You are viewing the historical archive of The Philosophy Forum.
For current discussions, visit the live forum.
Go to live forum

Pierre-Normand

Comments

Getting a conversation started with GPT4 regarding its tokenizer, its multilingual abilities, Fodor's LOT thesis and the Sapir-Whorf hypothesis. Hi GP...
April 03, 2023 at 11:57
It's not. To be clear, I was claiming that GPT4's abilities to think in any language didn't count as evidence against the hypothesis. The hypothesis a...
April 03, 2023 at 11:20
Discussing an issue surrounding alignment and consistency with GPT4, who offers some insights regarding the future of AI system development and the co...
April 03, 2023 at 11:13
Hi Jamal! I apologize for leaving you hanging for so long. My primary aim in this conversation (as well as many others) was to examine GPT-4's intelli...
April 03, 2023 at 10:16
This is fascinating. While thinking about GPT4's multilingual abilities, and its ability to synthesize knowledge that is represented in its training d...
April 03, 2023 at 09:41
Testing GPT4's understanding of Gödel's incompleteness theorems. GPT4 again passes the Turing Test with flying colors. (Thanks to my friend Michel V. ...
April 03, 2023 at 09:24
Aiming to tap more systematically into GPT-4's emergent reflexive abilities for purpose of self-monitoring. (An approach inspired by the recent paper ...
April 03, 2023 at 05:16
Thank you for providing this example, and for reminding me of the hide-and-reveal feature of this forum! I should re-edit some of my older and longer ...
April 03, 2023 at 02:27
Making use of GPT4 as a time-travel machine and visiting ancient Rome circa 50 BC. Part 1 (In subsequent part, I intend to modify the method in order ...
April 02, 2023 at 10:02
Having GPT4 summarise the subtitle file from a long YouTube video, mindful of its limited attention window, and then having it reflect back on the tas...
April 02, 2023 at 09:41
This was a nice discussion. I enjoyed the songs it wrote, especially the bit: "Some may say I'm just a machine, a tool to be used, But I like to think...
April 02, 2023 at 07:42
GPT-4 is much better, that's for sure. There are specific conditions, and specific topics (mainly those that it is insufficiently trained on), that wi...
April 02, 2023 at 07:30
Breakthrough in the 'palindrome project' - Teaching/learning how to spell words backwards with GPT4: a machine with a brain that only processes tokens...
April 01, 2023 at 11:06
Hi Benkey, Reading your whole conversation with ChatGPT, I must say that the bot is way better than I had remembered it to be. I hadn't used it for lo...
April 01, 2023 at 06:42
How does GPT-4 knows that it is GPT-4? And, does it really know it? (Overcoming skeptical worries, part - 1) PN: Hi old pal! GPT-4: Hello! It's great ...
April 01, 2023 at 06:19
Do you access it though a ChatGPT Plus subscription? You must select the model from the drop-down list on each new session (dialogue) before beginning...
March 31, 2023 at 10:39
Wonderful! I must go to bed now. I'll be back in 20-24 hours and edit this message to comment. Did you really have this conversation with ChatGPT (bas...
March 31, 2023 at 10:30
Probing GPT4's creative skills with mathematical poetry. (This was inspired by an example in the recent Sparks of Arti ficial General Intelligence pap...
March 31, 2023 at 10:06
Unruly schoolkid sitting in nerdy Professor GPT4's classroom. (Also demonstrating GPT4's ability to push back against incorrect information when promp...
March 31, 2023 at 08:36
@"Benkei" Engaging in philosophical discussion with GPT-4 (explanatory-levels, emergence, AI phenomenology and operational definitions) Hi GPT4! Consi...
March 30, 2023 at 09:11
I discussed with GPT4 the topic of its attention window and the nature of the signification units that it contains. I don't think it's a form of perce...
March 29, 2023 at 16:28
It had been brought to my attention by a friend of mine a few hours ago. The proposal seems reasonable to me. The potential dangers and disruptive aff...
March 29, 2023 at 16:13
A super duper easy way to exploit the hitherto untapped cognitive abilities of large language models like GPT4 Hello GPT4! Here is the abstract of a r...
March 29, 2023 at 11:07
Hi @"Benkei", nice talking to you again! I think GPT4's (as well as ChatGPT's) bias is a consequence of the late stages of its human-supervised traini...
March 29, 2023 at 10:01
Pursuing research, as well as some musings on philosophical behaviorism, with a recovering AI Alzheimer patient PN: I'd now like to submit to you an e...
March 29, 2023 at 08:46
Playing a game with GPT4 and witnessing it morphing from brilliant research assistant to Alzheimer patient. Hi GPT4! You wouldn't happen to know how m...
March 29, 2023 at 06:58
Thanks for that! It's fascinating. It will be interesting, as the author notes, to see those results replicated with GPT-4, which has a significantly ...
March 29, 2023 at 02:01
Pushing GPT4 to its limits and exploring the source of its blind spots. Hi GPT4, I think you may be familiar with a class of logical puzzles or riddle...
March 29, 2023 at 01:55
During a fleeting moment, GPT-4 slips up and seems to think of itself as a human being. PN: Before too much of the present discussion slips outside of...
March 29, 2023 at 00:09
Discussing with GPT4 its difficulty with processing word components, and guiding it towards potential solutions. PN: In addition to the need for craft...
March 28, 2023 at 23:29
Thank you @"Banno", for this very relevant reference. Especially useful are the following remarks: "The training data for ChatGPT-4 includes huge numb...
March 28, 2023 at 22:07
Another fun tidbit. GPT4 gets creative and then immediately morphes back into Eliza GPT4: This prompt directly instructs me to reverse the words and l...
March 28, 2023 at 05:55
I tried to trick GPT4 and it didn't fall for it. While assuming its default personality, it doesn't have a sense of its own finitude, not even a facti...
March 28, 2023 at 00:31
GPT4 provides remarkable insight into the source of its own errors and then manifests a case of cognitive overload. The bot provides insight into this...
March 27, 2023 at 23:27
Showcasing again GPT4's astounding ability to solve problems while being directed to do so in very abstract and non-directive terms. PN: This is good....
March 27, 2023 at 19:36
Follow up discussion with GPT4 regarding the meaning of "I" PN: This still is not quite right but the mistakes you are making are instructive. I think...
March 27, 2023 at 06:51
Actually, upon rereading GPT4's latest response in the previous post I see that it still didn't get it quite right. The issue wasn't anything inherent...
March 27, 2023 at 06:27
Another striking example of GPT4's ability to reassess its judgements when prompted to do so with minimal human guidance. PN: I think this is a fairly...
March 27, 2023 at 06:08
GPT4's ability to gracefully recover from episodes of hallucination. (Continuation of the dialogue in the previous post) PN: Now that we have broadly ...
March 27, 2023 at 05:38
Probing the source of GPT4's self-identification ability (which led to some hallucination likely triggered by the fact that GPT4 had painted itself in...
March 27, 2023 at 05:10
I had some doubts whether I might not have confused this book with "La nature dans la physique contemporaine", which has also rested on a shelf for de...
March 27, 2023 at 05:06
I'm not sure but, as a teen I had read Heisenberg's intellectual autobiography "Der Teil und das Ganze," (in the French translation "La partie et le t...
March 27, 2023 at 04:30
I am not sure what the source of those tidbits of self-knowledge are, though. Maybe the correct responses regarding self-identification have been rein...
March 27, 2023 at 04:16
@"T Clark" For the sake of comparison, I also ran the same two questions by GPT-3.5, except I lied to it regarding the source of the original interact...
March 27, 2023 at 03:41
@"T Clark", I inquired with GPT4 regarding your interaction with (I presumed) GPT-3.5. Here is the result. PN: Hi GPT4, For context, a friend of mine ...
March 27, 2023 at 03:30
You haven't tried GPT4 yet, have you? There is a considerable (in some cases massive) improvement from GPT-3.5 (ChatGPT) to GPT4 regarding their knowl...
March 27, 2023 at 03:06
GPT4 comes down to earth. I asked GPT4 to produce a new version of the summary of our latest conversation that is less jargony and more likely to be u...
March 26, 2023 at 15:57
Exploring external cognitive enhancers and implicit self-monitoring abilities as means to develop meta-cognitive strategies that GPT4 could be prompte...
March 26, 2023 at 15:51
Yes another cool tidbit exemplifying how AI language models might soon be able to become self-scientific-investigators, self-design-improvers and self...
March 26, 2023 at 13:56
Rather that supplying another long transcript, I'm going to let GPT4 offer a short progress report from its own POV. PN: Could you produce a significa...
March 26, 2023 at 13:36