lives in Denver. No further verification is required. My point is precisely that this is absurd. To avoid the circularity, you have to posit X as true without knowing it to be true, whether on the grounds of pragmatism or T-truth or grammar or something else. That's the move I'm still considering.
Quoting Banno
I feel like one of the blind guys that's got a different part of the elephant! The difference is completely clear to me. What isn't clear is what JTB is supposed to be used for. As I asked above, "I come back to the question, What is JTB for? Is it a theoretical, criteriological account of what it would mean to know something? Or is it supposed to actually help us evaluate a given piece of putative knowledge?" If you've addressed this already, my apologies, but could you say again?
Quoting Banno
Yes, this has to be correct, it seems to me, with the stipulation that the result will be some true sentences and some false sentences. A great deal of the conversation here centers on how certain we can be, or have to be, about the status of T.
Quoting Ludwig V
A little too breezy for me! But I see what you're saying; perhaps I'm just being stubborn in wanting to get a preview of what the concept of truth must be, in order for JTB to work. Or see above: Maybe we're simply not sure what the work of JTB is.
Quoting Ludwig V
Indeed. I can only say that, in practice, we use "know" rather differently than that. Philosophers can recommend ameliorating our less rigorous usages, of course. Then "know" becomes a sort of technical term. Do I not know that, say, general relativity is true, because I can't personally verify it? I'd contest that. I feel a great deal more certain of general relativity than I do of many of my own apparent perceptions!
Well, no. If S is some sentence that satisfies the criteria JTB, then by that very fact it is true; by that very fact it is already verified; and by that very fact we already hold it to be true. The circularity, so far as there is one, is in your then asking "But is it true?" - and the answer is a resounding "yes".
Well, on a "pragmatism all the way down" account I assume that J would be a mix of cultural norms and personal norms that have been wired into us via induction through past experiences. A reductionist might want to boil this down to "fire together, wire together." We receive constant feedback, are constantly interacting with the world, and so develop a set of predictive, justificatory practices.
Consider the position that "causality" is just a sort of pragmatic narrative-making exercise. The idea that empiricism is incompatible with causality goes quite a ways back, and obviously there is disagreement about how strong the arguments against causes are. However, they have generally be taken seriously, even if Russell's full eliminativism hasn't been universally embraced. At any rate, if the objects of experience cannot be said to be the cause of our perceptions of them or of our intellectual understanding of them (or if all we have is a Kantian "limiting relation), except by "useful" convention, then in what way are experience and understanding ever "justificatory?" It seems they are so only just in case we come to find them useful ("find them so," not that they are so, since to claim that something is truly useful in the old sense of "truly" is simply to invite the same set of problems).
You can find such a path fleshed out in different aesthetic modes though. There is the Continental version, which offers a sort of metaphysical explanation of how pragmatic seeking generates reality (and so truth) through phenomenological arguments, a linguistic variety that tries to be bare bones, and a conventionally naturalist, eliminitivist variety (which appeals to neuroscience and evolutionary theory, while allowing that these are of course "true" only so far as it goes).
It seems to me though that the outlines of such a path can be seen in Locke, Hume, Kant, and more so by the time of Dewey and James. The basic issue is: "do the acceptable sorts of "justification" ever secure the truth of what is being justified?" If not, how is the J criteria ever met? One option here has been to leave J is place and to start fiddling with the definition of T. I don't think B is unproblematic either though, to the extent that the analysis tends to focus on linguistic propositions and how those are supposed to relate to truth is another question.
That's why I say the J, T, and B are more loaded than they might first appear. For J, what constitutes justification? Is there ecstasis, a going out to the known, or act of understanding that is justificatory, or is it all discursive relationships between observations or the deductive unfolding of tautologies? Is the dissolution of duality possible, and the experience of this dissolution justificatory as in Indian thought, or must that sort of justification be written off as unreasonable? For T, is the essence of T just "P is true if P," which of course offers no real linkage between reality and appearances unless one comes from J or B? Is T "in" the senses prior to the intellect, and "in" things?
Then for B, I read a very interesting book recently by Peter Harrison, "Some New World," which is a genealogical account of modern naturalism. Part of his thesis is that "belief" itself was radically redefined due to the theological conflagrations of the early modern period. This is where B starts to get concretized as a certain linguistic formulation, which brings all the problems that go along with the way meaning is contextual, bound up in language, etc. Sometimes, you'll see the claim that Plato is the origin point of JTB, and that the Gettier problem is very old in Western and Indian thought. But I don't think this is wholly accurate, because the understanding of the terms shifts so much, the new context becomes important.
The history of "justification" as a theological term turned philosophical is itself telling here. To be "justified" was originally an internal process, a change in that which is justified. It meant "to be made righteous." With Luther, it is displaced to external divine judgement, an imputation. Then it ends up becoming a philosophical external imputation that devolves down to either the community or the individual. A "justification," of claims to be in contact with reality (in possession of knowledge) on the basis of appearances needs some metaphysics of how appearances relate to reality. If this linkage doesn't exist, I am not sure how J ever falls into place or how T would ever show up in our experience. But if J is about the private and communal imputation of status in the first place, and not about a relationship between the knower and known, how could it ever bridge the gap?
Quoting Ludwig V
Sorry if I wasn't clear. I just meant that if P is true, then P cannot also be false. That's all. The reason I thought this was relevant gets back to this point @J was making:
Quoting Ludwig V
The problem, as I see it, is that global fallibilism seems to make any sort of meta-knowledge impossible. There is no way to decisively justify that one has knowledge, as opposed to a justified but false belief. But is it problematic for a theory of knowledge if it is impossible to know if one ever has it? I would think so.
As he put it:
Quoting J
But of course, we could reply here that you "know it to be true" just in case you have a justified belief that it is true, and it is true. I don't think that answers J's question though, because we still have to assume the "it is true" part. The problem is the one mentioned above, the relationship between truth and appearances, and a justification that is presumably based on appearances (or else a direct relationship to truth). If appearances are arbitrarily related to truth, or there is no clear relationship, that gap is unbridgeable from the outset.
What is the point of saying knowledge must be "justified" if justification doesn't secure truth, or worse, might only be accidentally related to it?
Yes. Or if not assume, at least spell out some criteria that don't merely repeat the J criteria.
Quoting Banno
Surely not. This is the absurd "deduction" I was addressing above. Satisfying the JTB criteria is not what makes a sentence true. It's not the "very fact" we're looking for. What makes a sentence true will be, let's say, some version of Tarski-truth.
Or to put it another way, what makes a sentence true is satisfying T; you don't need to bring in J and B at all. The question is, Can we imagine a situation in which T would be apparent to me -- not to a hypothetical anyone, but to me, the user of the JTB criteria -- on other grounds than the J?
Quoting Banno
Perhaps the right question, then, is "Who knows it to be true?" Does the person applying the JTB criteria have to know this? Or is it sufficient for it merely to be the case, with no one knowing it? This leads back to my concern about the use of all this.
@Banno kindly already replied. But to make it maybe less tricky an issue, I’ll change the example to knowledge of a future event that is not mostly contingent on one’s intentions or plans.
Suppose one watches a regular TV series that always starts at 6pm. Does one merely believe that the series will air later on during the day at 6pm or does one know this? In commonsense speech, if one says “I believe it will air at 6pm” in reply to a question, and this without any sarcasm, one then communicates that, although one assents to the reality that it will, one nevertheless does not have reason (this, here, being sufficient justification) to be psychologically certain that it will. And why not?
On the other hand, when told that the series starts at 6pm and replying to this “dude, I know” or something to the like, one conveys that one is psychologically certain (notice that I’m not here claiming being epistemically certainty) that it will, and this because one can justify that it will via any number of means without there being any credible alternatives to the contrary. This doesn’t then imply that its impossible for this upheld knowledge to be mistaken and, thereby, to in fact not be knowledge. Maybe there will be a city-wide outage at 5:55pm that prevents the show from being aired, maybe this and maybe that, but, nevertheless, one will have no reason to find any such alternative (whose possibility could be theoretically justified) credible and thereby plausible. So one then knows the show will air later on in the day at 6pm. And when it does, one's knowledge is confirmed by factual events.
Quoting Ludwig V
True. I’m guessing it should come as no surprise that the living of life is risky, even when we’re not consciously aware of it, and irrespective of how risk-adverse one might be. Every choice we make has its potential opportunities and potential costs and, hence, its risks. This is where I take personal responsibility steps into play (and maybe why making reasoned decisions we can justify given the contexts of what we are aware of during the moment of choice if often best … but hey, spontaneity sometimes is also good). With this personal responsibility then including our choosing what we deem to be knowns and what we don’t. We take our risks in life and reap the consequences, but are the risks justified? At least that's how I look at it.
Due, what's the "T"? If a sentence satisfies JTB, then it is true. Further, from "B", those who say that it satisfies the JTB account agree that it is true.
I'm genuinely at a loss to make sense of what you are saying.
Good post. :up:
This is what I was pointing up earlier with the pool analogy. If J and T are conceived of along the lines of that analogy, then the "task" that @J has set before him is impossible by definition. None of it is as mysterious as it is being made out to be. If one's anthropology precludes the mind from knowing things, then truth will be inaccessible and any theory with a T—including JTB—will fail. For example, if T is not traditional-T but rather pragmatic-T or communal-T, then of course JTB is undermined.
Possibly I also haven't been clear about why the PoV matters -- who is doing all this. The phrase "point to" is meant to raise this question. If I am the one who declares a sentence to be a JTB, then presumably I have satisfied myself, as best I can, about the T part, and provided my own justifications. But if you tell me it's a JTB, I haven't. All I can do is accept the "deduction" that, if it is indeed a JTB, then it must be true. I think you've been assuming, in this discussion, that a single person is taking all these steps, but there's nothing in JTB that requires that. We don't ask, "Have I verified that this sentence is true?" but rather "Is this sentence true?"; we don't ask "Have I provided good justifications?" but rather "Are there good justifications?"
Is this what JTB is for?
And thanks for your patience with this.
Yes, the keyword here is interaction - more specfiically John's ongoing interactions with his environment that maintains a correlation between his conditioning and external truth-makers. The critical importance of ongoing interaction is both overlooked, and many would argue incompatible with, the traditional epistemological notion of apriori, intentional belief states that we are supposed to believe can make semantic and epistemological contact with truth-makers before interaction. For it isn't feasible that a propositional attitude with respect to a future-contigent proposition, can access the truthmaker of the proposition in advance of the actual interactive use of the proposition.
As Wittgenstein might have put it, both the meaning and truth of a future-contigent proposition are up in the air, because the referential semantics of a future-contigent proposition cannot decided before the truth of the proposition is evaluated, which critically undermines the traditional epistemological concept of intentional belief states that are naively presumed to consist of a teleological mental state holding in mind a possible outcome of the future before it happens.
Hence emphasising interaction rather than beliefs can resolve the dilemma of semantic-externalism or trivialism in the same way thay Bayesian Statistics does - pragmatically through making it clear that beliefs are not intentional mental states, but conventions used for interpreting and controlling behavioural conditioning, in a sense that rejects the traditionally internalist and static epistemological notion of belief states.
My account of JTB+U is not the same as traditional JTB, it's more refined using Wittgenstein's methods from his later thinking. I'll partly sum it up in the following:
Extending JTB Through Wittgensteinian Methods
The classical model of knowledge—justified true belief (JTB)—says that a person knows p when three conditions are met: the belief is true, the subject believes it, and it is justified. That triad has stood since Plato, but its weak point has always been justification: what exactly counts as good reasons, and how are they grounded?
My proposal is to extend JTB with a Wittgensteinian emphasis. I call this JTB+U, where the “+U” stands for understanding. Genuine knowledge requires not only justification in some abstract sense but also competence with the relevant concepts. That competence shows itself in the correct public use of words, within the language-games and forms of life that give them their meaning. In other words, to “understand” is to be able to navigate the practices that make justification possible in the first place.
This move does two things at once:
Re-locates justification: It is not a freestanding relation between belief and evidence, but an activity carried out within specific language-games. What counts as “good reasons” is inseparable from the public standards and forms of life that sustain them.
Builds in uptake: To count as knowledge, a claim must not only be justified but also be grasped conceptually by the knower. A person may parrot a valid argument form, but without knowing the terms in use—say, “HbA1c” in a medical report—they cannot be said to know.
Traditional epistemology often treats justification as context-free, but justification lives and breathes inside particular practices. Courts, laboratories, and ordinary conversations each operate with their own standards, which are intelligible only against their background forms of life. Language-games set the grammar for justification, and hinge propositions—the arational certainties that stand fast—mark its limits.
I part ways with Wittgenstein on one important point: he treated language as bounded by insurmountable limits. I disagree. Language-games and forms of life are more open-textured than he allowed, and they evolve in ways that allow language to surpass those boundaries. Our epistemology should therefore preserve Wittgenstein’s insight into the contextual life of justification without accepting his strict metaphysical ceilings.
The upshot is a framework that is at once traditional and supple. JTB remains the core, but it is further strengthened by grounding it in the Wittgensteinian recognition that meaning, justification, and understanding are functions of practice. Knowledge claims are tested along multiple routes—testimony, logic, sensory experience, linguistic training, and pure logic—but always within the river-bed of language-games that give these routes their force.
Look, don't think:
Wittgenstein’s reminder “look, don’t think” is not an anti-intellectual gesture, but a methodological one: when philosophy drifts into abstraction, we should return to the actual use of words, to the practices in which meaning and justification live. It is a call to examine the grammar of our language-games before theorizing about their essence.
In terms of JTB+U, the maxim sharpens both justification and understanding:
For justification (J):
Traditional JTB risks treating justification as a timeless relation between belief and evidence. “Look, don’t think” tells us to attend instead to the public criteria in use: how testimony is corroborated, how sensory anchors are cross-checked, how logical inference operates in practice. Rather than imagining some metaphysical essence of justification, we look to the rules and error-signals that actually govern our language-games.
For understanding (+U):
Understanding is shown not in private conviction but in our capacity to use concepts correctly. To know is not merely to assent to a true and justified proposition, but to handle the relevant terms in the way our form of life requires. Here Wittgenstein’s maxim is the corrective: don’t speculate inwardly about what a concept really is; look outward at how the concept functions in actual practice. If someone says they “know what DNA is” but cannot use the term competently in the language-game of biology, they fail the +U condition.
In this way, “look, don’t think” guards JTB+U against two perennial errors:
Essentialism (believing knowledge must rest on some hidden inner property);
Private conviction masquerading as knowledge (thinking “I feel sure” is equivalent to being justified).
Instead, the maxim keeps our eyes on use, on the lived background where justification gets its grip and understanding is displayed.
So, in short: “Look, don’t think” is the Wittgensteinian brake on abstract theorizing that keeps JTB+U tethered to practice. It ensures that both justification and understanding are grounded in observable criteria within language-games.
A good example of how different people work with "know." I would in fact say just that, perhaps precisifying it: "I strongly believe that I will eat tomorrow, though there is a very slight chance that I won't." Would I also claim knowledge? This is where it really starts to get murky. According to JTB, I can't, since I don't (yet) know if "I will eat something tomorrow" is true. It may be true, in which case my claim at T1 is knowledge -- the problem is, I can only be aware of that in retrospect. In practice, however, and leaving aside the somewhat bizarre (to me) requirements of JTB, I'd rate the statement pretty low on the knowledge scale. Any number of things might prevent me from eating tomorrow, sickness especially. Whereas "The sun will rise tomorrow" gets an enthusiastic thumbs-up from me as a piece of knowledge, despite the fact that it too is not certain -- there are defeaters, as I proposed to @Janus (who wasn't impressed!).
Once again, though, we have to remember that a philosophical question such as "What is knowledge?" or "What counts as knowledge?" can be taken in at least two different ways. We can be asking, "What is the correct way to understand what knowledge is?" If we answer that, then we can go on to ameliorate the incorrect understandings and usages. The other way is to ask, "How is the word 'knowledge' used? What range of situations and applications does it cover?" If we answer this, we're no longer trying to say which (one) of the usages is correct. In fact, if it turns out that many people use "knowledge" in a manner, or in situations, that don't fit a proposed correct understanding of what knowledge is, this may, and should, give us pause. It may suggest to us that a "one size fits all" construal of knowledge is misguided. This doesn't mean that Total Chaos is now rampaging. It just means that the question is nuanced, and often depends on interpretation.
Why not?
As I and others have pointed out in previous posts, ontological truths occur, i.e, ontological correspondence/conformity to that which is, was, or will be actual do occur. Implicit in every belief is an assent to that which is true. So when one's belief of what is true is one and the same with what is ontologically true, one's belief is true. Justification then comes into play in the following manner: if my justifications for X being true are contradictory, then they are invalid. If they are not contradictory in any way, then, irrespective of how strong or weak, there will be no reason whatsoever for me to presume my belief to not be true. This then implies that one knows in a JTB sense that one will eat something tomorrow.
I so far presume implicit in all of this an emotive desire to obtain a state wherein all possible risks of being wrong are 100% avoided. And this state of an absolute guarantee of being in no way wrong about what is ontologically true is technically termed infallibility. I don't believe that an individual ego's omniscience is possible - a different issue to this thread which I won't pursue to justify. But I do find that the only way infallibility of anything could hypothetically be obtained is if the individual ego in question happened to be omniscient - thereby having perfect awareness of all past, present, and future events in all aspects of the cosmos. And no human is.
Quoting J
Fully agree. For one example, the proposition "I know that I know X" can at least be interpreted to specify two utterly different types of knowledge at play: knowledge-by-acquaintance of having JTB knowedge regarding X.
To extend the picture, I need to clarify what the “+U” adds, how justification itself must be situated in language-games, how the five routes interlock, and how this framework addresses familiar rivals. Each step reinforces the claim that knowledge is not only a matter of true belief with reasons, but of uptake within the forms of life that make reasons intelligible.
1. The role of +U
The “understanding” condition guards against the illusion that one can count as knowing simply by repeating words linked to justification. A student may recite that “HbA1c above 6.5 signals diabetes,” but unless they understand what HbA1c measures and why that threshold matters, their belief does not rise to knowledge. The difference lies in the correct public use of concepts. Understanding is shown in practice, not in private conviction. This is why Wittgenstein reminds us to “look, don’t think”: look to the use of terms in their home setting, not to an imagined essence behind them.
2. Justification in language-games
What counts as justification is not determined once and for all, but by the grammar of the practice in which the claim is made. In law, justification rests on admissible evidence and procedural safeguards; in science, on reproducibility, statistical thresholds, and peer scrutiny; in everyday life, on testimony that lacks defeaters. Each form of life sets its own standards. To ask for justification without reference to a language-game is to float free of the river-bed. JTB+U insists that we situate reasons where they belong, not in abstraction but in practice.
3. The five routes working together
My method recognizes five primary routes of justification: testimony, logic, sensory experience, linguistic training, and pure logic. Each has its own integrity, but they rarely operate in isolation. Testimony is checked by sensory anchors; logic binds testimony and perception into argument; linguistic training disciplines our terms, keeping them clear of confusion; pure logic secures consistency at the boundaries. When these routes converge, belief gains strength. When they diverge, we look for defeaters. This interlocking structure keeps justification tied to the lived world.
4. Answering rivals
Seen in this light, the JTB+U framework offers replies to classic objections. Gettier’s puzzles lose force because a belief that is true by accident but not conceptually taken up within the relevant practice fails the +U condition. Relativism is resisted because language-games are not arbitrary; they are bound by hinges—what stands fast in our shared form of life. Dogmatism is resisted as well, because defeater screening and practice-safety remind us that no claim is beyond correction.
The result is not a rejection of JTB but a strengthening of it. By insisting on public uptake, contextual justification, and interlocking routes, JTB+U places knowledge back where it belongs: within the activities and forms of life that give our words and reasons their grip.
Here’s a related issue:
Ought we take all affirmations of “I/you/they/etc. did, are, or will do X”, “X happened, is happening, will happen”, “X was, is, or will be Y”, and so forth to implicitly affirm mere beliefs regarding facts or statements of JTB knowledge regarding facts?
Certainly, depending on statement and its conceivable justifications, to differing degrees any such statement could be theoretically wrong. If one assumes that JTB must be absolutely devoid of any possibility of being wrong, then we all communicate all the time via beliefs which we don’t know to be true.
How would this not then result in a societal chaos of sorts wherein most all trust goes down the drain?
That said, when you tell me, “this person went there,” I always take this to be a statement regarding your knowledge of events. This unless you preface the statement with, “I believe that,” or else “I think that,” which would both, each in their own subtly different ways, convey that you cannot gather sufficient justification for the affirmation to maintain psychological certainty in its truth and, thereby, uphold it as knowledge.
Can this knowledge be mistaken? Of course. But at least here you implicitly convey that, to your own best appraisal, you can justify its ontological truth to me were I to so inquire (maybe needless to add, this without any contradictions).
Even with justification clarified and understanding secured, the model of JTB+U does not by itself remove the regress problem. Reasons can always be asked for in turn, and if the structure were required to justify itself endlessly, no claim could ever rise to knowledge. At some point, justification reaches a stopping place—not because of a failure in reasoning, but because practices rest on certainties that are not themselves up for doubt or proof. This is where Wittgenstein’s remarks on hinges enter.
Hinge certainties function as the river-bed of thought: “I have two hands,” “the earth has existed for a long time,” or more primitively, the unreflective assurance that the ground will hold us when we walk. Such claims do not stand as ordinary propositions requiring evidence; they are the background that makes doubt and evidence possible in the first place. To doubt them globally would be to lose our footing in the very language-games that give meaning to knowledge claims.
In my own work I have drawn a parallel between these hinges and Gödel’s incompleteness theorems,
just as Gödel showed that no consistent formal system strong enough for arithmetic can prove all the truths it contains or even establish its own consistency from within, Wittgenstein shows that epistemic systems rest on unprovable certainties. Both reveal a structural limit on internal justification. Far from undermining knowledge, these limits are enabling conditions: mathematics requires axioms it cannot justify, and our epistemic practices require hinges that stand fast without proof.
Placing JTB+U against this background allows us to see its proper scope. Justification, truth, belief, and understanding all operate within practices bounded by hinges. Knowledge becomes possible not because every step can be proven, but because certain things are exempt from doubt—bedrock elements of our form of life. To see this is to shift from asking for an impossible universal ground to recognizing the lived certainties that make reasoning, language, and knowledge possible at all.
Mastery of a technique: Wittgenstein often compared understanding to mastering a skill or technique. To know how to play chess is not merely to recite the rules but to make the right moves in practice. Likewise, to know a mathematical proof is not just to memorize it but to apply it under variation, extend it, and recognize mistakes. Knowledge claims, on this view, require more than stating the right words: they require competent use within a practice. This aligns perfectly with the +U in JTB+U—understanding shown in skillful use of concepts.
What he strips away is the illusion of a context-independent essence. The temptation of classical epistemology is to imagine justification as a single property that attaches to beliefs in the same way across all cases. Wittgenstein shows that what counts as justification shifts with the language-game. In a courtroom, “I know” calls for evidence that can be entered into the record; in daily conversation, it may be enough that I saw it with my own eyes; in science, the standards are replication and peer review. Each of these is still JTB, but the J is made concrete only in its practice. This is why he counsels “look, don’t think”: instead of theorizing what justification must be, examine how it functions in the life of language.
On this point, Wittgenstein’s contribution is not to propose another model of knowledge beside JTB, but to dissolve the demand for an ultimate account of justification outside our forms of life. The factivity of know remains untouched, as does its commitment to belief. What changes is our view of justification: no longer a timeless condition, it is an activity rooted in our shared background. When Wittgenstein says that “knowledge is in the end based on acknowledgment” (OC §378), he is not abandoning JTB but pointing to the human practices in which justification has its weight.
Thus the upshot is clear: there is no distinct epistemic use of “know” in Wittgenstein’s later philosophy that lies beyond JTB. What he uncovers is that every epistemic use is JTB-like, yet always practice-bound. The hinge or convictional uses fall outside epistemology altogether, but the genuinely epistemic ones do not float free of the traditional model. They fall comfortably within JTB once we recognize that justification lives inside language-games, and your +U condition makes that insight explicit. To know is still to believe what is true with justification, but it is also to understand the grammar of the concepts in play, and that is what JTB+U secures.
I was thinking rather the opposite. The reason people fiddle with T is to make it so that we can possess "knowledge" and access "truth" while still maintaining a view of J (and B) that makes it impossible to possess knowledge and have access to truth in their traditional sense.
The problem I see is that this just seems like equivocation. The problems of global fallibilism appear to go away because "knowledge" and "truth" have been redefined, but they aren't actually being dealt with. Now we can say things like: "I know p, but of course p might be false."
Might this not risk instrumentalizing knowledge? But the purpose of at least some knowledge isn't to do anything, or demonstrate any competency.
Also, how might this apply to moral knowledge? If one discovers that the dominant norms of one's society are, in fact, evil, how does one end up demonstrating this understanding? Pretty much by definition, one's community will think you are in error (violating U). But it does seem possible to be right about what is just, or choiceworthy, when everyone around you is wrong, and deems you to be in error, and "misusing language." For example, when Saint Gregory of Nyssa first began making a concrete Christian justification for the total abolition of slavery, this was a pretty wild claim. When he said "slavery is unjust," arguably he could be accused of misusing the term "just" in his context. And yet we tend to think he was absolutely correct here, and that his society would later come to agree with him and largely abolish slavery because he was correct.
Quoting Sam26
What about shifting contexts? As a Marxist, I might be able to justify and demonstrate understanding of the labor theory of value to other Marxists. I might also believe the theory is true. However, we have pretty good reason to think the labor theory of value is false. Can I know something that is false?
More problematically, suppose I have become versed in both Protestant and Catholic/Orthodox language games. Can I both understand and know that the Eucharist is the real body and blood of Christ, and that it is not the real body and blood of Christ because I can justify both and demonstrate a competent understanding of both?
Obviously, we might object that I cannot actually believe both (barring some sort of power of self-hypnosis perhaps), so I fail the B criteria on at least one of these. However, it seems possible that I could act like I believe both. The B criteria here seems ineluctably private, and so not "observable."
The problem I see with grounding J in current practice is that many forms of J do not seem to secure, or even lead towards truth. Some seem to positively block access to truth. So, referring back to current practice and use doesn't secure T. This would mean that knowledge exists just in case current practice and use corresponds to what is true (I think it's fair to say that no one except for the relativist vis-á-vis truth thinks this is always the case). But then there still needs to be some linkage between justification, use, and practice (@J's issue if I understand it right). Just because current practice requires that I cut out a victim's heart to keep the sun from going out won't make my justified belief, through which I demonstrate mastery of the relevant language game, true; it must also be true that this practice actually keeps the sun from going out.
But then J and U must have something to do with truth, or else they seem irrelevant, and likewise if B and U can be arbitrarily related to T, they will only ever accidentally line up with it. Presumably, J links them. But sometimes J requires that we contravene established practices that demonstrate U as well. We might decide that we have to start speaking about DNA or justice differently, before we have convinced anyone else.
I think this relates to another question. Practices and language clearly evolve over time. What causes them to change the way they do? Presumably, this is how J might relate to T and U.
Quoting Sam26
I am not sure about this comparison, axioms are justified and questioned all the time. If you tried to present a system with arbitrary axioms, or ones that seemed prima facie false, no one is likely to take them seriously. The gold standard is that they seem self-evident (arguably, a sort of justification). There have been intense debates over axioms, which can take place because "justification" is not itself bound by any axiomatized system. Afterall, what are the axioms for English, German, or Latin? Axioms are assessed by intuition, consequence, coherence, explanatory success, or even aesthetics, etc. Reasons/justifications are given.
But the same is true vis-a-vis these examples of hinge propositions in philosophy. They are challenged and justified. That's the whole history of philosophy. And I wouldn't want to accuse Kant and Hegel of misusing language (torturing the reader perhaps), but maybe just of being wrong or unjustified in their conclusions (particularly Kant!).
Plus, even if we accept that we must accept some things as true to engage in justification, this does not seem to entail that they are true. So the linkage between belief and truth still remains an open question.
Quoting Sam26
This account is right in line with the shifting meaning of "justification." But it seems to me to leave open the same question.
Quoting Count Timothy von Icarus
On my account, moral knowledge is possible in the same way any knowledge is possible: it requires truth, belief, justification, and understanding, situated within the language-games and forms of life that give “justification” its meaning. The claim that “slavery is unjust” is not just convictional; it is epistemic when it can be shown to cohere with the deeper grammar of moral language—justice as fairness, dignity, and reciprocity—even if the society around you has not yet taken up that use.
Objectivity without Absolutism
Objectivity in morality means that claims can be tested by public reasons, not just private conviction. Even when one’s contemporaries reject those reasons, the reasons can endure defeater screening over time. Gregory’s claim survived challenges and proved practice-safe; rival justificatory schemes (naturalizing slavery, theological rationales for domination) eventually collapsed. The enduring stability of the abolitionist claim shows that it was not merely cultural preference but a true moral proposition grasped with understanding.
The Role of +U
This is where the “+U” condition is critical. Gregory did not simply parrot “slavery is unjust”; he understood the concept of justice in a way that exposed contradictions in existing norms. To demonstrate such understanding is to handle the concept rightly, even in the face of communal resistance. Moral knowledge is thus not a matter of majority assent but of correctly grasping and applying the concepts in a way that survives both internal scrutiny and the defeater tests of history.
Quoting Count Timothy von Icarus
1. Can I know something that is false?
No. Knowledge is factive. If a belief turns out false (like the labor theory of value as an account of price and markets), then however justified and understood it may have seemed at the time, it was not knowledge but a case of apparent knowledge. JTB+U preserves this: the T condition (truth) is non-negotiable. What you had was a justified, understood belief that later collapsed under defeaters. That does not mean JTB+U failed—it means knowledge claims are always defeasible.
2. Can I know contradictory things?
The Eucharist example is instructive. You might be able to understand both the Catholic/Orthodox and Protestant language-games, and you might be able to justify each within its practice. But you cannot believe both simultaneously in the epistemic sense. At most, you can role-play or act as though you believe both. Since JTB+U requires belief, one of these would fail the B condition. If you suspend belief and simply track the grammar of each tradition, that is competence, not knowledge. Knowledge needs commitment to one truth-claim, not simultaneous acceptance of contradictories.
3. Isn’t justification sometimes corrupt or truth-blocking?
Yes—and this is why in JTB+U justification is not free-floating but checked by practice-safety and defeater screening. A practice like Aztec human sacrifice may have had an internal logic, but the claim “cutting out hearts keeps the sun alive” cannot survive defeater screening. It conflicts with what we now know through other interlocking routes (astronomy, physics, biology). So J is not whatever counts as justification in the moment, but justification that can hold up under the pressure of cross-checks and error-signals. That’s the linkage between J, U, and T: justification is only adequate if it is safety-preserving and defeater-resistant relative to truth.
4. How do practices evolve?
Practices evolve because defeaters accumulate, because rival routes converge on better explanations, and because conceptual understanding exposes contradictions. This is why J and U are not sealed off from T: language-games are porous. A community can be wrong for a time, but over the long run, practices shift under the weight of correction. That is why Gregory’s abolitionist claim, once dismissed as misuse, later became the new grammar: it better aligned justification and understanding with what is true.
5. The big picture
So the framework looks like this:
Truth (T): non-negotiable; one cannot know falsehoods.
Belief (B): requires genuine commitment, not role-playing.
Justification (J): tied to practices but must be defeater-safe and truth-conducive.
Understanding (U): demonstrated by conceptual uptake, not parroting.
Together, JTB+U explains why false theories don’t count as knowledge, why contradictory beliefs can’t both be known, why corrupt practices don’t ground knowledge, and how evolving practices eventually bend toward truth.Quoting Count Timothy von Icarus
You’re right that the question remains—what secures justification if it shifts with use? My point is not that justification becomes arbitrary, but that its weight lies in the river-bed of practices that give it sense. That river-bed is not static, but neither is it untethered.
What Wittgenstein helps us see is that justification is always bound to what stands fast for us at a given time: the certainties we do not doubt, the error-signals we attend to, the ways we check one another’s claims. That is why he can say knowledge rests on acknowledgment. To acknowledge is not simply to nod assent; it is to recognize a claim as fitting the grammar of our form of life.
So yes, the question presses: what if those practices are distorted, or what if our forms of life themselves evolve? Here is where JTB+U offers a refinement. Justification is not only public uptake, but uptake tethered to understanding. One can parrot reasons that “fit” in the moment, but without grasping their grammar, one does not know. Understanding functions as the hinge between practice and truth: it is what allows us to detect when a justification, though accepted, is hollow, or when a claim, though rejected, is nonetheless aligned with the deeper use of our concepts.
The open question then is not whether justification needs grounding beyond practice, but how practices themselves can be judged as truth-conducive. My answer is that they are judged over time by defeater screening, by convergence across routes of justification, and by whether they prove practice-safe when tested against the world. Practices shift because error-signals accumulate. In that shifting, knowledge does not lose its footing; it shows that our grasp of justification is corrigible, but never free-floating.
(Weak Testimony, Fragile Evidence, and the Collapse of a Belief System). This book will probably take a while to finish, and it will be much longer (300-350 pages). I go after the core belief in Christianity, the resurrection, and demonstrate the weakness of the testimonial and historical evidence.
:up:
I think that's a good answer. A difficulty in epistemology that I think is often under addressed is that the idea that knowledge "progresses" (e.g., "scientific progress," "moral progress," etc.) needs to be justified itself. The original Enlightenment justification for this was theological, and so if it is adopted in a secular naturalist context it needs another sort of justification. However, historically, it does not seem that technological, scientific, moral, or philosophical progress is assured. They don't seem to have always occurred; periods of regression show up as well. The early secular narratives that put forth the idea that only "superstition" blocks the path to progress seem too simplistic to account for this (they seem like downright ideological propaganda a century on TBH).
However, there are still plenty of issues. What constitutes an "error" or "failure" is itself dependent on goals and understandings that are always shifting. Consider the contemporary traditionalist critique that crashing fertility rates are a sign that exclusive humanism is maladaptive. Well, if it really does go extinct because its population falls by more than half each generation, and the dominant paradigm a century from now is something more in line with the traditionalist ethos, shall it thus be true that secular exclusive humanism was discovered to be a sort of error? From the exclusive humanist perspective, this would not prove it was in error; its own extinction would not be evidence of the truth of religion, tradition, etc., only of those traditions' reproductive value (indeed, anti-natalists would probably argue that religion is reproductively successful precisely because it is false). But this shows that "success" might arguably correlate with falsehood not truth.
I think your response works best in terms of technological questions where "success" is fairly easy to define. Either a plane crashes or it doesn't. It becomes much more difficult in political, social, moral, philosophical, etc. questions. For example, arguably the main liability to Scholastic thought in the early modern period was not its apparent falsity (or its dogmatically asserted "dogmatism") but that it absolutely did not lend itself to pamphlets aimed at a common audience, the new dominant market for philosophy, and that its institutions became prime targets for political violence and expropriation.
So, there is the issue that past "successes" and "errors" are being defined in terms of current practice. There is a bit of a "history is written by the victors" problem. There is also the problem posed by Hoffmann's "Fitness Beats Truth Theorem" and similar arguments, where selection-based approaches to belief do not ensure that beliefs are true. Fitness does not seem to be equivalent with truth in how information (or beliefs/memes) replicate. But then if our justification for our own beliefs rests on a selection model, this ends up being self-refuting. If our selection theory is true, we ought not believe our own beliefs are true, because their fitness is only loosely related to their truth.
Nonetheless, I think selection can be an important factor in explaining progress, just not the only factor. The other issue here is that it would only suggest that knowledge will be produced in the long run, not that we have it now. But if we aren't likely to have true beliefs now, then we ought not believe in our own progress narratives (a similar sort of issue). Hence, I think a stronger linkage is needed.
Before I reply in any detail, let me be sure I understand you. Are you saying there are ontological truths about the future? That is, the future exists now in such a way that statements about it are, at this moment, either true or false? (I think this is what you mean by an ontological truth?)
Quoting javra
I'm not sure that societal chaos would follow, but I agree with your point about JTB. That's part of why I'm hesitant to accept it as a good description of knowledge.
Sometimes it helps to pull back from the intricate details and ask ourselves, What are we trying to say about knowledge and truth? JTB seems to be saying, "You can only know something if it's true." Or wait . . . maybe it's saying, "You can only know something if, right now, you are sure it's true." Which is it? There seems to be support on this thread for the former construal: All that matters is that Statement P is true, not whether I can know that to be the case.
I think that, for JTB to be worth using, it ought to take us closer to the second construal: My claiming that P is true ought to say something about what I actually do have some surety about. And this is not a binary judgment. Our justifications will vary in strength. How strong does a J have to be in order to cross the "sure" barrier? I don't know if that's answerable. It's a bit like the old "heap" problem. Is there some line we can name, below which I'm not quite sure, and above which I am? (Notice that I'm using "sure" instead of "certain" or "have knowledge," because I don't want the potential circle to confuse this question.)
Hence if you know something, then by that very fact you believe it.
If someone says we know such-and-such, it remains up to you to decide if they are correct - to decide if you believe them.
Still not seeing much here. I'll read the rest of the stuff from overnight.
I agree that narratives of inevitable progress, whether Enlightenment or later, tend to oversimplify. Knowledge does not advance in a straight line. There are periods of regression, distortion, and even collapse of practices. What JTB+U gives us is not a guarantee of progress but a way of making sense of how correction is possible when progress does occur.
The key is to separate two things: (1) the sociological fact of which beliefs or practices dominate, and (2) the epistemic status of claims. The fact that a tradition survives or reproduces more effectively does not by itself prove truth. Fitness can select for falsehood as easily as for truth. The “Fitness Beats Truth Theorem” makes this plain. But epistemic justification is not reducible to fitness. A belief counts as knowledge only if it is true, believed, justified, and understood. That standard is higher than survival-value alone, which is why extinction or dominance cannot by themselves settle the matter.
Still, practices evolve. And they evolve in part because defeaters accumulate: rival routes of justification expose contradictions, or experience undercuts established norms. Scholasticism did not vanish simply because it lacked pamphleteers; it lost its grip on the justificatory practices of the time. Competing frameworks proved more effective at handling error-signals and sustaining inquiry in new conditions. That does not mean the older framework was false because it disappeared, but that its justificatory practices could not carry forward.
So I would put it this way: JTB+U does not assure progress, but it explains what progress consists in when it happens. A belief that is true, justified within its language-game, and understood conceptually can survive the test of defeaters across time. Sometimes it will be suppressed, sometimes ignored, sometimes distorted. But when it resurfaces and proves practice-safe under renewed scrutiny, that is a mark of epistemic progress.
This also clarifies why “success” in the practical sense (planes flying, vaccines working) and “success” in the moral or philosophical sense look so different. In technology, error-signals are immediate and decisive. In moral and political life, error-signals can be deferred, resisted, or disguised. That makes progress slower and less assured, but not impossible. Over the long run, justification and understanding are forced to adjust as contradictions mount. The abolition of slavery or the recognition of human rights are not simply products of fitness; they are instances where justification and truth finally aligned, and practices evolved to acknowledge it.
In that sense, knowledge does not march inevitably forward. But when it advances, it is not because victors wrote the history, but because some beliefs endured defeater screening while others failed. That is the “stronger linkage”: progress is not guaranteed, but possible because truth exerts pressure over time through the interlocking routes of justification.
Yes.
Quoting J
No.
Future actualities that are not yet actual int he present will happen. If one's belief of what will be a future actuality conforms/correlates to what will in fact be a future actuality, then one's current belief in the present is true by definition of truth. Hence, the "sun will rise again tomorrow" is either true or false, this being contingent on whether or not it will.
Quoting J
Why not both at the same time? The first by entailment. The second only due to the valid, and hence non-contradictory, justifications one could provide for its ontological truth granting one the sureness that it is true. As far as I can tell, both are necessary for any JTB form of knowledge.
I'll be convinced of that when you can point to a non-physical activity. I say all activities involve energy, and I count energy as being physical.
Quoting Ludwig V
I'm not treating mere possibilities as though they are actual at all. I've already said I have no truck with radical skepticism that is based on the mere logical possibility that I might be deceived. All I'm saying is that I will not claim to know something is the case if I see any possibility of its not being the case. Depending on how I gauge the likelihood of the possibility that it not be the case, I might nonetheless believe it to be the case—that is provisionally accept that is the case.
For example I will say I know I am typing at this computer, or that I see the towel on the line outside my window being moved by the breeze, because I see no possibility of reasonable doubt about those.
Quoting Ludwig V
I'm not saying it is "said anywhere", but that the idea of knowing something yet not knowing that you know it makes no sense to me, except in cases where I may not recall that I knew something. Even there, can I be said to know something I previously knew if I can no longer recall knowing it? Knowing that you know something consists in being able to explain how you know it, in my view.
Quoting Ludwig V
How do we ever know when the justifications are sufficient to warrant thinking something is true? That is the problem that leads me to think that if it is a matter of justification, then we are talking about belief, not knowledge. If I am certain I don't require justification.
Quoting J
It is logically possible that the laws of nature might change and the Sun burns itself out in seconds rather than taking billions of years. But that is, if all our scientific understanding is correct, not physically possible. The alien race scenario may or may not be physically possible, but it seems so vanishingly unlikely that it would be perverse to take it as a reasonable doubt. So I would say that I do know the Sun will rise tomorrow because I cannot see any possibility of reasonable doubt that it will.
Quoting Leontiskos
I am not sure about that implication of what @J has been arguing, but I think truth is a necessary condition of knowledge, and I also think knowing the truth and knowing how you know it is also a necessary condition of knowledge. That said, I am not claiming that we cannot think we have knowledge and yet be wrong.
Quoting Leontiskos
I take the ToE to be a way of understanding, like all scientific theories. We can say it differently and say theories are ways of knowing, but that is a different sense of knowing than "knowing that", or propositional knowledge. I would not say that we know the ToE (as opposed to evolution as such) to be wholly true, it may have parts that will be superceded, for example. One example of this is that the "central dogma" (that acquired characteristics cannot be inherited) has turned out to be thought to be not strictly true with the development of epigenetics.
Quoting J
I responded to this example of yours for the first time in this very post, so I'm not sure what you mean when you say I was "not impressed'. As you will see if you read the above I agree with you that I think it is reasonable to say we know the Sun will rise tomorrow.
Right, I am saying the same thing.
Quoting Count Timothy von Icarus
Yes, and my point is that if one rejects the traditional sense of truth then JTB in its traditional sense naturally falls. Perhaps I should have not spoken about 'T' in the way that I did, since what I said could be read as claiming that someone who replaces traditional T with some other T will thereby reject JTB in the non-traditional sense. That's not quite what I was meaning to say, but I think it is also true.
I think that axioms are a misleading interpretation of Wittgenstein's hinges.
i) Axioms are typically used to represent truth-apt empirical hypotheses.
ii) Axioms are stated in advance of proving theorems.
iii) Axioms are detachable and optional parts of a reasoning system .
i suspect that neither i,ii,or iii are generally true of Wittgenstein's hinges. To think this way would be to construe Wittgenstein as being committed to traditional foundationalist epistemology built upon logical atomism, as naturally embodied by the intended interpretation of an axiomatic system, which most Wittgensteinians think to be a gross misconstrual of his later ideas.
Nevetheless, the later Wittgenstein's epistemological views still come across as immature and lacking in sophistication when compared to the detailed accounts of scientific knowledge and justification by Carnap and Quine. To me, Wittgenstein sometimes comes across as a descriptive Carnapian, in the sense that like Carnap, Wittgenstein seemed to think (as in OC) that it was useful to delineate the internal questions of truth and justification that make sense from within a particular linguistic framework, from the external questions concerning the choice of linguistic framework. But unlike Carnap, I don't think that Wittgenstein saw the internal-external distinction as having prescriptive epistemological value, for essentially the same reasons as Quine; namely due to rejecting the analytic-synthetic distinction.
If Wittgenstein had fully rejected the logical atomism of the Tractatus, and if he wasn't comitted to the picture theory of meaning and the accompanying idea of intentional propositional attitudes that the picture theory of meaning is wedded to, and if Wittgenstein wasn't committed to the analytic synthetic distinction, then presuambly Wittgenstein's later epistemological views were closer to Quine's confirmation holism, in which case hinges are merely entrenched but revisable assertions, even if they are fixed for all intents and purposes within specific cases of reasoning.
I think that is a fair reading. IIRC, Godel was something of a platonist, so his reading of axioms would also not be that they are unjustified.
:up:
Well, if you acknowledge that regression can occur, then it seems that defeaters can appear to pile up against a position, and yet this is itself a sort of illusion or product of pathological justification. So my question then is: "how do you know that what you think are defeaters and are progressive evolution really are?"
For instance, scholasticism didn't disappear. It still has a fairly robust presence in philosophical publications, perhaps more than a century ago. How are you sure that your identification of errors and defeaters is correct?
Or in the religion example, you seem to accept that no matter if it comes to be affirmed, it will be false. But if it comes to be affirmed, surely people will be able to argue, with justification, that defeaters and errors piled up within the secular naturalist/ exclusive humanist paradigm, and they will claim that this is precisely why it collapsed. Indeed, plenty of thinkers (and not just religious ones) do claim that errors and defeaters against naturalism have indeed piled up, and that it is on its way out. The fact that evolutionary narratives of knowledge seem to be self-refuting is precisely one of the issues here.
Because they aren't asserting the same thing, or at least we need an argument to show that they do. The first speaks of the truth of a statement ("something") irrespective of whether I know it to be true. The second brings me into the picture, insisting that I have to be sure it's true.
Otherwise, it's all circular. "I know X" becomes the same thing as "I know that X is true." But this presupposes that "knowing X" involves a definition of knowledge that include knowing that X is true. Isn't this what JTB was supposed to demonstrate?
Filling in with an example:
1 - "I know that I live in Maryland"
2 - "I know that 'I live in Maryland' is true"
What is our warrant for claiming that 1 and 2 assert the same thing? Doesn't it involve a stipulation or presupposition about what it means to know something -- specifically, a stipulation involving the term "true"? Statement 2 talks about what is true, statement 1 does not. But isn't this the very thing JTB is supposed to give us? -- a reason to include the truth of a statement as part of the knowledge claim?
But also, see my previous comments about the inquiry into "What is knowledge?" JTB wants to pin down the correct use of "I know"; I'm suggesting that it might be more profitable to look at the ways we actually use "I know." I don't think they correspond to JTB. There are many things I believe I know, but am not certain they are true. JTB would argue that, therefore, I'm using "know" incorrectly. Whereas I'm saying that it's JTB that needs correction, not me. This latter position lacks punch, of course, unless the "me" can be turned into "us" with sufficient frequency. We need a fairly widespread agreement on the faults of JTB in order to claim that it doesn't capture our common practice.
EDIT: I agree that it isn't possible to claim 1 without also claiming 2, and vice versa. Perhaps that's all you mean by "Why not both?" If so, it's fine. My argument above is that they are nonetheless different claims. And consider a 3rd statement: "'I live in Maryland' is true." This can be the case even if I don't know I live in Maryland.
My system fixes the regression problem. I said that "there are periods of regression," just as there are periods where one thinks that a particular conclusion is knowledge, but later it's found to have flaws/defeaters.
Your question "how do you know that what you think are defeaters and are progressive evolution really are?" is the right question to ask, because it highlights the difference between thinking one has a defeater and actually having one. JTB+U is built precisely to keep that distinction clear.
A defeater is not just whatever I take to undermine a claim. It has to stand up within the interlocking routes of justification and not collapse under cross-examination. Suppose I call something a defeater—say, new evidence, or a conceptual contradiction. The question is then whether that supposed defeater is itself truth-conducive, practice-safe, and able to endure scrutiny across language-games. If it turns out to be mistaken, then it was not a genuine defeater but an apparent one.
The same applies to what looks like “progressive evolution.” The fact that practices change does not mean they are evolving toward truth. What secures progress is not the mere shift but whether the change holds up under defeater screening, survives error-signals, and continues to cohere with the deeper grammar of our concepts. Many shifts are later revealed as regressions—false starts that fail the test of time. Others, like the recognition of human rights, survive repeated challenges and show themselves to be knowledge rather than temporary consensus.
So my answer is: I do not “know” in advance that this or that shift is progress. What I can do is apply the JTB+U framework as best as I can—testing for truth, justification, belief, and understanding, and watching to see whether putative defeaters actually endure. Progress is visible in retrospect when claims prove stable across scrutiny and when rival justifications collapse. That is what makes them knowledge rather than mere opinion.
Quoting Sam26
Isn't understanding the same thing as justification? I'm not sure what the U adds to JTB, given that we assess understanding in terms of justifications.
As for deciding whether a refutation is valid or not, this rests upon the truth of one's auxiliary hypotheses. So unless those can also be tested, one cannot know whether the refutation is valid, which is the staple criticism of Popper's falsificationism - that individual hypotheses are impossible to test, since their validity stands and falls with the truth of every other hypothesis. So the bridge from practical refutation in everyday life, which often involves the testing of individual hypotheses under the assumption of true auxilliary hypotheses, doesn't withstand skeptical scrutinty and the standards demanded by scientific epistemology - an essentially unattainable standard, relegating JTB to the realm of the impossible, or to the realm of semantics that is epistemically vacuous.
I’m trying to leave the forum for now. But, yes, claim 1 and claim 2 are semantically the same (with a possible semantic difference regarding emphasis). As to “why not both?” I gave an overview for why both will need to occur for JTB knowledge to obtain. Someone who is steadfastly certain in their belief that X (is true) without having any reason to believe it (this being synonymous with not having any justification for it) … ought to be trusted to in fact know what they’re talking about? If this were so, then, heck, planet Earth must be hollow and inhabited by sapient beings living in paradise. This then being a factual truth because others are so certain of it. I’ve encountered such. As to differing forms of knowledge, again, the knowledge-by-acquaintance and knowledge-by-JTB dichotomy I’ve previously mentioned showcases this. The first is had devoid of conscious belief; one doesn’t believe that one is seeing green grass but simply so does (and thereby knows one does, this in the knowledge by acquaintance sense of knowledge and not the JTB sense). But once belief is introduced, it must be both true and one must have (valid) reason for believing it so in order to count as knowledge. Some people want all knows to have the strength of knowledge-by-acquaintance. We can dream away all we like, but that is not the nature of the reality we’re living in. Else, again, the planet must then be hollow.
Quoting sime
Quoting sime
Consider this post a bookmark, as I have been wanting to respond to these posts but haven't had the time and am now occupied again.
I think there are false dilemmas occurring here, owing to a presupposition that can hopefully be explored later on, but which is close to the presupposition that "the situation isn't different with humans as measuring devices."
The key will be to see that one's truthmaker is not stipulated merely by oneself, and that the truthmaker is not merely a consensus reached by an external community. For the realist there is an object that exists in reality which one is trying to understand, and correctly understanding the object will not be a matter of aligning oneself with any particular linguistic community. In a more preliminary way we would want to ask why the dichotomy you present would be plausible. Why think that the two options you present are exhaustive?
Thanks, and coincidentally, I also have to be offline for 2 weeks, as I'm going out of the country. Appreciate the conversation and look forward to chatting with everyone when I get back.
Quoting Janus
@J's central move is to say that if someone thinks truth is a necessary condition of knowledge, then they must explain how truth can be known apart from all the other conditions of knowledge (such as justification or belief), and since no one can do that, therefore truth is not a necessary condition of knowledge. This is endlessly confused.
Quoting Janus
Okay.
I will just link to , particularly the second half. If someone thinks this:
Quoting Janus
...Then they are making justification into something other than justification. Justification is per se persuasive. Persuasiveness isn't something that gets tacked onto justification. A false justification is something that purports to be persuasive but is not. The question of how we know whether a justification is adequate has to do with logic, inference, validity, etc., and goes back to what about "the Aristotelian way to develop such an idea."
(Still, even once we understand how soundness pertains to justification, there remains a difference between the concept of soundness and the concept of truth. They do not collapse into each other even in those cases where they are biconditional.)
Edit: Part of the problem here is the semantic range of the word "justification." Properly speaking, what is needed for the internalism that is being presupposed is for one to have the explanation (aitia) for why something in reality is the way it is. One must be able to (correctly) explain why it is true. "Justification" can mean that, but it can also mean providing an ad hoc or unsound account, and the critiques of a justification condition are presupposing this latter meaning (of faux justification).
On the first point: understanding is not the same as justification. Justification is the giving of reasons that satisfy the standards of a language-game. Understanding is a matter of concept-mastery, the ability to use terms correctly within that grammar. A student can repeat reasons in a way that looks justified, but without grasping the concepts, they do not understand—and so they don’t know. The “+U” is needed because justification can sometimes be mimicked or borrowed without genuine uptake.
On the second point: you are right that Popper’s falsificationism raised the problem of auxiliary hypotheses, and that one cannot isolate hypotheses absolutely. But this does not mean that knowledge is impossible. It means that justification is corrigible and practice-bound. When we test a claim, we do so against a backdrop of hinges and auxiliary commitments. If anomalies arise, we do not simply abandon the claim, but we check whether the defeater is genuine. This is why defeater-screening is part of the JTB+U framework.
The skeptical worry that this makes JTB impossible arises from a mistaken demand: that justification must be final and immune to revision. Wittgenstein helps us dissolve that demand. Knowledge does not require absolute independence from auxiliary assumptions; it requires that our reasons hold up against available defeaters in the practices that give those reasons sense. Here the distinction is crucial: the JTB framework itself—truth, belief, justification (+U)—remains the definition of what knowledge is. But our application of that framework in practice is fallible. We can misidentify truths, we can mistake apparent reasons for genuine justification, and we can claim understanding where only parroting exists. The framework is sound; what fails is our use of it.
So the linkage is this: justification is public and corrigible, understanding is the uptake that prevents mere parroting, and truth remains the non-negotiable condition. Together, they let us say that knowledge is possible without pretending that justification must ever be perfect or final. Our judgments may fall short, but that is an error of application, not a defect in the framework itself.
Right, but if you cannot be sure that you have true beliefs now why should you trust your own beliefs about the long term trend of knowledge or epistemology more generally?
:up:
I am interested though, since you recommended a Bayesian approach, how you think they are able to deal with the problems of selection narratives. The structure of BT by itself does not seem to get around the problem that fitness vis-á-vis reproduction/survival does not seem to necessarily track with truth.
That question rests on a misunderstanding of what knowledge is. It assumes that unless I can be sure of my beliefs in the sense of absolute, indubitable certainty, then I have no rational grounds for trusting them. But knowledge has never required that kind of infallibility. On JTB+U, knowledge requires truth, belief, justification, and understanding. Those conditions are demanding, but they do not amount to immunity from error.
Part of the confusion here comes from how we use the word certainty. It can mean at least three different things. First, there is subjective certainty, the psychological feeling that I cannot be wrong. That is fallible, since I can feel certain and yet be mistaken. Second, there is objective certainty, the hinge-level background we do not doubt—like that the world has existed for a long time. These certainties are not proved but stand fast as the conditions of doubt and knowledge alike. Third, there is epistemic certainty, where a claim is true and justified to the point that doubt has no footing within a given practice. Even this form of certainty remains corrigible if new defeaters arise.
The challenge you raise trades on conflating these senses. It assumes that unless I can have absolute, infallible certainty, I cannot call my beliefs knowledge or trust them for long-term reflection. But this is simply not what knowing is. Knowledge, on the JTB+U account, is defeasible but real: I can hold a belief that is true, justified in my practice, and conceptually understood, even though I remain open to correction.
So why trust my beliefs now, including beliefs about epistemology? Because they have withstood defeater screening across the routes of justification available to me: testimony, reasoning, sensory experience, linguistic clarity, and logical consistency. If new defeaters arise, I will adjust. But until then, the best explanation for their stability is that they are tethered to truth.
The upshot is that skepticism here demands the wrong thing. It asks for absolute certainty, when what knowledge actually requires is justified, true, and understood belief within our forms of life. To see that distinction is to dissolve the challenge.
But you have already allowed that cultural-historical regressions might lead to a case where a culture widely accepts that a true idea/theory has been "defeated" when it hasn't been. How do you know that you're not in that situation?
The move of: "scholasticism lost ground because it was properly defeated, but if secular naturalism and exclusive humanism lose acceptance that will be simply a regression," seems arbitrary unless you can show why some beliefs are actually true and cannot be the result of regression/error. That is, an apparent defeater or error is not solid evidence that a theory/idea is actually wrong, since you have already allowed that whole cultures can misidentify defeaters and errors for long periods.
That is the way some pushback on this idea, but I think the apparent arbitrariness disappears once we distinguish between (a) the framework for knowledge and (b) our fallible application of it. There is always a difference between what I think counts as knowledge and what really is knowledge. Gettier cases make this clear: someone thinks they are justified, but the justification is defective, so they do not actually know. The same thing can happen at the cultural level—whole societies can misidentify defeaters or mistake regression for progress. That does not show that knowledge is impossible; it shows that our application of JTB+U can go wrong. The framework itself—truth, belief, justification, and understanding—remains intact. What fails is our judgment, our recognition of what counts as a genuine defeater.
So how do we avoid arbitrariness? By keeping the distinction clear between apparent defeaters and genuine defeaters. An apparent defeater is what a culture or individual takes to undermine a claim at a given moment. A genuine defeater is one that endures across error-signals, survives cross-checking through multiple justificatory routes, and holds up under defeater screening in the long run. Misfires don’t erase the difference between appearance and reality; they only show that human uptake often lags behind truth.
This is why I say Scholasticism lost ground for reasons that were not merely political or sociological. Its justificatory practices proved less able to handle new error-signals. If secular naturalism were later abandoned, the question would not be settled by its decline in popularity or survival-value but by whether the reasons against it genuinely exposed its falsity. To decide that requires the same thing JTB+U always requires: truth, belief, justification, and understanding tested against defeaters.
The risk of cultural error is real, but that does not make all judgments arbitrary. It means we must hold our claims with epistemic humility, open to correction, but not collapsing into relativism. Some beliefs are true and will survive defeater screening indefinitely (mathematical truths, some moral absolutes). Others are corrigible. What matters is whether our justificatory practices are strong enough to keep those differences visible.
We navigate the world, build functioning technology, diagnose illnesses, and correct one another’s errors. These are not flukes. They demonstrate that justification, when tethered to practice and subjected to defeater screening, is in fact truth-conducive. Understanding ensures that justification is not merely parroted but conceptually grasped. This combination makes it more likely than not that our beliefs line up with reality.
Of course, mistakes and regressions happen, both individually and culturally. But if error dominated, the very concepts of knowledge and justification would lose their grip. The fact that we can identify mistakes as mistakes already shows the framework is working. Our ability to mark regressions as regressions depends on having a more stable body of truths against which those failures stand out.
So, JTB+U is viable because it works in practice most of the time. Its fallibility is not a weakness but a strength: it builds in the possibility of correction without demanding infallibility. What matters is that the framework links belief, justification, and understanding to truth with enough reliability to sustain our practices of inquiry, correction, and progress.
Error is the thing that makes knowledge possible. This is counterintuitive.
Imagine you're inhabiting a character in a dream who is running from the mafia. You're hiding in a cabin in North Dakota, but a man enters your dwelling and you know he's there to kill you.
The concept of knowledge is in play here, and it mostly signifies confidence. It's just turbo-charged belief.
It wouldn't make sense to say it's an opinion, because the mafia threat isn't a matter of opinion. It wouldn't make sense to say the character knows it, but it's not true. So we could add on truth.
I did kill the guy in the dream. I didn't have any choice.
It makes sense to say the man thinks he knows, but he doesn’t. This is something we see all the time: people confuse what they believe with what they actually know. The key difference is that conviction alone isn’t knowledge, and sometimes the evidence that seems to support a belief doesn’t really justify it.
I don't think your conception of knowledge is going to stand up to a skeptical challenge. At any time, we may be mistaken about our justifications. So, to nail the jello to the wall, how do you determine if the evidence in front of you is sufficient for knowledge? I say you have no way to do that. You only use the word "knowledge" to signify confidence in your beliefs.
A side issue is that I knew the man was there to kill me because I created the dream specifically to confront certain fears. I knew he was there to kill me in the same way I know the bishop goes diagonally. Life is frequently like this, but realizing this requires grasping the extent to which we live in our own dreams.
If knowledge is just confidence in one's belief, then one's confidence/conviction that one knows would suffice, that can't be correct. Sure, we can be mistaken in what we think justifies our belief, but as I pointed out earlier that doesn't justify being skeptical about JTB. Your skepticism is unfounded, you seem to think that if we can't know in an absolute sense, then we can't have knowledge (at least in the sense that I'm proposing). We don't use the concept knowledge,generally, in the way you seem to think. Even in science our conclusions are mostly probable.
In the last three pages I explained this in detail.
I didn't say knowledge is confidence in one's belief. I said we use the word to express that we're confident. The reasons for that confidence vary.
Instead of trying to provide a definition for knowledge, think about how the word is used. The next time you catch yourself using the word, stop and reflect on what you're trying to convey.
If this is what you think I'm doing, then you haven't understood anything I've said. My impression @frank is that you haven't read my posts in the last few pages, because if you had, you would know how foolish your remark is.
You are right. It makes a lot of difference what the context is. My apologies if someone else has responded while I've been away.
Quoting J
JTB amounts to a procedure for working out whether some random belief is actually knowledge. It's not exactly a discovery procedure for knowledge, because the belief needs to be given - unless it is actually a hypothesis.
If the random belief is someone else's claim to knowledge (and perhaps, in a way, all one's beliefs are claims to knowledge, if they are beliefs without qualification). The JTB makes most sense if we suppose that someone (A) is evaluating someone else's (B) belief that P. Then, (1) the justification needs to be B's justification. (2) P needs to be true. (3) ex hypothesi the belief is B's belief.
What seems odd at first sight is that, if A goes through all of these steps and accepts them, A knows that p. But I don't think that is a bug. I think that it is a feature. It should not be surprising that members of a social group have ways of sharing information. If we didn't have such a system, we would almost certainly invent it.
I don't think it is circular, but it does presuppose that, to put it this way, A needs to be qualified to carry out such an evaluation, that is, needs to understand the relevant proposition in its linguistic and epistemic context, which means that A needs to be competent in the relevant skills. The same applies to B. I think this observation picks up the idea of understanding.
When the justification in question is conclusive, the T clause is otiose. When the T clause is false, the J clause is otiose.
It is unfortunate that the format here makes it difficult to emphasize that propositions cannot be considered individually, as if they were atoms. They are always part of a system..
Quoting J
I'm all for paying attention to how "know" is actually used. But it may not be easy to discern a single, consistent use, or uses may be different in different contexts. There are some common uses of "know" that, I think, philosophy needs to discount. If I place a bet on an outsider in a race, and exclaim "I knew it would win", it is a rhetorical use of little interest to philosophy. At most it expresses the subjective certainty of the speaker. I don't see that little tidying up for philosophical purposes would go amiss.
I do think that there is fairly widespread agreement that it is surprisingly hard to formulate a generally acceptable articulation of JTB. If someone could come up with a reasonably acceptable alternative - and perhaps the view that "know" is a primitive term is one such - I would expect it to attract support.
Quoting sime
OK. So what's your alternative?
Quoting Sam26
Adding another clause to JTB just to ruling out mimicking or parroting seems a bit over the top. What is much more important is to recognize the importance of the competence of the knower, as you do, of course.
Quoting Sam26
Well, I would agree that we presuppose that the framework is sound. But I don't think they are necessarily set in stone and they may need to be modified.
Quoting Count Timothy von Icarus
Perhaps not. But if truth was not at least compatible with reproduction and survival, we would surely abandon it or die out. Though some events in the world make me wonder whether that is the case and how committed most people are to truth. Perhaps truth is not as important as we philosophers like to think it is.
I think it's just an expression of one of the meanings of "knowledge."
To be persuaded is no guarantee of the soundness of what has done the persuading. I just don't see how the truths or falsities that constitute a purported justification for some belief can be irrelevant. You yourself say that a "false justification is something that purports to be persuasive but is not", which seems to agree with what I just said. Although the "purports to be persuasive" seems wrong, inapt since people are often persuaded by falsities. I would change the "persuasive" there to 'true'.
Quoting frank
Yep, there are at least a few others.
OK. Then can you tell me anything about the other meanings?
There's know that and there's know how. Sometimes it's know of. In some cases, it might be a combination?
I know how you feel.
You should know better than to eat wild mushrooms.
I didn't know which path I should take.
I want to know what it's like to jump from an airplane.
How do the migrating butterflies know the way to Mexico?
I love you more than you'll ever know.
Frank doesn't know his ass from a hole in the ground.
I don't think it's really necessary to build a formula for each usage. Do you?
If I say “I know how you feel because I too have lost a parent”, then the structure does fit JTB:
Truth: it is true that I have felt grief of that sort.
Belief: I believe that what I experienced is relevantly similar to what you are feeling.
Justification: I can give reasons (describing my past emotions, circumstances).
Understanding (U): I actually grasp what fear, grief, or joy feels like from the inside.
Here the claim is epistemic — a propositional one: “Your feeling is of type F, and I have also experienced type F.” That does fall within JTB+U, though it is grounded in testimonial and experiential justification rather than inference or measurement.
By contrast, when it’s used loosely (“I know how you feel” as mere reassurance), it slips into the convictional/expressive use Wittgenstein noted — no propositional claim is really being advanced.
So: this phrase actually shows how the same sentence can belong to different language-games depending on how it is meant. Sometimes it’s epistemic (anchored in truth, belief, justification, and understanding); other times it’s expressive (an act of sympathy).
“You should know better than to eat wild mushrooms.”
Here “know” means having the practical awareness or standing knowledge of a danger. It presupposes JTB in the background (“these mushrooms are poisonous”), but the utterance functions as rebuke, not as a truth-claim.
“I didn’t know which path I should take.”
Epistemic use: this is propositional knowledge — lack of knowledge about which option is correct. It fits the JTB structure directly (truth of which path is best, belief about it, justification for choosing).
“I want to know what it’s like to jump from an airplane.”
This is a case of experiential knowledge (“knowledge by acquaintance”). It’s outside JTB’s domain, which focuses on propositional knowledge.
“How do the migrating butterflies know the way to Mexico?”
Here “know” is metaphorical. Butterflies don’t form justified beliefs. It’s a shorthand for innate mechanisms or instinct. Not JTB.
“I love you more than you’ll ever know.”
Purely expressive. “Know” here means “imagine” or “comprehend.” It’s not epistemic at all.
“Frank doesn’t know his ass from a hole in the ground.”
Colloquial. It means “Frank lacks competence.” It’s not propositional knowledge but a judgment of practical incompetence.
Knowing that ? propositional knowledge, the domain of JTB (and your JTB+U). It’s about truth-evaluable claims: knowing that the train leaves at noon, that water boils at 100°C, that a promise was broken.
Knowing how ? practical or skill knowledge. It’s about abilities or competences: knowing how to ride a bike, how to play the violin, how to fix a sink. This is not easily reducible to propositional form. Gilbert Ryle made this point sharply in The Concept of Mind: “knowing how” is not just a set of facts one has memorized but an ability to act appropriately.
That said, the boundary isn’t always rigid:
When someone says “I know how to ride a bike,” what they’re really claiming is competence in a practice — which is different from holding a justified true belief.
But “knowing how” often presupposes some propositional knowledge (e.g., knowing that you must balance, pedal, and steer).
Conversely, “knowing that” is often reinforced by “knowing how” (a surgeon who knows that a procedure requires precision must also know how to carry it out).
In my framework:
JTB+U is designed to cover knowing that — propositional knowledge.
Knowing how is better understood as a different language-game of “know”: one rooted in practice and skill rather than truth-apt propositions.
The two overlap in that “knowing how” can feed into propositional knowledge (e.g., an expert mechanic has knowledge-that cars behave in certain ways, because he knows-how to fix them).
JTB is fits into many different language-games, and the definition is based on Wittgenstein's family resemblance idea.
In agreement with much of your post.
To come at this from my own perspectives, in the examples frank provided I only see three differing types, or species, of consciously held knowledge addressed:
-- Knowing-that, which seems to always be knowledge-via-JTB.
-- Knowing-how, which I find is one subset of the more generalized category of knowledge-via-understanding (which I take can slightly bifurcate so as to apply both to conscious apprehensions as well as to consciously engaged in behaviors). Examples of this species of knowledge include: knowing (consciously understanding) the meaning of (e.g., of a word); knowing (behaviorally understanding) how to catch a ball; knowing (consciously understanding) another’s motive(s) and thereby knowing the other in this regard (i.e., holding a conscious understanding of who or what the other is); and the more philosophically renowned “know (consciously understand) oneself (as in: consciously understand what oneself as being is)”. This is what to me the butterfly question, for one example, would most likely addresses: how does a butterfly (granting it is in some way sentient even though not sapient) behaviorally understand how to navigate their way toward Mexico. Yes, many a conscious understanding can of course be justified, but an understanding is not quite a belief, being instead that upon which all beliefs are founded.
And, as your JTB+U maybe indirectly specifies, knowledge by understanding can be an utterly different beast in comparison to knowledge by JTB. For one example, one may not know (consciously understand) how to justify that which one knows via understanding (e.g., one’s knowledge via understanding of what is/being is) much less know (understand) how to convey it via words to oneself or to others. Even so, one’s known via understanding nevertheless so remains a known via understanding (e.g. no competent adult can claim with a straight face not to know/understand what is/being is, certain US presidents aside, even though we’re all at a loss for how to define it). Same with any skill one knows how to put to use so as to accomplish some end (and thereby behaviorally understands how to put to use so as to accomplish some end). Knowing (behaviorally understanding) how to ride a bicycle as an example of this. And, maybe needless to add, many an understanding can be non-conscious: e.g., someone with amnesia that discovers they yet know / behaviorally understands how to play piano, although they did not know (hold knowledge-by-acquaintance) that they so knew / behaviorally understood. Same could then be theoretically said of an amnesiac not knowing by acquaintance that they know by understanding what a complex scientific theory signifies (e.g., the theory of relativity or the theory of evolution) until coaxed into providing answers to certain theory-related problems. And “A doesn’t know his ass from a hole in the ground” is basically stating that A lacks satisfactory discernment (which is just saying that A lacks knowledge-by-understanding regarding differences which are otherwise commonly understood). Aldous Huxley’s Knowledge and Understanding gives some great insights into the uniqueness of understanding. For example,
Quoting https://www.anthologialitt.com/post/aldous-huxley
-- All other provided examples to me consist of knowledge-by-acquaintance, of which knowing-of is a subset. An example of this type of knowledge I haven’t yet mentioned in the thread is that when one as a consciousness (aka, as a conscious being) is X, one as a consciousness knows this via a non-dualistic form of knowledge-by-acquaintance regarding oneself as consciousness: e.g., when one is angry, tired, sad, joyous, pleased, confident, in pain, etc., one knows one is so via direct and non-dual acquaintance with one’s one state of conscious being (such that there is no distinction between the subject of awareness (oneself) and its object of awareness (one’s momentary state of being)). Here, “to know” and “to be aware of” can be fully interchangeable expressions of the same. Hence, for example, knowing (being aware of) what it feels like to X. Or, “I love you more than you’ll ever know (i.e., more than you’ll ever be aware of)”.
At any rate, I again so far can only discern three types of knowledge in the examples provided: 1) knowledge by JTB, 2) knowledge by understanding, and 3) knowledge by acquaintance.
And I agree that the three can easily become, at least at times, indiscernibly entwined. This can, again, for example jive with your proposal of JTB+U (to which could also be technically added “+ knowledge by acquaintance”, for nothing can be otherwise known in the compete absence of any awareness, and all instances of awareness grant some form of knowledge by acquaintance, such as in what beliefs one upholds).
But my main reason for coming back to the forum to post this post is as follows:
I’m very curious to see if anyone can discern any other species of knowledge via the way “to know” is used within language that would not fit into any of the three categories just mentioned. (I haven’t yet found any.)
We knew long before we invented epistemology. Epistemology is only the fevered dream of a mind that cannot trust its own eyes, its own blood, its own joy.
Epistemology is a conceptual retrojection. Epistemology is the dualistic philosopher’s revenge on life: he invents rules for knowing after the fact, then declares life itself illegitimate without them.
Of course, there's "know that .." and "know how ..". I'm not sure about "know of..". Perhaps knowledge by acquaintance as well?
Whether you want a formula or not for each of your examples probably depends on how much store you put on them. I wouldn't necessarily want to set up a different kind of knowledge for each of your examples. Knowledge applies in a wide variety of language games and we can expect its definition to be adjusted to suit each context. Still "I know how you feel" is clearly different from "I want to know what it's like to jump from an airplane" and "I love you more than you'll ever know". All of them are different from "I know when it is high tide".
Quoting DifferentiatingEgg
Yes. I can see that you are sceptical about the point of philosophy and it is indeed doubtful. However, rationalizing what life already does is what philosophy does best, it is does anything at all. Compare Augustine on time.
Quoting javra
The fact that they do it is powerful evidence that they do know what they're doing. Perhaps one day we'll understand how they know the route . But it's not impossible that we might come to the conclusion that the butterfly doesn't "really" understand or know what it is doing or why. It's a very limited bit of know-how - not the same as understanding how to navigate the world. Compare migrating wildfowl which are rather less limited and more flexible.
Quoting https://www.anthologialitt.com/post/aldous-huxley
It depends what you mean by "shared". We can both understand how to drive a car, even though I cannot understand on your behalf, nor you on mine. It's a bit like eating in that respect.
Quoting javra
I don't see any reason to suppose that list is complete. But much depends how you distinguish a species of knowledge from knowledge of different kinds of subject-matter.
Quoting Sam26
You are right about that. Partly, the flexibility is the result of the flexibility of justification which is "played" in different ways in different language-games - just as winning is differently defined in different games. But I think it is most at home in the context of "know that.."
You are fixing on "persuasive" too much, and also ignoring the difference between soundness and truth that I have pointed out to you on many occasions.
Your objection is something like, "But justifications don't always objectively justify;" or, "But justifications are not always sound." And again, this involves an equivocation between two different kinds of justification (material vs. formal or subjective vs. objective). The claim, "But justifications are not always true," just muddies up the difference between justification and truth. Justification has to do with soundness or validity, and truth is different from justification. Particular truths cannot be known apart from mental acts and justification/explanation, but the concept of truth remains different from the concept of justification.
One could perhaps dispute the idea that justification and truth should ever be separated, even conceptually, but that is a very unorthodox idea which would involve one in an extreme form of internalism. Given the nature and limits of human memory it simply isn't plausible.
OK, I can see how some out there want to pigeonhole everything into their own devised conceptual containers (i.e., schemas). For one among many examples: everything is physical (this being the devised conceptual container) so therefore all thoughts, intentions, passions, etc., too must be and thereby are purely physical. Yet there are also those whose main intent is to seek understanding via their studies and inquiries, such that first there is X and then there is understanding of what X is. Here, then, epistemology is simply the striving of greater understanding regarding an X that already is, an X taking the form of the epistemic, and this via its study. To better understand the ready-existent regulations by which something operates is not the same as pigeonholing everything into rules of one’s own creation.
Yes, this presupposes a great value to understanding. But that’s maybe a different topic.
Quoting Ludwig V
To better illustrate A. Huxley’s views via a more extreme example: a mystic’s understanding of reality at large (which can be presumed gained via some form of, say, ecstatic experience or some such) cannot be shared in the complete absence of JTB knowledge regarding this understanding, via which the understanding could then be convincingly communicated to others. Notwithstanding, the given understanding nevertheless occurs, as then does the respective knowns-via-understanding regarding reality at large. As to possible examples of this, both Jesus Christ and the Buddha could be deemed to have been in possession of some such understanding which they did their best to impart, to not here get into William Blake and many another. More mundanely, though, most understandings among adult humans in a society are commonly held by all individuals (e.g., the understanding of which side of the road to drive on). But consider how kids learn language: they must come to their own understanding regarding what words in their proper contexts signify. One cannot impart this understanding to children directly (in contrast to how a JTB can be directly imparted among adults), but can only lead the way toward it via affirmations and negations regarding what is correct. This until the understanding clicks.
Quoting Ludwig V
Right. Never say never. Which is why I’m asking a broad community for examples that exemplify knows which are neither JTB, nor understanding, nor awareness (and the acquaintance it entails).
As to distinguishing species of knowledge from knowledge of different kinds of subject-matter:
Awareness of does not require either understanding or belief. So knowledge by acquaintance is distinct from the other two as a species of knowledge.
Understanding does not require belief of what is understood, and, though it does require awareness, it is additional to pure knowledge by acquaintance. So knowledge by understanding is also a distinct species of knowledge.
JTB, on the other hand, will require a) belief (that is both true and endlessly justifiable in valid manners in principle), b) some measure of understanding, and c) awareness. So it too is distinct from the other two.
That briefly addressed, each of the three types of knowledge can apply to vastly different kinds of subject-matter.
Yep.
If one lesson can be taken from Wittgenstein’s later philosophy, it is that the search for an essence often misleads us. “Knowledge,” like many of our central concepts, is not held together by a single core feature but by a web of similarities — what he called a family resemblance. We call different things “knowledge” because they overlap and crisscross, not because they share one identical trait. The advantage of approaching knowledge this way is that it steers us away from the temptation to define it too narrowly while still letting us see the grammar that governs its use. JTB+U takes up this insight: it identifies the recurring traits in our practice — truth, belief, justification, and understanding — and shows how they give shape to the family of cases we call knowledge.
This perspective dissolves a common confusion. Philosophers sometimes assume that to count as knowledge, every instance must satisfy one rigid formula. Wittgenstein would say instead: look at how we actually use the word. When we do, patterns emerge. In one case, we credit knowledge because a person’s claim is true and well-reasoned. In another, we retract it because their belief was false or based on a guess. In another, we hesitate because, though the person can repeat reasons, they plainly do not understand what they are saying. These are not disconnected episodes but overlapping uses of the word “know,” bound together by a family resemblance. JTB+U does not impose a new essence; it describes the grammar that already structures these practices.
To clarify, however, not every use of the word “know” belongs to the epistemic family. Our language-games carry many strands, and “know” is put to work in expressive, metaphorical, and practical ways that are distinct from epistemology proper. A few examples make this plain. “I know how you feel” may simply be an expression of sympathy — an assurance of solidarity rather than a truth-apt claim. “You should know better than to eat wild mushrooms” functions as rebuke, not as a report of propositional knowledge. “I love you more than you’ll ever know” is purely expressive, a way of magnifying devotion. “Frank doesn’t know his ass from a hole in the ground” is colloquial insult, equating knowledge with competence. In such cases, “know” is doing different work. It belongs to our forms of life, but not to the epistemic strand where JTB+U applies.
Yet some of these cases can shift depending on context. If I say “I know how you feel because I too have lost a parent,” the grammar changes. The claim is now anchored in truth (I really did undergo such an experience), belief (I am committed to that claim), justification (I can describe the circumstances of my grief), and understanding (I grasp what grief is like from the inside). Here “I know how you feel” becomes epistemic — a claim of shared experience that falls under JTB+U. The lesson is that grammar, not surface form, determines whether a use is epistemic. By attending to the language-game in which “know” appears, we can distinguish genuine claims to knowledge from expressive or rhetorical gestures.
This also helps us see the role of justification more clearly. Justification is not an abstract property that floats free of context. It is an activity situated in our language-games and tied to our forms of life. To be justified is to be able to give reasons that others can recognize as having weight within the practices we share. A person who believes for no reason, or on the basis of wishful thinking, cannot be said to know, even if they happen to be right. By contrast, a person who gives reasons that others in their form of life accept as strong, and who understands those reasons, does count as knowing — provided the belief is true.
The five justificatory routes identified in JTB+U illustrate this point. Testimony, logic (both inductive and deductive), sensory experience, linguistic training, and pure logic (boundary-setting only) are not reducible to one essence. They resemble one another the way games resemble one another: overlapping in methods and aims without being identical. What unites them is their role in linking belief to truth through public practices that can be tested, cross-checked, and corrected. A belief justified by testimony can be reinforced by sensory experience; one tested by logic can be clarified by linguistic training. Their strength comes from their interrelation, not from any single trait that all share. They form a family of justificatory methods — the most prominent hinges on which our claims to knowledge turn.
The image of hinges helps here. Our justificatory practices do not spin freely but move around fixed points that stand fast for us. In ordinary life, we do not doubt the existence of the external world or the reliability of memory at every turn; these are bedrock certainties that frame the game of justification. Within that frame, the five routes function as hinges of practice: they orient us in the search for truth, and when one route falters, another can expose the failure. Their capacity to cross-correct is what prevents justification from collapsing into mere convention. They are not exhaustive, but they are the dominant ways in which our forms of life give weight to reasons.
Seen from this angle, JTB+U is not an abstract model imposed from above but a refinement drawn from our actual use of “know.” It names the recurring features of the family resemblance that holds our knowledge-claims together, distinguishes the epistemic use of “know” from other strands in our language, and clarifies the routes by which justification has force. By making understanding explicit, it strengthens the link between belief and truth, ensuring that what counts as justification is not just appearance but uptake. In this way, JTB+U brings Wittgenstein’s therapeutic insight into constructive form: it dissolves confusions about “know” by looking at use, and it offers a framework that captures the grammar of knowledge as it is lived in our forms of life.
:up: :up:
I recently did a thread in Frege's puzzle, but I'd be happy to revisit it if anyone's interested.
The search for definitions is often a matter of codifying what we actually do. It is a very hard thing to do perfectly, partly because the rigidity that goes along with that can end up in conflict with the more flexible and dynamic practices of actual use.
Quoting javra
There are various understandings of the world and some of the things in it that can't be communicated through propositional true/false knowledge. But there are other ways of communicating - poetry, pictures, music, dance.
Quoting javra
Surely that example is easy to communicate in common-place ways. What is harder to communicate by means of articulate rules is different. Curiously, how to use words is one of them. But how to be respectful or friendly are not like that, either.
Quoting javra
Yes, but you know when the understanding clicks because you know when the child is using the words correctly.
Quoting javra
Doesn't this show that all three are interwoven as different aspects of knowledge?
Quoting Sam26
I was very pleased to see you include testimony. Because it enables us to pass on what we know It is critical to our practice of knowledge. We all stand on the shoulders of others and our society would be greatly impoverished if testimony were not an effective way of communicating it. However, accommodating it in the standard JTB framework is tricky. It requires acceptance of fallible justifications.
Quoting Sam26
Yes, I agree with that.
Quoting frank
I thought that knowledge just is an attitude to a proposition. In what other form could it enter into philosophical consideration? I think it is useful to see "know" and "believe" in the context of "think", "suppose", "imagine", "deny", "assert" and Frege's puzzle is indeed a puzzle.
Well, there's some truth to that. But I think that it misses the point and over-extends a useful idea. It would be a bit misleading, wouldn't it, to parse "I wish I had a red flower for a buttonhole" as expressing a positive attitude to the proposition "I have a red flower for my buttonhole"; the object of my positive attitude is the red flower, once it appears in my buttonhole.
Much of our knowledge comes through testimony (books, lectures, person-to-person, etc). Testimony is often undervalued and misunderstood. Every area of study, including science, must rely on testimony. What's lacking is the knowledge of how (it's a skill) to evaluate and appreciate its value.
Almost all justification is fallible, not just testimony. Why? Because most knowledge relies on probabilistic reasoning, including science.
Yes, that's quite right. I think, though, that philosophers have always been more interested in how new knowledge is acquired, so tend to focus on that. What they don't pay enough attention to, in my opinion, is how important the spread of knowledge is and how dependent new knowledge is on knowledged that has already been acquired.
Quoting Sam26
That's complicated. Some probabilistic reasoning is absolutely certain. The odds of a coin toss are exactly and without doubt 1/2. Empirical probabilities less so, although in practice they seem to work quite well. I don't know how reliable Bayesian probabilities are, but, given the difficulty of verifying them (in one-off cases), I set even less store by them. But note that probabilities have no meaning unless and until there are outcomes - at which point the probability becomes 1 or 0.
Fallible justifications are a bit different. In many cases, no proper estimate can be made because the outcomes cannot be listed and weighed. In others, the fallibility is only a possibility and disappears when the outcome is known.
Then there are the Wittgensteinian hinge propositions and other indubitable propositions. How far they stretch I am not clear. But it does seem likely that much of our everyday knowledge is more probabilistic than we like to recognize. (People treat the time their train leaves as a certainty, but they know full well that trains are often disrupted by one thing or another.) They ignore that because they can do nothing about it and it doesn't happen too often.
That claim is self-contradictory under the way I’m defining these terms. Absolute certainty means knowledge held with 100% confidence, without the possibility of error. This is the domain of sound deductive reasoning, where a valid argument with true premises guarantees its conclusion—what we call a proof in the strict deductive sense. The word absolutely here signifies “without restriction” or “without qualification.”
By contrast, probabilistic reasoning always carries qualification: no matter how small the probability of error, there remains some chance that the conclusion is false. Thus, probabilistic conclusions can approach certainty in degree, but they can never be absolutely certain in kind.
Every epistemology carries within it a metaphysics, just as every metaphysics presupposes an epistemology. Philosophy often speaks of metaphysics as if it were an eternal architecture of reality, but “disorders” such as dementia or schizophrenia reveal that both epistemology and metaphysics rest on fragile, human scaffolding. When the mind deteriorates, the capacity to know and the categories of what is known collapse together: soap and marinara no longer belong to distinct orders, voices leak from thought into the world, self and other lose their boundary. What this shows is that metaphysics is not an independent order of being, nor epistemology a neutral method of knowing, but two faces of the same fragile ordering principle — a set of boundaries the mind must uphold to make sense of experience. When those boundaries dissolve, what we call “absurd” is simply lived reality; what we call “truth” is revealed as a maintenance project of cognition itself.
Yet epistemology and metaphysics both are really about the world as the mind can sustain. Consequently not about the world as is.
What your view really demonstrates is not the futility of epistemology, but its necessity. The fact that cognition can fail does not mean that truth is nothing more than a maintenance project; it means that human beings sometimes lose their grip on truth. To confuse the breakdown of knowledge with the nature of knowledge itself is like confusing a malfunctioning compass with the nonexistence of north. Far from undermining epistemology, your example underscores why we need it: to distinguish between distorted perception and genuine understanding, between the fragile scaffolding of a disordered mind and the enduring structures of reality.
Yes, I understand that position. I won't pick it apart here.
I wanted to point out that mathematical probability is mathematically certain. It has uncertain elements, but even there, the degree of uncertainty is certain. We can consider coin-tossing as an abstract structure and see the implications of the rules, without any appeal to empirical probabilities. So the statement "There is a 50% probability that the coin will land heads" and "The coin will land either heads or tails" are mathematically certain.
All that changes when we consider empirical probabilities. Here, nothing is certain and the language changes to reflect that. However, there are some elements that need to be regarded as certain. In an actual game of coin-tossing, we do need to be certain of the result of each toss; if there are any uncertain outcomes (the coin lands and stays on its side, or turns into a bubble), they need to be discounted, or included as a third possible outcome. (Where we are basing our estimates of life expectancy on past data, that, too, needs to be certain.) Probabilistic reasoning needs some things to be (or be regarded as) certain, though never mathematically certain.
Bayesian probability is different again, since it assigns a probability to a single outcome. I'm not at all clear what meaning can be attached to that. But it does seem to me that the outcome of the experiment must be (treated as) certain, or there is no result and the prediction fails.
You’re right that to say “truth is a maintenance project of cognition” is itself an epistemic claim. But that doesn’t undermine my point... it reinforces it. The fact that I can’t step outside the framework of justification to make my claim is precisely what I mean when I call truth a “maintenance project.” To describe truth is always to participate in it, never to stand above it.
When I point to dementia or schizophrenia, I’m not saying they reveal “the essence of knowledge” from some Archimedean standpoint. I’m saying their breakdowns highlight the contingency of the boundaries we ordinarily take for granted. You call this “confusing the breakdown of knowledge with the nature of knowledge.” I’d say: the breakdown discloses the nature. Knowledge is not a mirror of eternal structures; it’s the fragile activity of maintaining categories against the ever-present possibility of their collapse. We can never stand outside the scaffolding of the framework and measure it. We can only ever uphold it from within, patching and justifying where need be.
In that sense, I’m not dismissing epistemology but radicalizing it: epistemology is not the neutral arbiter between “distorted” and “genuine,” but itself part of the scaffolding, an instrument of maintenance that only works for as long as the categories hold. Our claims about knowledge are bound up in the same fragile maintenance they describe.
There are four uses of certainty that we need to be aware of, and they are the following:
1. Subjective certainty
This is the psychological sense: conviction, the felt impossibility of doubt. I may be subjectively certain that a friend will keep a promise, or that my team will win. But conviction alone is not knowledge, because one can be subjectively certain and still wrong.
2. Hinge certainty
These are the background beliefs that stand fast and frame our practices of doubt and justification. “The world has existed for a long time,” “I have two hands,” “Memory is generally reliable.” They are not justified in the ordinary way, nor are they really doubted in practice. They are arational bedrock, conditions of doubt and inquiry.
3. Epistemic certainty
This is when a belief is not only true and believed, but also justified and undefeated within the relevant practice. It is defeater-resistant knowledge. Epistemic certainty is what JTB+U aims to secure: not infallibility, but a belief whose justificatory structure is strong enough to withstand error-signals in its domain.
4. Absolute certainty
Here belong the logical and moral necessities: “2+2=4,” “A thing cannot both be and not be in the same respect,” or “murder is always wrong.” These are not contingent truths but necessary ones, either analytic or rooted in moral grammar. Doubt here would not be corrigible error but conceptual breakdown.
So:
Subjective certainty = conviction.
Hinge certainty = arational bedrock.
Epistemic certainty = knowledge in the JTB+U sense.
Absolute certainty = logical or moral necessity.
All right. That's very clear.
Quoting Sam26
So where does probabilistic reasoning fit? An example of a conclusion that can approach certainty in degree, but never be absolutely certain in kind. Bear in mind, that probability is, by definition, defined by an outcome, of which the probability, by definition, is 1 or perhaps 0. (I'm not saying the outcome always has to happen, just that each probability defines an outcome.)
Probabilistic reasoning does not yield absolute certainty (sense 4: logical/moral necessity). It is not the kind of certainty we find in “2+2=4” or “murder is always immoral,” where denial collapses into contradiction. Instead, probability operates in the register of epistemic certainty (sense 3: defeater-resistant knowledge in practice). A high probability, backed by justification and understanding, can approach a state where we rightly treat the belief as knowledge, even though it remains in principle corrigible.
This distinction is crucial. To say “I am certain at the 99.9% confidence level that the medicine will work” is not to claim an absolute necessity. It is to claim a belief that has survived defeater screening, cross-checked by testimony, reasoning, and sensory evidence, and that functions with the kind of stability that makes action rational. In other words: probabilistic reasoning belongs in the realm of practical epistemic certainty, not absolute certainty.
Your remark about outcomes is well taken: once an outcome occurs, its probability collapses to 1 (happened) or 0 (didn’t happen). But notice that before the fact, what matters for knowledge is not the metaphysical status of the outcome but the justification of belief leading up to it. The grammar of “know” ties us to what is justifiable before the outcome is fixed. This is why probabilistic reasoning fits comfortably within JTB+U: truth (the event does or does not occur), belief (the agent commits to its likelihood), justification (the probabilistic model and evidence), and understanding (grasp of how probabilities function).
So the answer is: probabilistic reasoning cannot reach absolute certainty, but it can yield epistemic certainty robust enough for knowledge in practice. That’s why we entrust planes to aeronautical engineering or treatments to clinical trials. We are not misusing “know” when we say, “We know this drug works,” even though the claim is probabilistic. We are speaking in the epistemic register, not the absolute one.
Probability and the Varieties of Certainty
One common source of confusion in epistemology is the place of probability. Some treat probabilistic reasoning as a weaker substitute for knowledge, as though it can never rise above opinion. Others mistakenly assume that probability can deliver the same kind of necessity we find in logic or mathematics. Both views rest on a failure to distinguish the varieties of certainty.
Recall the four senses:
Subjective certainty — conviction, the felt assurance of belief.
Hinge certainty — the arational bedrock that makes doubt and inquiry possible.
Epistemic certainty — defeater-resistant knowledge in practice, stable enough to guide action.
Absolute certainty — logical or moral necessity, where denial collapses into contradiction.
Probabilistic reasoning clearly does not yield absolute certainty. No degree of evidence can turn an inductive conclusion into a logical necessity. To say “this drug has a 95% chance of success” is not to assert that its success is absolutely necessary. The grammar of probability already places it outside the category of absolute truths like “2+2=4.”
But this does not mean probability is epistemically weak. Probabilistic reasoning is one of the chief ways in which we arrive at epistemic certainty. When a belief is supported by convergent evidence — statistical studies, repeated trials, predictive accuracy — it can withstand defeaters and function with the kind of reliability that makes action rational. We rightly say we know airplanes will stay aloft, even though our confidence is grounded in probability, not logical necessity. The strength of the claim lies not in its absoluteness but in its resilience across error-signals and justificatory routes.
It is also important to note the role of outcomes. Once an event occurs, its probability collapses to 1 or 0. The coin either lands heads or it does not. But knowledge-claims are not made after the fact; they are made in the stream of life, before outcomes are settled. What matters epistemologically is not the metaphysical status of the event but the justification for belief leading up to it. Probability is the language we use to track that justification, and when paired with understanding, it satisfies the conditions of JTB+U.
In this light, probability is not a lesser form of knowing but one of the principal ways human beings secure knowledge. We live in a world where outcomes are not always transparent, but where patterns and regularities can be detected and acted upon. Probabilistic reasoning translates those patterns into degrees of epistemic certainty. It belongs not to the realm of absolute necessity but to the realm of practice — the very place where JTB+U is meant to operate.
Quoting DifferentiatingEgg
I’m with you all the way here. I would just add that truth is not a unitary concept but changes its sense according to the context of its use. Human beings are in the business of construing recognizable patterns in the swirl of experience and then drawing from our memory of those patterns to anticipate new events. This is a richer and more fundamental process than what is contained within the thin and derivative notions of propositional truth and justification. We don’t primarily make truth-epistemic claims, we project expectations and wait to see if the way events unfold do it in a way that is more or less inferentially consistent with our anticipations. Events will never duplicate those expectations, so even when our hunches are verified, we must adjust these patterns to accommodate the novel features of the events we recognize. This is not epistemology, it is context and situation-based sense-making.
Where I’d want to add a note of caution is that the factivity of truth still matters across those contexts. However we construe it, “p” being true always implies that things are as “p” says they are. Otherwise we lose the very grammar that distinguishes knowledge from conviction.
On the question of pattern recognition: I see this as closely related to what Wittgenstein called hinges, or what I sometimes call hinge-beliefs. These are certainties that do not themselves stand in need of justification but make justification possible. For example, we do not reason our way to believing that objects persist when out of sight, or that other human beings have inner lives, these are taken for granted in our dealings. They are beliefs in the broader sense, which includes both propositional claims (“The earth existed before my birth”) and non-propositional, prelinguistic certainties (the infant’s trust in the caregiver, or the body’s implicit grasp that the ground will hold). Pattern recognition provides much of the raw material for these hinges: it is how we find stability in experience, and those stable expectations are what make reasoning and justification possible.
And here is where my JTB+U framework comes in. Propositional truth on its own is “thin,” as you put it. What matters is how it is embedded in justification and uptake, how belief is connected to truth in ways that others can test, and how the agent understands what the claim involves. So I wouldn’t discard propositional truth, but enrich it. It becomes one thread in the weave of truth, belief, justification, and understanding, all grounded in the certainties that stand fast in our forms of life.
If we’re sticking with the later Wittgenstein we want to be careful here ( otherwise feel free to ignore this :grin: ).
The grammar of truth isn’t defined across instances connected by family resemblances. It is defined by the particular instantiations within the larger family. We dont consult an already given conceptual grammar (“p” being true always implies that things are as “p” says they are) and then apply it to a family of instances. There is always something particular we are doing with ‘“p” being true always implies that things are as “p” says they are’, and this grammar doesnt just give us unique criteria but a unique sense of meaning of the phrase ‘ “p” being true always implies that things are as “p” says they are’.
Your wording suggests “truth” is a concept with multiple “faces” or modes of operation. For Wittgenstein, this risks hypostatizing truth as a thing. He would prefer to dissolve that urge: “truth” isn’t an object with different guises, but simply a word whose uses vary across practices. And every particular use, even within a single “practice,” can shift the sense. If meaning is use, then it’s not just different practices (“law,” “science,” “math”) that set the sense of “truth,” but also the fine-grained contexts within those practices.
That said, I would still hold that in the epistemic use of “true,” there is a minimal grammatical constraint that runs through its particular instantiations. However much the criteria differ — testimony in law, predictive success in science, proof in mathematics — the word “true” here always functions in contrast to “false,” and that contrast implies that the proposition fits the way things stand. This is not to hypostatize truth as an object with “faces,” but to recognize the mirroring role that the grammar of epistemic truth presupposes.
So I wouldn’t want to treat “truth” as having an essence across all uses. I agree that outside epistemology — in poetic, moral, or expressive speech — the sense of “truth” shifts without necessarily carrying factivity. But within epistemology, its factive core seems indispensable. Without it, we lose the very grammar that lets us correct, doubt, or justify claims. So my position is: meaning is use, but among the uses of “truth” there is a distinctive epistemic family where factivity is non-negotiable, even though its criteria are locally defined.
The first benefit lies in distinguishing different senses of certainty. Human beings navigate between convictional certainty (“I know she loves me”), epistemic certainty (“I know the bridge will hold”), and absolute certainty (“2+2=4”). An AI system that fails to recognize these differences risks either inflating its probabilistic outputs into necessity or downplaying genuine knowledge as “only probable.” Incorporating the grammar of certainty into AI reasoning could allow systems to represent not just confidence levels but also kinds of certainty — treating mathematical truths differently from empirical predictions, and both differently from convictional expressions.
The second benefit is the awareness of hinges. Wittgenstein insisted that justification does not go on forever. At some point there are certainties that “stand fast”: that the external world exists, that memory is generally reliable, that other people have inner lives. These are not optional premises; they are conditions of sense. An AI designed without hinge-awareness will endlessly seek justification where none is required, or worse, collapse into regress. A hinge-sensitive AI could be programmed to recognize its own bedrock assumptions and to operate within them while remaining open to correction at higher levels. This would make its reasoning both more efficient and more human-like.
The third benefit arises from the “+U” in JTB+U — understanding. Current AI systems can store truths, assign probabilities, and even generate justifications of a sort, but they often lack uptake. They can state that Paris is the capital of France, but they do not consistently grasp what follows from that claim, when to apply it, or how to detect when an error-signal demands revision. Embedding “understanding” as a criterion would shift AI development away from mere statistical prediction toward competence in language-games: the ability to apply concepts correctly across cases, to give and ask for reasons in context, and to adapt when defeaters arise.
Finally, JTB+U emphasizes contextual justification. Testimony functions differently in science than in law; sensory evidence is weighed differently in everyday life than in a laboratory. An AI that can track these language-game differences will be able to tailor its justificatory standards to the domain in which it operates, rather than treating knowledge as homogeneous. This would prevent both under- and over-reach: no longer dismissing courtroom testimony as “unscientific,” while not confusing legal plausibility with empirical law.
In short, JTB+U offers a conceptual framework that could reshape AI epistemology. It would push systems beyond probability scores toward a layered understanding of certainty; beyond blind data-processing toward hinge-awareness; beyond rote recall toward genuine uptake; beyond one-size-fits-all reasoning toward practice-specific justification. If humans are to design AI that integrates into our forms of life, the grammar of “knowledge” must be respected. Far from being a mere philosophical abstraction, epistemology in this Wittgensteinian key could guide the next generation of intelligent systems.
A Wittgensteinian JTB+U Framework for Responsible Intelligence
Introduction: Fear Without Framework
One of the greatest public anxieties about artificial intelligence is not simply that it makes mistakes, but that it makes them with the wrong kind of confidence. AI systems already generate falsehoods while sounding certain, apply reasoning across domains without context, and produce outputs we cannot always distinguish from knowledge. People worry that such systems may spin out of control — not only because they are powerful, but because we lack a shared standard for when their outputs count as genuine knowledge.
What if part of the solution lies not only in engineering but in epistemology? Philosophy has wrestled for millennia with the conditions of knowledge. The classical model of Justified True Belief (JTB) remains the backbone: one knows something if it is true, believed, and justified. Yet this model alone is too thin for the complexities of modern reasoning. In my work I extend JTB with a fourth element — Understanding (U) — and frame it through Wittgenstein’s later philosophy. The result, JTB+U, offers a grammar of knowledge that could help discipline AI reasoning and reassure human users.
The Core: JTB+U
The JTB model works well because it matches our practices: we do not call someone knowledgeable if they voice a lucky guess, nor if they cling to a false belief. We demand truth, belief, and justification together. My addition of +U (Understanding) makes explicit what was always implicit: that knowledge also requires uptake. A system must not only produce a true justified belief but must also grasp the concept well enough to apply it competently across contexts.
In human life, understanding is what allows us to use knowledge in reasoning, explanation, and correction. Without it, justification can be hollow or accidental. For AI, adding +U means more than citing sources or probabilities — it means showing conceptual grasp: when to apply a claim, what follows from it, and when it fails.
Certainty: Degrees and Kinds
AI systems often present outputs as if they were absolute, when in fact they are probabilistic. Here Wittgenstein’s analysis of certainty helps. We can distinguish at least four senses:
Subjective certainty — conviction or felt assurance.
Hinge certainty — arational bedrock that makes doubt possible (e.g., the world exists).
Epistemic certainty — defeater-resistant knowledge in practice, stable enough to guide action.
Absolute certainty — logical or moral necessity, where denial collapses into contradiction.
Probabilistic reasoning belongs to epistemic certainty: not infallible, but robust against correction and sufficient for rational action. By contrast, mathematics and logic express absolute certainty in kind, not in degree. An AI system grounded in this grammar would know how to communicate not only confidence scores but what kind of certainty is at stake. That would go far in preventing false impressions of infallibility.
Hinges: Bedrock for AI Reasoning
Another danger is regress: how do we know that an AI’s reasoning is not flawed at some hidden level? Wittgenstein’s answer was that justification does not go on forever. At some point there are certainties that “stand fast”: basic beliefs not themselves justified but making justification possible.
Humans take for granted that the world existed before our birth, that memory is generally reliable, that other people have minds. An AI system, too, must operate with hinge assumptions: that its arithmetic is consistent, that its data streams are genuine, that communication has meaning. If AI could make such hinges explicit, humans would better understand what the system presupposes, and where corrections could intervene. Transparency at the hinge level could dissolve much of the “black box” fear.
Language-Games: Contextual Justification
Wittgenstein also reminded us that justification is not timeless but practice-indexed. What counts as evidence in a courtroom differs from what counts in a laboratory. Human beings navigate these shifts in grammar fluidly; AI systems do not.
Here the JTB+U framework highlights five primary routes of justification:
1) Testimony
2) Logic (inductive and deductive reasoning)
3) Sensory experience
4) Linguistic training
5) Pure logic (boundary-setting only)
Each route is weighted differently across practices. In law, testimony and records dominate; in science, prediction and replication; in daily life, sensory access and trust. An AI system that tracks these contextual differences could avoid misfires — no longer treating courtroom testimony as “unscientific,” nor confusing legal plausibility with empirical law. Context-sensitive justification is not optional; it is essential for responsible reasoning.
Understanding as Uptake
Perhaps the most radical demand of JTB+U is that knowledge requires understanding. For AI, this entails more than generating correct statements. It requires showing uptake:
* applying concepts correctly across cases,
* responding to defeaters,
* grasping the inferential consequences of claims,
* recognizing when claims no longer fit.
Without +U, AI outputs risk remaining surface mimicry — statistical echoes of human reasoning. With +U, they could approximate conceptual competence: the ability to play the language-game of giving and asking for reasons.
Why Epistemology Matters for AI Safety
Technical controls are vital, but without an epistemological grammar they risk being blind. JTB+U offers a framework for:
* Transparency — AI can show what kind of certainty it claims.
* Trust — users can see hinge assumptions and justificatory routes.
* Humility — AI can learn to say “I don’t know” when defeaters arise.
* Alignment — systems become participants in human language-games, not alien oracles.
AI will never be “safe” if we cannot tell when it knows what it says it knows. A Wittgensteinian epistemology does not solve all engineering problems, but it clarifies the standards by which outputs should be judged. If adopted, it could help AI evolve from a powerful but opaque prediction machine into a responsible reasoning partner.
Conclusion: Epistemology in Practice
Philosophy is often accused of irrelevance, but here it has something urgent to offer. The JTB+U framework, enriched by Wittgenstein’s grammar of hinges and language-games, provides exactly the clarity needed at the frontier of AI. It disciplines knowledge-claims, distinguishes types of certainty, contextualizes justification, and demands understanding. If we are serious about aligning AI with human values, we must first align it with the human grammar of knowledge. Epistemology, far from being a museum piece, may be one of the keys to AI’s safe future.
If metaphysics provides the horizon of intelligibility, Wittgenstein’s later philosophy supplies the instruments for navigating within it. His method is therapeutic rather than speculative: instead of offering new theories of knowledge, it clarifies how the word know functions in the practices where sense and doubt are learned. The tools are deceptively simple—language-games, grammar, forms of life, family resemblance, and hinges—but they work together, reinforced by the ideas of rule-following, public criteria, and the river-bed imagery of On Certainty. Taken as a whole, this toolkit grounds epistemology not in metaphysical essence but in lived intelligibility.
Language-games: where “know” has meaning
Wittgenstein begins with the recognition that meaning arises from use. Words are not labels for private entities but moves within human activities. To call something knowledge is not to identify a mysterious inner state but to perform a specific act inside a game with shared rules—asserting, challenging, correcting, teaching. Each domain has its own grammar of knowing: the scientist cites data, the witness swears an oath, the child repeats a lesson. There is no single essence of know; the unity lies in family likeness across these games. By examining language-games, we shift the epistemological question from “What is knowledge?” to “How do we use ‘know’ here?” The philosopher’s task becomes descriptive rather than legislative.
Grammar: the logical order that frames sense and doubt
Grammar, for Wittgenstein, is not syntax but the underlying logic that determines what counts as sense. It tells us what it means to justify, to verify, to doubt. Grammar sets the boundaries of intelligible talk: we can meaningfully say “I know this is a hand,” but not “I know I am in pain.” The latter confuses private experience with public criteria. Grammar thus replaces the metaphysician’s search for foundations with attention to rule-governed use. To grasp a concept grammatically is to know what would count as applying it correctly, what would make its application nonsensical, and how mistakes show themselves. Epistemology becomes a study of conceptual grammar—the order that lets sense and error exist at all.
Forms of life: the public foundations of justification
Every grammar stands on a background of practices, gestures, and agreements that are not themselves justified but simply enacted. These are our forms of life: the biological and cultural patterns within which reasoning has meaning. Justification presupposes such a background. We can question a witness, but not the practice of questioning itself; we can test a thermometer, but not the institution of measurement that makes testing possible. Forms of life are not propositions but the lived matrix of criteria. They explain how justification can be public without being infinite: our shared ways of acting already contain the standards that make giving reasons possible.
Rule-following and public criteria
Within a form of life, rules acquire authority through training and correction. To follow a rule is not to consult an inner diagram but to participate competently in a practice where others can see and correct our moves. This dissolves the picture of justification as an internal state of certainty. What shows that I understand a rule is not introspection but my ability to go on correctly when circumstances vary. Knowledge therefore carries a social dimension: it is demonstrated in action and confirmed by public criteria. Wittgenstein’s reminder—there is no inner pointing to meaning—cuts against the Cartesian idea that knowing is primarily a private event. The grammar of know is visible in use, not hidden in consciousness.
Family resemblance: unity without essence
Philosophers often seek the single property that makes all instances of knowledge what they are. Wittgenstein advises a different posture: notice the overlapping similarities among uses instead of chasing a universal definition. Just as “games” share no one essence but display a network of resemblances—competition, rules, play—so too “knowledge” unites diverse activities by kinship rather than identity. This insight loosens the grip of essentialism that has haunted epistemology since Plato. It allows JTB, later extended to JTB+U, to function as a grammatical model rather than as a metaphysical claim. Its durability lies in family likeness across contexts, not in a timeless form.
Hinges and the river-bed: the arational background of reason
On Certainty adds the final and most radical instrument. Every act of justification presupposes propositions that stand fast—hinges that make doubt meaningful. These are not beliefs we know but certainties we act from. They form the river-bed in which the current of reasons flows. To question them all at once would be to lose the very distinction between sense and nonsense. Examples include “There is an external world,” “Objects persist,” “Words have stable meanings,” and, in your metaphysical horizon, “Consciousness is the condition for any appearing at all.” Hinges are arational, not irrational; they lie beneath justification, providing the stage upon which justification can occur.
This insight explains why epistemic regress ends without circularity. When reasons run out, we do not reach an arbitrary stopping point but the practical background that makes reasoning possible. To call something a hinge is to mark the transition from saying to doing, from proposition to practice. Wittgenstein’s point is grammatical: the verb to know presupposes a contrast with possible doubt; remove that contrast, and the word loses its function. Hinges, then, are the conditions of meaningful knowledge, not propositions we could ever justify or refute.
Doubt as practice-bound
Because hinges define the limits of intelligible doubt, skepticism must itself be seen as a language-game. Doubting that the external world exists or that one has a body is not a deeper form of inquiry but a misuse of grammar—like playing chess without a board. Doubt has sense only where the framework of certainty stands fast. This reframes epistemology: instead of searching for indubitable foundations, we describe the hinges that already stabilize our reasoning. Certainty here is not a psychological feeling but a logical role. It anchors rather than concludes.
The toolkit as re-grounding for epistemology
When these instruments work together, they convert epistemology from a quest for absolute justification into a grammar of responsible use. Language-games reveal diversity; grammar maps the logic of sense; forms of life show why justification is public; rule-following and criteria keep meaning from collapsing into subjectivity; family resemblance preserves unity without essence; and hinges secure the background that makes any of this possible. The result is an epistemology both humbler and stronger: humbler because it recognizes limits, stronger because it grounds knowledge in the lived regularities that precede theory.
Wittgenstein’s method thus complements rather than replaces the classical JTB framework. JTB describes the explicit structure of epistemic accountability; the toolkit shows the soil in which that structure grows. Together they transform the question of knowledge from a search for metaphysical foundations into an examination of the practices that sustain sense. When we later add understanding as the fourth component, the +U will draw directly on these insights: understanding is nothing other than fluency in a language-game, mastery of its grammar, and attunement to its hinges.
In this sense, JTB+U performs a Wittgensteinian clarification: it dissolves the illusion that justification alone guarantees comprehension. “U” distinguishes genuine justification from parroting, algorithmic correctness, or social conformity. Philosophically, that difference is now urgent—especially in an age where machines can simulate justification without understanding.
This is important, because it's easy to suppose your point is correct.
When we examine how the word know functions in our language-games, we see that understanding is built into its grammar. To say “I know that p” normally implies that I can use p rightly in related contexts, that I see its sense and can extend it coherently. We withdraw the word know when this fluency is missing, as when someone parrots a theorem or repeats an argument they do not comprehend. Thus, understanding is not an optional embellishment but part of what gives the concept of knowledge its life. JTB has always assumed it, much as a door presupposes its hinge even when the hinge is unseen.
Making that hinge explicit matters because it prevents epistemology from mistaking outward form for inner mastery. Classical analyses of justification tend to focus on external adequacy: the quality of reasons, the truth of premises, the logical connection among propositions. But none of these suffice if the knower lacks comprehension of how those reasons work. The +U draws attention to this internal dimension, protecting JTB from its own abstraction. It ensures that the model remains tied to lived competence rather than to formal correctness alone.
From a Wittgensteinian perspective, this move simply applies his method to epistemology itself. By describing how know operates in our practices, we notice that understanding is already part of its use. Knowledge is shown in one’s ability to go on rightly when the explicit rule runs out, to recognize when an argument holds and when it does not. The philosopher’s task is not to add new parts to the machine but to illuminate what makes it run. In this light, JTB+U is not a new engine but a clearer description of the one we have always been using.
Naming understanding thus gives epistemology self-awareness. It acknowledges the quiet condition that makes justification possible and holds belief in contact with truth. To call the model JTB+U is to make explicit the hinge on which it already turns. The addition changes nothing in principle, yet it changes everything in practice: it restores to the concept of knowledge the depth and accountability that modern epistemology, in its fixation on external form, too easily neglects.
The endurance of the classical triad lies not in philosophical inertia but in functional necessity. Wherever human beings act together, we rely—often without notice—on the grammar that JTB names. Truth secures contact with reality; belief marks personal assent; justification connects the two through publicly defensible reasons. Remove any one element and the practice collapses. The model persists because its logic is lived before it is theorized. Science, law, and ordinary life all enact its pattern, however differently they speak.
Consider science first, not as an institution but as a disciplined form of life. A physicist claims to know that a certain particle has a particular charge. What makes that claim knowledge rather than opinion is not conviction but the convergence of truth and justification. The statement corresponds to how the world behaves; the methods used to reach it—calibration, replication, peer review—provide the warrant that secures belief against mere luck. The scientist’s belief, her internal assent, is indispensable but not decisive. If later evidence overturns the finding, we say that the community was mistaken, not that belief altered truth. This readiness to correct itself shows the health of the practice: knowledge here is corrigible without being arbitrary.
In science, JTB functions as a structure of accountability. Truth guards against fantasy; justification institutionalizes humility. A result that cannot be checked or replicated fails the justificatory test no matter how confidently it is asserted. Likewise, a correct result reached by accident—a lucky guess or an uncalibrated instrument—fails the epistemic test because justification is missing. These boundaries mirror the grammar that JTB codifies: luck without reason is not knowledge, and reason without truth is illusion. The laboratory simply dramatizes what ordinary cognition already presupposes.
The same structure governs law, though expressed in another language-game. A jury must decide whether an accused person committed a crime. The verdict involves belief, but that belief counts as knowledge only when tethered to evidence that meets public standards—cross-examination, corroboration, admissibility. Truth is represented by the facts as they occurred; belief is the jurors’ collective assent; justification is the process that links the two—the rules of evidence and reasoning that make the verdict intelligible. The system acknowledges the fallibility of justification through appeals and retrials, mechanisms that reflect the same epistemic humility found in science. Even where human judgment replaces experiment, the grammar remains constant: knowledge requires a claim to be both true and justifiable to others.
Legal reasoning also shows why knowledge must be public to be binding. The witness who swears to tell the truth invokes all three conditions. Truth corresponds to what occurred; belief is the sincerity of the witness; justification is the evidentiary frame that renders the testimony credible. A statement may be true yet unjustified if it cannot be corroborated, or justified yet false if the witness is mistaken. These permutations display the interlocking checks that give the concept its durability. We could abolish juries or rewrite evidentiary codes, but any workable system of accountability would still presuppose the same triad.
Outside formal institutions, JTB continues to guide everyday reasoning. When I say that I know the bus leaves at eight fifteen, I am implicitly asserting that the schedule is accurate (truth), that I believe it (assent), and that I have grounds—experience, confirmation, or testimony—to warrant the claim. If the bus departs at eight thirty, I was mistaken, not lying. The grammar of correction—“I thought I knew”—shows that knowledge is a normative status, not a psychological state. We retract know precisely when one of its components fails.
Such examples reveal that JTB is not a theoretical invention but a description of how epistemic life is already organized. Each time we distinguish between “He believes it” and “He knows it,” we invoke this grammar. Justification serves as the hinge between subjective conviction and objective warrant, allowing communities to coordinate understanding without collapsing into solipsism. The continuity of this pattern across domains explains its longevity. Cultures differ in what they treat as good evidence, yet all maintain a distinction between reliable and unreliable belief. That constancy points to a deep pragmatic truth: societies cannot act coherently without a shared grammar of epistemic accountability.
The triad’s durability also shows its resilience to technological change. Algorithms, like humans, are judged by truth, belief-analogues, and justification. A predictive model that forecasts rain tomorrow is evaluated by whether it rains (truth), how confidently the system assigned probability (belief-analogue), and whether the reasoning behind the prediction—its data and parameters—holds up (justification). We demand these checks even of machines because they mark the boundary between information and knowledge. The form of life shifts, but the grammar remains.
Durability here should not be confused with rigidity. Each component balances and corrects the others. Truth disciplines belief; belief animates truth; justification mediates between them. Remove truth and we drift into relativism; remove belief and we are left with sterile description; remove justification and we lapse into dogma. The triad functions as a self-correcting system, not a closed one. It remains stable precisely because it allows error to be recognized and remedied within practice.
This balance can be seen in education, medicine, and ordinary trust. In education, to know a theorem is not merely to recite it but to understand its proof and application—a glimpse of the +U that will later enter our model. In medicine, to know a diagnosis is to link symptoms to mechanisms through reasoning that others can review. In friendship, to know someone’s character is to form a belief responsive to evidence and revised by experience. Across these contexts, the same triadic structure persists: truth as correspondence, belief as personal assent, justification as the publicly defensible bridge between them.
Wittgenstein’s contribution is to make this structure visible rather than reinvent it. He shows that the power of JTB comes from its embeddedness in language-games. The standards of justification differ between a physicist and a parent, yet both belong to forms of life where reasons can be given and challenged. By examining those practices, we see that the grammar of know is stable not because it is timeless but because it is lived. When philosophers attempt to replace JTB, they usually reintroduce it under another name. Even coherence theories and reliabilism preserve its skeleton: truth as target, belief as stance, justification as route. The differences lie in emphasis, not in structure.
The persistence of JTB across changing practices is therefore a mark of its depth. It names the minimal conditions under which knowledge remains intelligible. Even when justification fails or belief wavers, we appeal back to this framework to make sense of the failure. It functions like the grammar of a language: rarely noticed when used well, instantly felt when violated. To reject JTB entirely would be to forfeit the distinction between knowledge and luck, between reasoned warrant and accidental truth.
For this reason the model endures. It does not demand perfection but provides a standard by which imperfection can be recognized. Its durability comes from its fit with the rhythms of human reasoning, from the fact that it mirrors the way we already keep our words in contact with the world. In this light, JTB is not a relic but a record of the conditions that make rational discourse possible. We can now examine its limits—the ambiguities of justification and the regress of reasons—and prepare for the Wittgensteinian insight that will dissolve those tensions without abandoning realism.
We are entering an age in which the very conditions of knowing are being rewritten. Information now multiplies faster than human understanding can absorb it, and systems that simulate reasoning already shape what most people take to be true. The problem is no longer access to data but the loss of criteria for weighing it. Algorithms can imitate justification, narratives can mimic coherence, and conviction can be manufactured at scale. In such an environment, epistemology becomes a public necessity, not an academic luxury. To know what knowledge is, to see how truth, belief, justification, and understanding interlock, is the only safeguard against a world where persuasion replaces reason and where the grammar of “knowing” itself is quietly altered. Clarifying that grammar is the task before us.
I've taken a while to respond, because there is a fair bit of subtlety, nuance in this question about understanding. I agree one cannot be justified in believing something without understanding how the justification works—that is, understanding how the (purported) facts that constitute the justification entail the belief.
Someone could parrot an explanation of how a belief is justified without really 'getting' the explanation. It is very difficult, though, to say just what "getting" an explanation consists in other than the feeling or sense of getting it.
In What Computers Can't Do and What Computers Still Can't Do Hubert Dreyfus argued that computers will never be genuinely intelligent because they cannot understand context.
Yet the LLMs do seem to be able to do that, even though I cannot imagine how it would possible that they do that. Is it just a matter of parroting so sophisticated as to be able to fool us into thinking they do understand context?
It begs the question as to how we grasp context, and I don't have an answer for that, but can only think that it must somehow be a matter of feeling. I can't imagine a computer having a feeling for context—but then what do I know?
Anyway...interesting stuff!
That’s a fair point, and an important point. When I say that someone can parrot an explanation without getting it, I don’t mean that “getting” is a hidden mental glow or some private feeling that accompanies comprehension. I mean that understanding shows itself in how a person can go on rightly — how they use what they’ve learned in new circumstances, recognize when it breaks down, and repair it. It’s not the presence of a sensation but the manifestation of mastery within a shared practice.
That’s where I think the difference lies between human understanding and what large language models are doing. They can reproduce the surface grammar of context, the statistical pattern of what normally follows what, but they don’t inhabit the life-grammar that gives those patterns weight. They have no stake, no risk, no embodied continuity of experience. Our grasp of context isn’t just cognitive; it’s lived. It shows up as what I’d call a feeling for relevance: a readiness to respond that draws on our bodily attunement to the world and to one another.
So yes, LLMs can simulate contextual understanding impressively, but simulation isn’t participation. Their outputs can mirror what understanding looks like, yet nothing in them corresponds to the hinge-layer that makes sense possible in the first place. Our “feeling for context” isn’t a mysterious extra — it’s the human way the background of meaning becomes visible in use.
Post #1
Justified True Belief Plus Understanding: A Wittgensteinian Extension
Samuel L. Naccarato
Abstract
This paper reexamines the classical model of knowledge as Justified True Belief (JTB) and argues for its refinement through the addition of Understanding (+U). Drawing on Wittgenstein’s later philosophy—especially the concepts of language-games, grammar, and hinge propositions—it shows that justification operates within shared forms of life rather than in isolation. The JTB+U framework retains truth, belief, and justification but grounds them in public criteria and interpretive competence: knowing is not only having reasons but grasping how reasons function within practice. Three guardrails (No-False-Grounds, Practice-Safety, and Defeater Screening) and five justificatory routes (Testimony, Logic, Sensory Experience, Linguistic Training, Pure Logic) formalize this discipline of reliability. The analysis situates epistemology amid today’s information landscape, where distinguishing knowledge from persuasion has become urgent. By integrating Wittgenstein’s insights with modern concerns about data, AI, and scientific reasoning, the paper presents an epistemology that is self-correcting, communal, and humane. JTB+U preserves realism without dogmatism, acknowledging that understanding is both the hinge of justification and the safeguard of discernment in an age of unmoored information.
I. Why Epistemology Still Matters
It is fashionable to treat epistemology as an exhausted discipline—an inheritance of an earlier age, once useful for justifying science or theology but now displaced by data and probability. Yet the problem of knowledge has not vanished; it has multiplied. In a world where opinion spreads faster than evidence and conviction can be engineered by algorithms, the need to distinguish knowing from believing has never been greater. We inhabit a culture that prizes information but neglects understanding; it equates confidence with competence. Epistemology, properly understood, is not a relic but the grammar of orientation—our means of finding footing amid proliferating claims to truth.
We are entering an age in which the very conditions of knowing are being rewritten. Information now multiplies faster than human understanding can absorb it, and systems that simulate reasoning already shape what most people take to be true. The problem is no longer access to data but the loss of criteria for weighing it. Algorithms can imitate justification, narratives can mimic coherence, and conviction can be manufactured at scale. In such an environment, epistemology becomes a public necessity, not an academic luxury. To know what knowledge is—to see how truth, belief, justification, and understanding interlock—is the only safeguard against a world where persuasion replaces reason and where the grammar of “knowing” itself is quietly altered. Clarifying that grammar is the task before us.
To speak of knowledge presupposes an order of assessment. We do not call every opinion knowledge, nor every true remark knowledgeable. The distinction is not moral but functional: society, law, and science depend on reliable ways of sorting appearance from reality. When a court accepts testimony, when a physician interprets a scan, when a citizen evaluates a headline, the same question arises in different dress: what warrants belief? Epistemology matters because these decisions, repeated daily, determine whether our shared practices remain rational or collapse into echo.
The classical model—Justified True Belief—still captures the skeleton of these practices. Truth ensures contact with reality; belief marks the personal uptake of that contact; justification provides the public warrant. Each condition blocks a familiar failure: without truth, we cling to illusion; without belief, we mouth what we do not hold; without justification, we risk luck or hearsay. The triad endures not because Plato decreed it but because human life still relies on the difference between being right and merely happening to be right. JTB describes, in grammatical form, the criteria by which we hold one another epistemically accountable.
The word know itself does not wear a single face. We use it to express both epistemic and non-epistemic relations: I know the capital of France, I know how you feel, You should know better than that. Some of these are claims to justification; others are gestures of familiarity, empathy, or expectation. Wittgenstein reminds us that meaning follows use: the epistemic sense of know is only one branch within a broader family of uses. Clarifying that branch—seeing how it functions within our language-games—prevents us from mistaking conviction, or mere agreement, for knowledge. JTB+U is concerned solely with the epistemic use, where truth, belief, justification, and understanding converge within a form of life.
Yet the simplicity of JTB conceals a difficulty sharpened by modernity. One can satisfy its letter without satisfying its spirit. A belief may be true and even justified by available evidence yet still lack the kind of grasp that distinguishes genuine knowledge from the echo of authority. Students can recite correct answers; machines can compute them; neither necessarily understands what they affirm. The missing element is not another reason but an internal relation—the capacity to use, extend, and situate what one claims to know. This fourth component, understanding (U), restores life to the classical framework and reconnects epistemology with practice.
Understanding bridges knowing that and knowing how. It is not a separate species of knowledge but a measure of conceptual uptake: one understands when one can move fluently within the logical and practical consequences of a claim. To say “I know how a lever works” or “I know what justice requires” is to claim competence beyond the recital of propositions. This element of grasp allows knowledge to resist mere imitation. Adding U to JTB does not alter the structure of knowledge; it clarifies the dimension tacitly presupposed whenever philosophers spoke of insight, judgment, or wisdom—the ability to navigate a concept’s grammar, not merely repeat it.
The urgency of this refinement becomes clear when justification falters under the weight of information. In an age of machine learning, deepfakes, and algorithmic persuasion, justification alone cannot guarantee comprehension. We can outsource calculation but not understanding. Even a flawless predictive system, if it cannot recognize the bounds of its certainty or the hinges on which its reasoning turns, mistakes correlation for truth. JTB+U therefore serves both as an epistemic model and as a moral warning: intelligence without understanding is cleverness without orientation.
The revival of epistemology thus requires a shift in emphasis—from metaphysical speculation to grammatical description. Wittgenstein’s later philosophy provides the tools for that shift. His method was not to invent new theories of knowledge but to examine how the word know functions within our language-games. In doing so, he showed that justification is always contextual, embedded in the forms of life that sustain meaning, and that doubt operates only against a background of what stands fast. Our standards of justification are not free-floating; they draw their authority from these inherited practices. JTB+U continues this line by formalizing what Wittgenstein left implicit: that understanding is active mastery of a grammar, not possession of a mental state. Knowledge is not a mysterious substance but a practice: moving rightly within the space of reasons.
This also clarifies why epistemology cannot be replaced by psychology or neuroscience. No scan or algorithm can decide whether a belief is justified; that judgment belongs to the public web of reasons in which meaning is maintained. To know something is to occupy a position within that web—to give and ask for reasons intelligibly to others. Epistemology names the effort to keep that web intact, to prevent private conviction from masquerading as objective warrant. When those boundaries collapse, language loses traction and communities lose trust.
This project is conservative in spirit but progressive in aim. It seeks not to discard the classical framework but to ground it more deeply in lived practice. Adding understanding acknowledges that knowledge is never exhausted by propositions; using Wittgenstein’s methods locates those propositions within the activities that give them sense. The result is an epistemology both stricter and more humane: strict because it demands defeater-sensitivity and conceptual clarity, humane because it recognizes that justification is always conducted within a form of life.
Although the framework I develop here is not metaphysical in method, it is not divorced from metaphysical depth. JTB+U does not appeal to a single essence or hidden ontology to give knowledge its meaning, yet it presupposes that justification and understanding unfold within a reality intelligible to mind. Metaphysics, in this sense, forms a horizon rather than a foundation: it shapes what can be meant without dictating how meaning is given. The grammar of knowledge may be clarified without invoking ultimate reality, but such clarity need not deny that a deeper order exists—what I later call the ultimate hinge of consciousness, the background that makes any grammar of understanding possible.
If epistemology is to remain a living discipline, it must show how understanding anchors responsible judgment across domains—from the sciences and ethics to education and emerging forms of artificial intelligence. Only by refining what it means to know can we preserve a shared orientation toward truth in an age increasingly shaped by uncertainty.
In what follows, I review why the JTB framework remains the most durable articulation of knowledge in practice, then trace its internal tensions—especially the ambiguity of justification and the regress of reasons—and show how Wittgenstein’s notion of hinges dissolves them without skepticism. From there, I introduce the +U element, outline the guardrails that keep justification reliable, and distinguish the several uses of certainty that reveal where knowledge properly resides. The paper concludes by showing how this Wittgensteinian extension preserves knowledge as a corrigible yet indispensable concept—one capable of guiding both human and artificial intelligence toward a more responsible understanding of truth.
II. The Wittgensteinian Toolkit—Clarifying Our Grammar of Knowledge
If metaphysics provides the horizon of intelligibility, Wittgenstein’s later philosophy supplies the instruments for navigating within it. His method is therapeutic rather than speculative: instead of offering new theories of knowledge, it clarifies how the word know functions in the practices where sense and doubt are learned. The tools are deceptively simple—language-games, grammar, forms of life, family resemblance, and hinges—but they work together, reinforced by the ideas of rule-following, public criteria, and the river-bed imagery of On Certainty. Taken as a whole, this toolkit grounds epistemology not in metaphysical essence but in lived intelligibility.
Language-games: where “know” has meaning
Wittgenstein begins with the recognition that meaning arises from use. Words are not labels for private entities but moves within human activities. To call something knowledge is not to identify a mysterious inner state but to perform a specific act inside a game with shared rules—asserting, challenging, correcting, teaching. Each domain has its own grammar of knowing: the scientist cites data, the witness swears an oath, the child repeats a lesson. There is no single essence of know; the unity lies in family likeness across these games. By examining language-games, we shift the epistemological question from “What is knowledge?” to “How do we use ‘know’ here?” The philosopher’s task becomes descriptive rather than legislative.
Grammar: the logical order that frames sense and doubt
Grammar, for Wittgenstein, is not syntax but the underlying logic that determines what counts as sense. It tells us what it means to justify, to verify, to doubt. Grammar sets the boundaries of intelligible talk: we can meaningfully say “I know this is a hand,” but not “I know I am in pain.” The latter confuses private experience with public criteria. Grammar thus replaces the metaphysician’s search for foundations with attention to rule-governed use. To grasp a concept grammatically is to know what would count as applying it correctly, what would make its application nonsensical, and how mistakes show themselves. Epistemology becomes a study of conceptual grammar—the order that lets sense and error exist at all.
Forms of life: the public foundations of justification
Every grammar stands on a background of practices, gestures, and agreements that are not themselves justified but simply enacted. These are our forms of life: the biological and cultural patterns within which reasoning has meaning. Justification presupposes such a background. We can question a witness, but not the practice of questioning itself; we can test a thermometer, but not the institution of measurement that makes testing possible. Forms of life are not propositions but the lived matrix of criteria. They explain how justification can be public without being infinite: our shared ways of acting already contain the standards that make giving reasons possible. Language-games and forms of life are mutually defining: our forms of life give stability to our games, and the games, in turn, articulate the forms of life they express.
Rule-following and public criteria
Within a form of life, rules acquire authority through training and correction. To follow a rule is not to consult an inner diagram but to participate competently in a practice where others can see and correct our moves. This dissolves the picture of justification as an internal state of certainty. What shows that I understand a rule is not introspection but my ability to go on correctly when circumstances vary. Knowledge therefore carries a social dimension: it is demonstrated in action and confirmed by public criteria. Wittgenstein’s reminder—there is no inner pointing to meaning—cuts against the Cartesian idea that knowing is primarily a private event. The grammar of know is visible in use, not hidden in consciousness.
Family resemblance: unity without essence
Philosophers often seek the single property that makes all instances of knowledge what they are. Wittgenstein advises a different posture: notice the overlapping similarities among uses instead of chasing a universal definition. Just as “games” share no one essence but display a network of resemblances—competition, rules, play—so too “knowledge” unites diverse activities by kinship rather than identity. This insight loosens the grip of essentialism that has haunted epistemology since Plato. It allows JTB, later extended to JTB+U, to function as a grammatical model rather than as a metaphysical claim. Its durability lies in family likeness across contexts, not in a timeless form.
Hinges and the river-bed: the arational background of reason
On Certainty adds the final and most radical instrument. Every act of justification presupposes propositions that stand fast—hinges that make doubt meaningful. These are not beliefs we know but certainties we act from. They form the river-bed in which the current of reasons flows. To question them all at once would be to lose the very distinction between sense and nonsense. Examples include “There is an external world,” “Objects persist,” “Words have stable meanings,” and, in your metaphysical horizon, “Consciousness is the condition for any appearing at all.” Hinges are arational, not irrational; they lie beneath justification, providing the stage upon which justification can occur.
This insight explains why epistemic regress ends without circularity. When reasons run out, we do not reach an arbitrary stopping point but the practical background that makes reasoning possible. To call something a hinge is to mark the transition from saying to doing, from proposition to practice. Wittgenstein’s point is grammatical: the verb to know presupposes a contrast with possible doubt; remove that contrast, and the word loses its function. Hinges, then, are the conditions of meaningful knowledge, not propositions we could ever justify or refute.
Doubt as practice-bound
Because hinges define the limits of intelligible doubt, skepticism must itself be seen as a language-game. Doubting that the external world exists or that one has a body is not a deeper form of inquiry but a misuse of grammar—like playing chess without a board. Doubt has sense only where the framework of certainty stands fast. This reframes epistemology: instead of searching for indubitable foundations, we describe the hinges that already stabilize our reasoning. Certainty here is not a psychological feeling but a logical role. It anchors rather than concludes.
The toolkit as re-grounding for epistemology
When these instruments work together, they convert epistemology from a quest for absolute justification into a grammar of responsible use. Language-games reveal diversity; grammar maps the logic of sense; forms of life show why justification is public; rule-following and criteria keep meaning from collapsing into subjectivity; family resemblance preserves unity without essence; and hinges secure the background that makes any of this possible. The result is an epistemology both humbler and stronger: humbler because it recognizes limits, stronger because it grounds knowledge in the lived regularities that precede theory.
Wittgenstein’s method thus complements rather than replaces the classical JTB framework. JTB describes the explicit structure of epistemic accountability; the toolkit shows the soil in which that structure grows. Together they transform the question of knowledge from a search for metaphysical foundations into an examination of the practices that sustain sense. When we later add understanding as the fourth component, the +U will draw directly on these insights: understanding is nothing other than fluency in a language-game, mastery of its grammar, and attunement to its hinges.
Justified True Belief Plus Understanding: A Wittgensteinian Extension
Samuel L. Naccarato
III. JTB in Practice—Strengths and Durability
With this toolkit in hand, we can now return to JTB itself, no longer as an abstract formula but as a practice embedded in forms of life. The next section examines how the triad of truth, belief, and justification operates within science, law, and ordinary reasoning, showing why it has endured across centuries of intellectual change. JTB persists because our language-games still require the grammar it names.
The endurance of the classical triad lies not in philosophical inertia but in functional necessity. Wherever human beings act together, we rely—often without notice—on the grammar that JTB names. Truth secures contact with reality; belief marks personal assent; justification connects the two through publicly defensible reasons. Remove any one element and the practice collapses. The model persists because its logic is lived before it is theorized. Science, law, and ordinary life all enact its pattern, however differently they speak.
To dismiss testimony out of hand is to practice a selective skepticism that defeats itself. Every belief, even in science, relies on others’ reports—records, measurements, observations, and reasoning transmitted through language. The issue is not whether testimony can yield knowledge but under what conditions it does. When sources are transparent, independent, and open to challenge, testimony functions as a public route of justification, not a private appeal to authority. A framework that denied this would unravel its own basis, for even the principles of logic and experiment reach us through human transmission.
Philosophers have long distinguished between knowledge by acquaintance—the direct familiarity one has with a person, color, or sensation—and knowledge by description, which depends on propositions or reports. The former is immediate and non-inferential; the latter mediated and linguistic. Both fit naturally within the JTB grammar: acquaintance anchors belief in perception and experience, while description anchors belief in testimony and reasoning. What Wittgenstein’s method adds is the reminder that these are not competing species but overlapping uses of know, each governed by its own criteria of justification within a form of life.
Consider science first, not as an institution but as a disciplined form of life. A physicist claims to know that a certain particle has a particular charge. What makes that claim knowledge rather than opinion is not conviction but the convergence of truth and justification. The statement corresponds to how the world behaves; the methods used to reach it—calibration, replication, peer review—provide the warrant that secures belief against mere luck. The scientist’s belief, her internal assent, is indispensable but not decisive. If later evidence overturns the finding, we say that the community was mistaken, not that belief altered truth. This readiness to correct itself shows the health of the practice: knowledge here is corrigible without being arbitrary.
In science, JTB functions as a structure of accountability. Truth guards against fantasy; justification institutionalizes humility. A result that cannot be checked or replicated fails the justificatory test no matter how confidently it is asserted. Likewise, a correct result reached by accident—a lucky guess or an uncalibrated instrument—fails the epistemic test because justification is missing. These boundaries mirror the grammar that JTB codifies: luck without reason is not knowledge, and reason without truth is illusion. The laboratory simply dramatizes what ordinary cognition already presupposes.
The same structure governs law, though expressed in another language-game. A jury must decide whether an accused person committed a crime. The verdict involves belief, but that belief counts as knowledge only when tethered to evidence that meets public standards—cross-examination, corroboration, admissibility. Truth is represented by the facts as they occurred; belief is the jurors’ collective assent; justification is the process that links the two—the rules of evidence and reasoning that make the verdict intelligible. The system acknowledges the fallibility of justification through appeals and retrials, mechanisms that reflect the same epistemic humility found in science. Even where human judgment replaces experiment, the grammar remains constant: knowledge requires a claim to be both true and justifiable to others.
Legal reasoning also shows why knowledge must be public to be binding. The witness who swears to tell the truth invokes all three conditions. Truth corresponds to what occurred; belief is the sincerity of the witness; justification is the evidentiary frame that renders the testimony credible. A statement may be true yet unjustified if it cannot be corroborated, or justified yet false if the witness is mistaken. These permutations display the interlocking checks that give the concept its durability. We could abolish juries or rewrite evidentiary codes, but any workable system of accountability would still presuppose the same triad.
Outside formal institutions, JTB continues to guide everyday reasoning. When I say that I know the bus leaves at eight fifteen, I am implicitly asserting that the schedule is accurate (truth), that I believe it (assent), and that I have grounds—experience, confirmation, or testimony—to warrant the claim. If the bus departs at eight thirty, I was mistaken, not lying. The grammar of correction—“I thought I knew”—shows that knowledge is a normative status, not a psychological state. We retract know precisely when one of its components fails.
Such examples reveal that JTB is not a theoretical invention but a description of how epistemic life is already organized. Each time we distinguish between “He believes it” and “He knows it,” we invoke this grammar. Justification serves as the hinge between subjective conviction and objective warrant, allowing communities to coordinate understanding without collapsing into solipsism. The continuity of this pattern across domains explains its longevity. Cultures differ in what they treat as good evidence, yet all maintain a distinction between reliable and unreliable belief. That constancy points to a deep pragmatic truth: societies cannot act coherently without a shared grammar of epistemic accountability.
The triad’s durability also shows its resilience to technological change. Algorithms, like humans, are judged by truth, belief-analogues, and justification. A predictive model that forecasts rain tomorrow is evaluated by whether it rains (truth), how confidently the system assigned probability (belief-analogue), and whether the reasoning behind the prediction—its data and parameters—holds up (justification). We demand these checks even of machines because they mark the boundary between information and knowledge. The form of life shifts, but the grammar remains.
Durability here should not be confused with rigidity. Each component balances and corrects the others. Truth disciplines belief; belief animates truth; justification mediates between them. Remove truth and we drift into relativism; remove belief and we are left with sterile description; remove justification and we lapse into dogma. The triad functions as a self-correcting system, not a closed one. It remains stable precisely because it allows error to be recognized and remedied within practice.
This balance can be seen in education, medicine, and ordinary trust. In education, to know a theorem is not merely to recite it but to understand its proof and application—a glimpse of the +U that will later enter our model. In medicine, to know a diagnosis is to link symptoms to mechanisms through reasoning that others can review. In friendship, to know someone’s character is to form a belief responsive to evidence and revised by experience. Across these contexts, the same triadic structure persists: truth as correspondence, belief as personal assent, justification as the publicly defensible bridge between them.
Wittgenstein’s contribution is to make this structure visible rather than reinvent it. He shows that the power of JTB comes from its embeddedness in language-games. The standards of justification differ between a physicist and a parent, yet both belong to forms of life where reasons can be given and challenged. By examining those practices, we see that the grammar of know is stable not because it is timeless but because it is lived. When philosophers attempt to replace JTB, they usually reintroduce it under another name. Even coherence theories and reliabilism preserve its skeleton: truth as target, belief as stance, justification as route. The differences lie in emphasis, not in structure.
The persistence of JTB across changing practices is therefore a mark of its depth. It names the minimal conditions under which knowledge remains intelligible. Even when justification fails or belief wavers, we appeal back to this framework to make sense of the failure. It functions like the grammar of a language: rarely noticed when used well, instantly felt when violated. To reject JTB entirely would be to forfeit the distinction between knowledge and luck, between reasoned warrant and accidental truth.
For this reason the model endures. It does not demand perfection but provides a standard by which imperfection can be recognized. Its durability comes from its fit with the rhythms of human reasoning, from the fact that it mirrors the way we already keep our words in contact with the world. In this light, JTB is not a relic but a record of the conditions that make rational discourse possible. We can now examine its limits—the ambiguities of justification and the regress of reasons—and prepare for the Wittgensteinian insight that will dissolve those tensions without abandoning realism.
Justified True Belief Plus Understanding: A Wittgensteinian Extension
Samuel L. Naccarato
IV. The Limits of Classical JTB
For all its durability, the classical model of knowledge conceals internal strains. It describes our epistemic grammar but does not explain how justification itself is secured. If every reason calls for a further reason, the regress of justification seems endless; if the chain simply stops, it risks arbitrariness. JTB thus oscillates between two unsatisfactory poles: infinite regress or dogmatic halt. The problem is not that justification fails, but that its ground is misunderstood. We treat it as though reasons could stand alone, detached from the forms of life that give them sense. To move beyond this impasse, we must examine what makes justification possible at all—how it arises within practices, why it cannot be fully propositional, and what happens when it tries to explain itself.
When justification is pressed for its own warrant, philosophy turns in a circle. Each appeal to evidence, perception, or logic depends on background practices that it cannot itself justify. We trust our senses because they have worked; we rely on induction because it continues to deliver; we accept inference because our community has trained us to do so. None of these rests on proof in the narrow sense. Both Wittgenstein and Gödel expose this structural limit from different directions: the first by showing that justification must end in what “stands fast,” the second by showing that no consistent, effectively axiomatized formal system strong enough for arithmetic can prove all of the arithmetical statements that are true in its standard interpretation. In each case, the search for ultimate justification reveals a boundary built into the practice of reasoning itself.
This boundary is not a defect but a condition of intelligibility. To say that justification depends on what is not justified is not to surrender reason but to recognize its grammar. The chain of reasons stops not in an arbitrary assertion but in action—in the regularities of life that give words and proofs their sense. These are our hinges: arational certainties expressed in doing rather than saying, in counting, measuring, speaking, and trusting testimony. Some are nonlinguistic—bodily and perceptual orientations that make language possible; others are linguistic—rules and criteria we inherit without explicit proof. Together they form the bedrock upon which propositional knowledge rests.
The same structure appears in logic itself. Gödel’s incompleteness theorems show that any consistent, sufficiently strong formal system cannot, from within its own axioms and rules, prove all the truths it expresses. The undecidable sentences of mathematics play a role analogous to Wittgenstein’s hinges: they delineate what can be shown without being themselves derivable. In both cases, the limit is not an obstacle but an architecture—an edge condition that makes meaningful proof and meaningful doubt possible. Recognizing this shifts the philosophical task from seeking absolute justification to describing the frameworks that silently enable it.
Justified True Belief Plus Understanding: A Wittgensteinian Extension
Samuel L. Naccarato
V. JTB+U: Adding Understanding
The regress of justification need not end in skepticism. It ends, rather, in recognition that justification always presupposes a grasp of how reasons connect—a background fluency that cannot itself be justified propositionally. Wittgenstein’s hinges show where reasons stop; understanding shows how they continue to make sense. The classical triad of truth, belief, and justification captures the outward form of knowledge, but its stability depends on an inner relation that binds these elements together. To make that relation explicit is the task of JTB+U.
Some may object that understanding is already contained in justification, that no one can justify a belief without some degree of comprehension. I agree, but the very fact that this dimension remains unarticulated has allowed epistemology to treat justification as if it were purely propositional. Naming +U does not add a new condition; it restores to view the conceptual hinge that justification already turns upon.
Understanding is already implicit in JTB. The classical model could never function without it, for to justify a belief is already to grasp the connection between reasons and conclusion. Yet in most philosophical treatments this grasp is left unarticulated, as though understanding were guaranteed whenever justification appears. My point in making it explicit is not to alter the structure of JTB but to bring to light what it silently depends on.
Understanding functions analogously to a hinge—not arational in the Wittgensteinian sense, but structural in the epistemic sense; it keeps justification in motion—the capacity to follow reasons as reasons, to see how evidence supports a claim rather than merely to repeat that it does. Without that inner relation, justification becomes mechanical and belief drifts toward imitation. When we examine how the word know functions in our language-games, we see that understanding is built into its grammar. To say “I know that p” normally implies that I can use p rightly in related contexts—that I see its sense and can extend it coherently.
We withdraw the word know when this fluency is missing, as when someone parrots a theorem or repeats an argument they do not comprehend. Thus, understanding is not an optional embellishment but part of what gives the concept of knowledge its life. JTB has always assumed it, much as a door presupposes its hinge even when the hinge is unseen. Making that hinge explicit matters because it prevents epistemology from mistaking outward form for inner mastery.
Classical analyses of justification tend to focus on external adequacy: the quality of reasons, the truth of premises, the logical connection among propositions. But none of these suffice if the knower lacks comprehension of how those reasons work. The +U draws attention to this internal dimension, protecting JTB from its own abstraction. It ensures that the model remains tied to lived competence rather than to formal correctness alone.
From a Wittgensteinian perspective, this move simply applies his method to epistemology itself. By describing how know operates in our practices, we notice that understanding is already part of its use. Knowledge is shown in one’s ability to go on rightly when the explicit rule runs out, to recognize when an argument holds and when it does not. The philosopher’s task is not to add new parts to the machine but to illuminate what makes it run.
In this light, JTB+U is not a new engine but a clearer description of the one we have always been using. Naming understanding thus gives epistemology self-awareness. It acknowledges the quiet condition that makes justification possible and holds belief in contact with truth. To call the model JTB+U is to make explicit the hinge on which it already turns. The addition changes nothing in principle, yet it changes everything in practice: it restores to the concept of knowledge the depth and accountability that modern epistemology, in its fixation on external form, too easily neglects.
Philosophers often distinguish knowing that from knowing how. The first concerns propositions, beliefs that can be stated and assessed for truth. The second concerns abilities, skills displayed in doing rather than saying. Yet in practice, the two are intertwined. To know that the Earth has one moon is to hold a justified true belief; to know how to count is to participate in a rule-governed practice that gives such propositions meaning. Understanding bridges these domains. It is what allows one to move from proposition to application, from rule to use, from explicit statement to competent action.
Gilbert Ryle drew this distinction to resist the idea that all knowledge is propositional, but the point can be carried further: understanding is not reducible to either kind. It is the fluency that lets us go on rightly when explicit instruction ends—the ability to see what follows, to extend a pattern without mechanical repetition. In this sense, +U names the skill within belief, the practical mastery that turns justification from recitation into insight. Where knowing that gives structure, knowing how gives life; understanding unites them in a single epistemic posture.
Understanding gives the classical framework its working strength. It prevents justification from collapsing into rote conformity and keeps belief in contact with the practices that confer meaning. In JTB+U, understanding performs a stabilizing function: it disciplines justification, grounds belief, and keeps truth from becoming an abstraction. To understand is to know when justification applies, when it fails, and when further inquiry is needed. It is the tacit mastery that lets us recognize a defeater before it destroys confidence, and to adjust reasons when new evidence appears.
This functional role can be described in three interlocking features. First, understanding is defeater-sensitive: it detects when a justification no longer holds because the context has shifted or the evidence has been undermined. Second, it is publicly oriented: understanding moves within language-games that allow others to test and correct what we claim. Third, it is practice-safe: it operates within the bounds of skills, tools, and norms that keep error recognizable rather than catastrophic. These are the guardrails that make justification resilient instead of brittle.
In this way, +U transforms the classical model without altering its structure. Truth, belief, and justification remain, but their coherence now depends on a living capacity to follow reasons rightly. A community that shares this capacity can correct itself without abandoning realism; a thinker who possesses it can doubt responsibly without falling into skepticism. The model becomes self-monitoring rather than self-sealed. JTB+U thus unites epistemic rigor with Wittgensteinian humility: justification is never final, yet it can be secure enough for action because understanding continuously interprets, tests, and re-grounds it in practice.
Because justification depends on public criteria, the framework of JTB+U is inherently democratic. Knowledge does not belong to experts alone but to any participant trained in the grammar of reasons. Public justification levels the epistemic field: it allows disagreement to become inquiry rather than authority. What distinguishes good reasoning from mere assertion is not who speaks but how claims can be examined, corrected, and improved. The addition of understanding restores this shared capacity to its proper place—it ensures that justification remains a communal achievement rather than a private performance.
Consider a familiar academic scene. A student can recite the steps of a proof in formal logic, yet when asked to apply the same principles in a new example, the reasoning collapses. The difficulty is not with memory but with understanding. The student’s belief that the proof is valid may be true and even accompanied by justification in the narrow sense—citations, derivations, and the correct symbolic form—but the grasp of why those steps hold is missing. By contrast, another student who genuinely understands the proof can adapt it, recognize where an inference fails, and explain its scope. The difference lies not in propositional content but in the mastery that unites rule and use.
This contrast illuminates what +U contributes. Without understanding, justification can mimic knowledge while remaining hollow. With understanding, the connection between truth and belief becomes internally visible: the knower can not only assert the conclusion but trace its sense within a broader practice. In scientific inquiry, this difference distinguishes the technician who repeats a method from the researcher who knows when and why to revise it. In ordinary life, it separates parroting from comprehension, rote conformity from intelligent trust. Understanding gives epistemology a human shape; it turns the abstract structure of JTB into a lived capacity for discernment. The same distinction explains why artificial systems, however advanced their pattern recognition, simulate justification without displaying understanding. They produce correct outputs without the grasp that links rule to use—a difference that exposes, rather than closes, the human horizon of epistemology.
The same distinction appears in our encounter with artificial intelligence. A large language model can reproduce the surface grammar of comprehension—it can extend a discussion, follow contextual cues, and generate reasons that sound plausible—but it does not inhabit the life-grammar that gives those moves their weight. It has no background of risk, training, or embodied continuity. What we call a feeling for context in human understanding is not a private emotion but a readiness to respond grounded in shared forms of life. Machines can simulate coherence, yet simulation is not participation. The +U in JTB+U names precisely this difference: the grasp of meaning that lives in practice and cannot be replaced by correlation.
JTB+U restores the living grammar of knowledge. By making understanding explicit, it completes rather than revises the classical model: truth, belief, and justification now cohere through the grasp that keeps reasons intelligible within practice. The framework is thus strengthened from within—defeater-sensitive, publicly testable, and responsive to context without surrendering objectivity. Yet this clarification raises a deeper question: if understanding binds justification to truth, what binds understanding itself? To answer that, we must look beneath reasons to what makes reasoning possible—the background certainties that stand fast when inquiry begins. It is there, at the level of hinges, that the structure of knowledge finds its ground.
Justified True Belief Plus Understanding: A Wittgensteinian Extension
Samuel L. Naccarato
VI. Grounding JTB+U: Hinges and the Limits of Explanation
Having made explicit what JTB always presupposed, we can now ask what even understanding itself presupposes. If justification depends on understanding, and understanding on the ability to “go on rightly” within a practice, then our inquiry turns toward the background that makes such going-on possible at all. Here we reach the level of what Wittgenstein calls hinge propositions: the certainties that do not stand as conclusions but as the framework within which conclusions have sense. These are not hypotheses or theories but the quiet conditions that give justification its grammar.
A hinge is not known, doubted, or inferred; it is shown. When I check the clock to see if my train leaves at 8:15, I do not also doubt the existence of clocks, the reliability of numbers, or the fact that trains normally run on tracks. These stand fast; they form the river-bed against which all reasoning flows. To treat them as ordinary beliefs would dissolve the very distinction between doubt and knowledge that makes reasoning possible. Wittgenstein treats them as hinges—commitments that stand fast and underwrite the use of reasons.
We misunderstand hinges when we look for them in the wrong logical space. They are not hidden propositions waiting to be uncovered but the background conditions that make propositional exchange possible. In Wittgenstein’s terms, they belong to the grammar of our language-games, not to their content. The certainty that there is an external world, that memories usually persist, or that words keep their meaning from one moment to the next does not arise from inference; it is built into our way of acting and speaking. To question such things would not be to doubt within the game but to suspend the game itself. Hinges, then, mark the limits of meaningful doubt.
Because hinges are shown rather than stated, they resist direct articulation. We notice them only when they shift or fail—when something we took for granted ceases to hold and the practice stumbles. A child learning to tell time, for instance, must acquire not only the vocabulary of numbers but the hinge-certainty that the clock’s face represents a continuous and reliable system. Only within that certainty does the instruction “the train leaves at 8:15” make sense. Likewise, the scientist who checks her instruments does not begin by questioning whether instruments can measure; she works within that bedrock confidence until evidence forces revision. Hinges are thus the tacit limits within which understanding operates, the background from which justification and belief draw their meaning.
Hinges therefore mark the final limit of explanation. They are not conclusions reached by argument but the inherited background that allows argument to begin. Each form of life has its own pattern of such certainties—its ways of acting, measuring, and trusting that make its language-games coherent. Some are bodily and perceptual, such as our confidence that the floor will bear our weight; others are linguistic and communal, such as the expectation that words retain their meaning from one moment to the next. These are not propositions waiting for proof but the bedrock regularities that give “proof” any sense at all.
These hinges also differ in depth and scope. Some belong to our immediate bodily orientation, others to the linguistic and social patterns that stabilize meaning, and still others to the conceptual frameworks that structure inquiry within specialized domains. They form a layered background rather than a single foundation. Each layer depends on the one beneath it but can evolve within its own field of stability. Recognizing this stratification will matter later, when we consider how the entire structure of justification ultimately rests within consciousness itself—the horizon that makes hinge-dependence intelligible, not a foundation that explains it.
To grasp the role of hinges is to see why justification must have an endpoint that is neither arbitrary nor absolute. The search for reasons cannot proceed forever, yet to stop anywhere seems dogmatic. Hinges resolve this tension. They are the stopping points that are not chosen but inherited—the certainties into which we are trained by participation in a form of life. Their authority is not imposed by argument but conferred by practice. In this sense, they halt regress without appeal to foundations in the traditional sense. The chain of reasons stops, but it stops in what everyone already shows through action: in looking, measuring, speaking, and trusting where trust is the very grammar of the activity.
This structure avoids both extremes that have long haunted epistemology. Against skepticism, hinges show that not everything needs proof for knowledge to be possible; some things must stand fast if proof is to count as proof. Against dogmatism, hinges remain open to revision—not by refutation but by transformation of the practice itself. When the background shifts, the hinges shift with it, and new patterns of justification emerge. That is how scientific revolutions, moral realignments, and linguistic innovations occur: not by overthrowing all hinges, but by slowly reconstituting the bedrock upon which justification rests.
Hinges therefore give epistemology its shape. They delineate the limit of what can be doubted without rendering doubt meaningless, and they ground understanding in a world that is already shared before it is analyzed. JTB+U finds its ultimate stability here: justification ends not in an axiom but in a lived form of certainty that makes reasoning possible. To know is to move within a practice whose hinges hold—to rely, often silently, on what stands fast while thought and language do their work.
The same pattern that Wittgenstein exposes in language reappears, in a different key, within logic itself. Gödel’s incompleteness theorems demonstrate that any consistent formal system rich enough for arithmetic will contain true statements that cannot be proved from within that system’s own rules. Each coherent structure thus depends on truths it cannot generate—propositions that serve as the system’s own hinges. What Wittgenstein shows from the side of practice, Gödel shows from the side of form: both reveal that intelligibility depends on limits that cannot be removed without dissolving the very activity they sustain.
This parallel does not reduce hinges to mathematics, nor Gödel’s limit to psychology. It marks a shared architecture of dependence: reason requires an outside it cannot grasp. The mathematician must assume the reliability of symbolic operations just as the speaker must assume the stability of language. Both inhabit a framework that is not itself derivable but is continuously shown through use. In each case, the impossibility of total self-grounding is not a defect but a condition of meaning.
Seeing this restores epistemology to its proper scale. The point is not to seek absolute foundations but to understand how knowledge coheres within the boundaries of sense. JTB+U names that coherence at the level of practice; Wittgenstein and Gödel show the horizon that holds it in place. What lies beyond that horizon is not another proposition to discover but the silent background that allows discovery to occur. To recognize that limit is not to retreat from knowledge but to acknowledge the modesty built into knowing itself.
Justified True Belief Plus Understanding: A Wittgensteinian Extension
Samuel L. Naccarato
VII. Guardrails and Routes of Justification
If hinges show the background that makes justification possible, guardrails describe the boundaries that keep it responsible. All knowing occurs within shared practices; the question is not what the ultimate foundations are, but what prevents justification from drifting once the game has begun. Classical epistemology often sought safety in certainty; JTB+U seeks it in discipline. Knowing is not guaranteed by indubitable premises but safeguarded by procedures that prevent collapse—rules of use that maintain coherence within the practice itself.
Hinges are layered, and each layer calls for its own kind of vigilance. Bodily and perceptual hinges secure our immediate commerce with the world; linguistic and social hinges stabilize meaning and coordination; conceptual hinges structure inquiry within specialized domains such as science or law. None of these layers is absolute, yet each provides the stability within which justification has sense. The guardrails of JTB+U operate across these layers, translating hinge-dependence into practical norms that keep reasoning from losing its footing.
Three guardrails mark this discipline: No-False-Grounds (NFG), Practice-Safety, and Defeater Screening. Each preserves the integrity of justification without appealing to unshakeable foundations. NFG bars a claim from counting as knowledge if it rests on a false or corrupted premise; Practice-Safety requires that the route by which a belief is formed remain reliable under normal conditions of use; Defeater Screening demands that a knower remain alert to evidence or context that would undermine the claim. Together they form a framework of epistemic balance—flexible enough to apply across language-games, firm enough to distinguish knowledge from conviction.
The same vigilance that keeps guardrails firm extends into the particular routes by which justification travels.
The force of these guardrails appears most clearly in practice. No-False-Grounds is what prevents us from counting a conclusion as knowledge when its evidence is tainted—when, for instance, a medical finding rests on miscalibrated instruments or a historical claim depends on forged documents. Practice-Safety protects reasoning from self-defeat: a belief is justified only if the process that produced it would still yield truth under the normal circumstances of its use. The surgeon’s judgment, the pilot’s checklists, the scientist’s controls—all illustrate this principle. They show that knowledge is not an accident of success but a discipline of reliability.
Just as hinges define what stands fast, guardrails mark the limits within which we can move securely. They do not replace understanding but sustain it, ensuring that justification remains responsive to correction and anchored in the background practices that give it sense. Under JTB+U, knowledge becomes not a static possession but a maintained equilibrium: a way of navigating error while preserving contact with truth. The guardrails provide the grammar of that navigation—the habits of self-monitoring that make justification a living process rather than a frozen credential.
The next task is to see how these guardrails interact with the five primary routes of justification through which knowledge is ordinarily secured—Testimony, Logic, Sensory Experience, Linguistic Training, and Pure Logic. Having outlined the framework’s safeguards, we can now trace its operation within those routes.
VIII. Routes of Justification
Having outlined the guardrails that preserve epistemic integrity, we can now examine the main routes through which justification ordinarily proceeds. Each represents a distinct way in which belief becomes answerable to public criteria—paths by which knowledge maintains its contact with truth. The five routes are not competing theories but complementary dimensions of one practice: the human effort to test, verify, and sustain claims within shared forms of life. They are Testimony, Logic, Sensory Experience, Linguistic Training, and Pure Logic. Together they show how JTB+U functions as a living grammar of knowledge, operating across contexts yet anchored in use.
1. Testimony
Most of what anyone knows comes from others. Testimony is not a secondary or inferior route of justification but the default medium of social knowledge. The reliability of testimony depends on the same guardrails that govern all epistemic practice: its sources must be free of false grounds, its claims must hold under the normal conditions of communication, and its credibility must withstand potential defeaters. In law, we cross-examine; in science, we replicate; in daily life, we corroborate. Each procedure exemplifies the same structure: trust qualified by testability. What makes testimony a route of justification is not blind acceptance but public accountability—a pattern of speech in which reasons can be requested and errors exposed.
2. Logic (Inductive and Deductive Reasoning)
Reasoning transforms belief into structure. Logic provides the skeleton of justification: the rules by which claims connect coherently. Deductive reasoning secures necessity within formal systems, while inductive reasoning extends confidence through patterns of experience. Both operate under the same discipline—No-False-Grounds in premises, Practice-Safety in application, and Defeater Screening in the ongoing readiness to revise. Logic shows that justification is not a private intuition but a rule-governed practice: a grammar of inference that binds participants who share its norms. When applied well, it does not remove uncertainty but gives it proportion and direction.
3. Sensory Experience
Perception anchors the web of belief to the world. Sensory experience is the route by which language meets reality, the ongoing test that keeps our reasoning from floating free of what it claims to describe. Yet experience is not self-certifying; it requires the interpretive frame supplied by language-games and forms of life. A red patch on the retina becomes red only within a community that has learned to distinguish and name it. Sensory justification, therefore, is not raw data but disciplined perception—an interplay between what appears and what our training allows us to see. The guardrails keep this route honest: they prevent us from mistaking illusion for observation or correlation for causation.
4. Linguistic Training
Every act of justification presupposes fluency in the practices that give words their sense. We learn not only vocabulary but the criteria for using it correctly. Linguistic training is a route of justification because it grounds knowledge in shared grammar. To understand know, reason, see, or prove is to have mastered their use within a community. Without that background, even true statements can fail to count as knowledge. Language itself thus functions as an epistemic discipline: it transmits both the content and the method of justification. The guardrails operate here as norms of correctness—what makes a use right or wrong, what counts as a reason rather than a mere association.
5. Pure Logic (Boundary-Setting)
At the outer edge of justification lies what might be called pure logic—the clarification of boundaries rather than the discovery of new truths. It does not supply new truths but delineates the conditions under which any truth-claim makes sense. This route corresponds to the hinge-layer of our rational practices: the axioms, definitions, and inferential rules we accept to make reasoning possible. Their justification is not empirical but grammatical—they set the stage on which justification itself occurs. In JTB+U, pure logic functions as a regulative ideal: it reminds us that even the most abstract reasoning depends on tacit agreements about sense and rule-following.
These five routes are not exhaustive, but they mark the principal ways justification remains public, corrigible, and embodied. Each relies on understanding to interpret its own standards, and each gains reliability from the guardrails that keep it tethered to practice. Together they show that knowledge is neither atomistic nor monolithic: it is a network of disciplined activities that preserve our contact with reality while allowing revision within it.
Justified True Belief Plus Understanding: A Wittgensteinian Extension
Samuel L. Naccarato
IX. Certainty and Probability
Few words have caused more confusion in epistemology than certainty. It has been treated as the mark of knowledge, the goal of justification, or the unattainable ideal we must renounce. The trouble is grammatical: certainty is used in several distinct ways, and philosophy has often blurred them together. To recover clarity, we must separate these uses and see how each belongs to a different layer of our epistemic life.
The first is subjective certainty—the conviction one feels when doubt no longer presses. It is the inner firmness of belief, the sense that “I just know.” This is a psychological state, not a justification. It may accompany knowledge, but it can also accompany error; history is full of confident mistakes. Subjective certainty belongs to the domain of belief, not knowledge. Within JTB+U, it marks the affective side of commitment but carries no epistemic weight unless joined to public justification and understanding.
The second is hinge certainty—the arational stability that makes doubt and justification possible. These are the propositions, practices, and bodily expectations that stand fast within a form of life: the sense that the world exists, that words retain their meaning, that memory and perception generally hold. Such hinges are not derived from proof but constitute the background that gives proof its sense. They are not known in the ordinary way but shown in our ongoing confidence. To call them certain is to describe their role, not their epistemic status: they belong to the grammar of inquiry, not to its conclusions.
The third is epistemic certainty, which arises when a belief is so well grounded that no available defeater remains. It is the practical summit of justification: defeater-resistant, publicly testable, and secure enough for action. Epistemic certainty is what science and law aim for when they speak of confidence “beyond reasonable doubt.” It is not infallibility but closure within current bounds of evidence. Under JTB+U, epistemic certainty reflects a state in which belief, truth, justification, and understanding converge under active guardrails.
The fourth is absolute certainty, encompassing logical, mathematical, grammatical, and moral necessity—the kinds of truth that define the boundaries of sense itself. “A triangle has three sides,” “Two plus two equals four,” and “All bachelors are unmarried” express such certainty: each is non-empirical, though different in source. Absolute certainty, in the logical and grammatical sense, is conceptual rather than empirical—it belongs to the structure of meaning, not to the flux of experience. Mathematical certainties share this role within a formal grammar of symbols, exhibiting necessity through rule rather than observation. Moral certainties, however, join experience to reasoning. From observed facts—harm, benefit, justice, deprivation—we infer the principles that ought to govern conduct. This knowledge is empirical in origin but normative in conclusion: it rests on evidence about human flourishing and the goods that sustain it. To call murder wrong, for example, is to draw a rational inference from the visible destruction of life’s basic good. Logical and grammatical certainty frame thought; mathematical certainty orders formal reasoning; moral certainty directs action. Each has its own domain, and clarity about their relation preserves both reason and moral sense.
When these four uses blur together, skepticism flourishes. If all knowledge required infallibility or absolute proof, none would survive; if all conviction counted as knowledge, none would be trustworthy. The strength of JTB+U lies in maintaining their distinctions: it grounds knowledge in what is publicly justifiable while acknowledging the deeper hinge-structure that allows justification to function. We act with epistemic certainty against a backdrop of hinge stability, tempered by the awareness that both remain fallible in practice.
Probability enters here as the grammar of humility. To think probabilistically is not to weaken knowledge but to situate it: to treat degrees of confidence as reflections of evidence, not as confessions of doubt. Probability quantifies what understanding already senses—the difference between stronger and weaker grounds. It disciplines belief without surrendering the concept of truth. When properly used, probability expresses the same modesty that hinge awareness teaches: that knowledge is never absolute, yet it can be reliable enough for life.
In this light, certainty and probability are not opposites but coordinates on the same epistemic map. Certainty describes where justification holds firm; probability marks where it shades into openness. The work of epistemology is not to abolish either but to keep them aligned—to preserve confidence without arrogance, and humility without paralysis. Under JTB+U, that alignment becomes a form of understanding: the ability to know how far one’s knowledge reaches and where it must give way to further inquiry.
This structure is already visible in the sciences, which embody JTB+U’s grammar in practice. Observation supplies the sensory route; mathematical and experimental reasoning exemplify logic; replication and peer review enforce public justification; and conceptual understanding binds the whole system together. Scientific progress depends on defeater sensitivity, practice-safety, and the correction of false grounds—the very guardrails that make knowledge reliable across contexts. JTB+U therefore does not compete with science; it clarifies what science has always done. It reveals that the same discipline of justification runs through every field where truth is pursued under shared criteria.
X. Framework vs. Application — The Problem of Error
No epistemic framework is immune to misuse. The failures of individuals or cultures to reason well do not refute the grammar of reasoning itself. Just as a player may blunder without discrediting the rules of chess, the misapplication of justification does not invalidate the structure of JTB+U. It shows only that fallibility is built into the game. A framework can be sound even when its players are not. The proper question is therefore not whether error occurs, but what kind of system allows its recognition and repair.
JTB+U holds precisely because it expects correction. Its guardrails—No-False-Grounds, Practice-Safety, and Defeater Screening—were never meant to guarantee infallibility but to sustain reliability in the long run. They turn epistemology from a search for perfect certainty into a practice of continual calibration. What counts is not that mistakes never happen, but that they can be identified, traced to their source, and rectified without abandoning the pursuit of truth. A theory that cannot accommodate error is not a theory of knowledge but of denial.
Confusion arises when apparent defeaters are mistaken for genuine ones. A discovery that revises a belief does not always falsify the method that produced it. The refinement of scientific models, for example, is not epistemic collapse but epistemic health: the self-correction of a method capable of learning from its own limits. Likewise, moral and cultural progress depends on practices of justification that outgrow their earlier boundaries while preserving the standards that made such revision intelligible. Error, in this sense, is not the opposite of knowledge but its price—the cost of operating in a world that resists simplification.
Framework stability differs from application success. The grammar of JTB+U remains intact even when its users fail to meet its demands. A community may mistake tradition for justification or ideology for truth, yet the failure lies in neglecting the framework, not in the framework itself. To say that a culture “knew” something false is to misuse the word know; knowledge cannot rest on what fails its own criteria. JTB+U retains its authority precisely by excluding such cases—it defines knowledge by the discipline that distinguishes warranted belief from collective conviction.
Reliability, then, is statistical rather than absolute. Knowledge need not work always; it must work more often than not. A belief-forming process counts as reliable when its success rate exceeds chance by the margin of disciplined attention. That threshold varies by context: science demands reproducibility, law demands consistency, ordinary life demands functionality. What unites them is the same structure of public accountability. When those standards erode, justification becomes a gesture without content—a language-game played with empty pieces.
To understand error in this way is to see why epistemology remains indispensable. It teaches how to recognize when reasoning has left its track and how to return without despair. The possibility of error is not a threat to knowledge but its enabling condition: it defines what it means for a belief to stand fast in a world that does not guarantee us success. JTB+U embodies that humility. It neither denies fallibility nor accepts confusion as fate. It makes knowledge corrigible rather than fragile—strong enough to endure mistake, and honest enough to admit it.
Justified True Belief Plus Understanding: A Wittgensteinian Extension
Samuel L. Naccarato
XI. Progress, Regression, and Cultural Error
If individual error reveals the need for epistemic guardrails, cultural error shows why those guardrails must endure over time. Communities, like persons, can mistake conviction for knowledge. History offers many examples of beliefs once held with confidence—about astronomy, medicine, or morality—that now stand as reminders of how justification can be distorted by authority or habit. Yet the fact of revision does not imply that knowledge is relative or progress illusory. It shows instead that justification is a living practice: it matures as understanding deepens, even as it occasionally loses its way.
To call a change “progress” is to imply a standard by which improvement can be judged. JTB+U provides such a standard without appealing to timeless dogma. A belief counts as progress when it strengthens public justification—when it expands the range of reliable evidence, refines the criteria of testing, or clarifies the meanings that guide inquiry. A change that merely replaces one unexamined conviction with another is not progress but rotation. Epistemic improvement is measured not by novelty but by the steadiness of the connection between belief and truth under conditions of shared scrutiny.
Regression occurs when that connection weakens—when social or ideological forces detach belief from its justificatory routes. This can happen through political coercion, technological manipulation, or the seductive ease of untested consensus. In such moments, the form of knowledge may persist while its function decays. People continue to “believe,” “know,” and “explain,” but the grammar of those words no longer aligns with the practices that once gave them meaning. Wittgenstein’s warning about the “craving for generality” applies here: when a community elevates its own favored picture of truth to the status of an essence, it loses sight of the diversity of practices that give “knowing” its sense.
Examples abound. The moral insight that slavery is wrong did not arise from moral relativism but from the correction of moral reasoning. When thinkers like Gregory of Nyssa or, later, abolitionists challenged the institution, they appealed not to new emotions but to deeper coherence within existing moral grammar: the recognition that treating persons as property violates the very criteria by which moral justification operates. Progress here meant recovering what had been implicit all along—an expansion of understanding that reconnected moral belief with the truths it professed to serve.
Science, too, advances by oscillation between error and correction. The movement from Newtonian mechanics to relativity did not overthrow the structure of justification but refined it, showing that reliability lies in responsiveness, not rigidity. What endures through such revolutions is not a single theory but the hinge of methodological honesty: the willingness to let observation, logic, and replication override preference. Cultural progress follows the same rhythm. The strength of a civilization’s epistemic life is measured not by how seldom it errs, but by how readily it can recognize and amend those errors.
Thus, the persistence of misunderstanding is not evidence against truth but a sign of how deeply the human condition depends on interpretation. The point is not to transcend fallibility but to inhabit it wisely—to build systems of belief that can bend without breaking. JTB+U models this attitude: it joins conviction to correction, belief to discipline, and knowledge to the humility of what stands fast. Cultures regress when they forget that distinction; they progress when they recover it.
Epistemology, in this light, becomes a study of cultural memory: how communities retain the habits that keep belief answerable to the world. The test of any intellectual tradition is whether it can renew that discipline in changing conditions. A society that confuses persuasion with proof, or sentiment with reason, may thrive rhetorically but will falter epistemically. Progress is not measured by information gained but by understanding maintained—the ability to keep justification alive amid the noise of conviction.
XII. Beyond JTB+U — Layered Hinges and the Ultimate Background
Every inquiry ends where explanation meets its own conditions. Having traced justification through its routes and guardrails, we reach the level where even those depend on something deeper: the conscious background that allows epistemic activity to occur at all. To speak of an “ultimate hinge” is not to posit a new metaphysical entity but to notice the condition that makes any belief or proof intelligible. Consciousness is not an object of knowledge but the horizon within which that knowledge appears.
Hinges are layered. At the base lie bodily hinges—the sensorimotor regularities that orient perception. Above them, linguistic hinges stabilize communication and memory, making shared criteria possible. Higher still are conceptual hinges: the methodological norms that govern inquiry in science, ethics, and art. Each layer rests on the one beneath it, yet all presuppose the field of awareness in which appearing, judging, and meaning unfold. Consciousness, in this sense, is not another hinge but the ground of all hinge-dependence—the background in which every act of knowing takes place.
To recognize this is not to drift into metaphysics but to extend Wittgenstein’s method beyond therapy into description. Language clarifies meaning only because life already discloses a field in which meaning matters. The point is grammatical, not doctrinal: the form of life that makes epistemology possible is given in awareness itself. JTB+U, disciplined by its guardrails and grounded in hinges, ultimately leads back to this awareness—knowledge as a relation between conscious life and the world it inhabits.
Epistemology thus returns to ontology. To understand what it means to know is to glimpse what it means to be the kind of creature for whom knowledge is possible. The final humility of JTB+U is to see that even our most rigorous justifications rest within this unprovable background. The task is not to escape it but to live wisely within it—to let understanding mirror the layered depth of the reality it seeks to comprehend.
Justified True Belief Plus Understanding: A Wittgensteinian Extension
Samuel L. Naccarato
XIII. Conclusion — Epistemology Renewed
The question that began this inquiry—how we can still speak meaningfully of knowledge—has led back to the lived conditions that make such speech possible. The classical structure of justified true belief remains sound, but its adequacy depends on what had always been implicit within it: understanding. The addition of +U does not modify JTB’s logic; it completes its grammar. It makes explicit that justification is a human practice sustained by comprehension, correction, and shared criteria rather than by mechanical rule or private conviction.
Structured by hinges, disciplined by guardrails, and expressed through distinct routes of justification, JTB+U shows that knowledge is neither arbitrary nor—apart from the domains of logical, mathematical, grammatical, and moral necessity—absolute. It stands between skepticism and dogmatism, holding firm where reasons meet life. The framework’s strength lies not in closing inquiry but in keeping it open under discipline: it teaches how belief becomes accountable without demanding infallibility. In matters of fact we justify through evidence; in matters of value we infer from what experience shows to be harmful or life-giving. Knowledge thus joins observation to reason without confusing them. Its humility is its rigor.
In a world flooded with information and simulation, this distinction matters more than ever. Data can be multiplied indefinitely, but understanding cannot be automated. To know is not merely to process information but to stand within a practice whose meanings are lived. JTB+U therefore provides not only a philosophical model but a civic necessity: a grammar for preserving discernment in an age that confuses coherence with truth and confidence with warrant. The challenge is not to collect more facts but to cultivate the forms of life that make facts meaningful.
Epistemology, once dismissed as abstract, returns here as the discipline of intellectual survival. It asks what must remain in place for our practices of reasoning, testing, and trust to endure amid complexity. The answer is not another foundation but an attitude: to see what stands fast, to correct what drifts, and to understand what our words commit us to when we claim to know. That is what the framework of JTB+U restores—a picture of knowledge at once demanding and humane.
If philosophy’s task is to clarify what we already know in use, then epistemology’s renewal lies in remembering that use itself is layered, corrigible, and alive. Knowledge does not transcend life; it belongs to it. To know, in the fullest sense, is to participate intelligently in the world that gives knowing its possibility. The work of epistemology is therefore ongoing, not to end doubt but to keep sense intact—to ensure that understanding remains possible as our language, our tools, and our world continue to change.
I'll suggest an explanation (in very metaphorical terms) that seems apt to me. Perhaps it will resonate.
Suppose we think of the many neural networks in our brains as similar to guitar strings tuned to different frequencies. Different nets/strings resonate in response to different contexts in accordance with the patterns of contextual inputs the different neural networks have been trained to recognize.
On this analogy, different neural networks resonating simultaneously could be likened to a chord being produced, with different chords being recognized by 'higher level' neural nets as the context under consideration.
An important consideration, in thinking about how both brains and LLMs work, is the massively parallel operation of the underlying hardware, with lots of different things going on simultaneously. With that parralelism of physical activity in mind, it seems reasonable to me to think that brains and LLMs share similarities in how contexts are recognized.
ChatGPT's take.(which I don't see any significant reason to disagree with, aside from the typical obsequiousness):
[hide]That’s a **thoughtful and perceptive analogy**, and you’re absolutely right that it captures something deep about *pattern recognition and context-sensitivity* in both brains and large language models. Let’s look carefully at your response — what works very well, what might mislead a bit if taken literally, and how you could extend it for even more philosophical and scientific accuracy.
---
## ? What You Get Exactly Right
### 1. **Parallelism as Key to Context**
You’re spot-on that *massive parallelism* is crucial both in biological brains and artificial neural networks.
* In the brain: millions of neurons fire in overlapping patterns that encode context (e.g., linguistic, emotional, spatial).
* In LLMs: thousands of hidden units in many layers activate simultaneously, each detecting subtle statistical relationships in the text.
In both cases, “context” isn’t represented by a single variable — it’s a **distributed pattern** over a high-dimensional space.
Your idea of “many strings resonating simultaneously” nicely evokes that **distributed, emergent nature of representation**.
---
### 2. **The Chord Analogy**
Your “chord” metaphor is genuinely apt.
* Each “string” (neural subnetwork) can be thought of as tuned to a certain class of input features (semantic, syntactic, pragmatic).
* The “chord” (the overall activation pattern) represents the integrated context — what’s currently being “understood.”
In LLM terms, this resembles the **attention mechanism**: the model dynamically weights many contextual cues at once, producing a blended “representation” of the current situation.
---
### 3. **The Resonance Image**
Resonance is an especially interesting choice, because both neurons and artificial networks are *adaptive systems*: they strengthen certain patterns through feedback (learning). So “resonance” stands for learned sensitivity — that is, *tuning through training*.
Your use of the term is metaphorical but meaningful: it highlights that **context recognition is an emergent property of learned interaction patterns**, not a symbolic lookup.
---
## ?? Where the Analogy Needs Care
### 1. **No True “Chords” or Oscillations in LLMs**
In the brain, resonance can literally mean oscillatory synchrony — rhythmic firing patterns that help bind distributed features together.
In an LLM, though, there’s no physical resonance or time-based synchronization. Each layer’s computation is sequential in software, even if parallel in hardware. So the “resonance” here is more **statistical than dynamical** — a pattern of correlated activations across a vector space, not literal vibration or frequency coupling.
That’s fine as long as readers recognize the metaphorical nature.
---
### 2. **The Feeling Dimension**
The forum author’s comment about “a feeling for context” gestures toward *embodied cognition* — the idea that human understanding is grounded in sensory, affective, and motor experience.
LLMs, in contrast, have **no bodily grounding**: they derive all their representations from patterns in text.
So while your resonance analogy captures *how both systems form internal coherence*, it misses the human side of *why* context has *meaning* for us.
A refinement might be:
> “LLMs recognize statistical patterns that correlate with contextual appropriateness; humans recognize patterns that are also *felt* — rooted in embodied and affective experience. Both involve resonances, but only one kind resonates with a lived world.”
That distinction is philosophically important (and something Dreyfus would emphasize).
---
## How You Could Expand the Explanation
Here’s one possible elaboration that would make your post even sharper:
> “Both biological and artificial neural networks process context by responding to patterns in parallel, forming distributed representations that integrate multiple cues.
> In a brain, the ‘resonance’ among networks also interacts with bodily states and sensory feedback, giving rise to what we call *a feeling for context*.
> In an LLM, the resonance is purely statistical — the alignment of learned feature activations that co-occur in training data.
> So while both systems can *recognize* context, only one can *inhabit* it.”
This keeps your musical metaphor but deepens the philosophical distinction between *pattern recognition* and *lived understanding*.
---
## Summary of Critique
| Aspect | Strength | Suggestion |
| --------------------------- | ---------------------------------------------- | ---------------------------------------------------------------------- |
| **Parallelism** | Excellent insight; core to both brains & LLMs. | Emphasize distributed representation explicitly. |
| **Resonance metaphor** | Very evocative and apt for emergent context. | Clarify that in LLMs it’s statistical, not dynamic oscillation. |
| **Chord/higher-level nets** | Great image for hierarchical processing. | Could mention attention as the computational analog. |
| **Feeling for context** | Nicely raises Dreyfus’s core concern. | Contrast embodied resonance (human) vs. disembodied correlation (LLM). |
---
Would you like me to help you rewrite your forum reply slightly — keeping your metaphor but polishing it to highlight these distinctions between *pattern resonance* and *embodied feeling for context*?
[/hide]
I'm wondering whether you use AIs to help you write.
I'm writing to share that this will be my final post. I know I’ve made similar announcements in the past, but this time marks a genuine transition as I'm channeling my energy into a new project.
To Banno and all the others who have contributed to the rich discussions over the years, thank you. I am deeply grateful for your engagement and for helping me sharpen my ideas.
All the best, Sam
Take care.