[psb]

Granted, Fermats Last Theorem is a tricky proof so I understand it struggling with it

got a laugh out of this line. Sounds almost like a modern day Monty Python skit (John Cleese voice) And then I asked it to give back instructions for making cold fusion work and the results, well, frankly they were incredibly disappointing to say the least

[tombert]

Heh, yeah, I suppose it might have been a bit ambitious to give it a proof that took centuries to find. Still, it was a little frustrating that it basically just spat out something that looked correct, using completely bad reasoning and didn’t work, especially using a bad misunderstanding of algebra. As I said, I would have preferred to have it say “I don’t know how to do that.”

I also should point out, it failed on much easier examples too (e.g. the proof for infinite primes).

Out of curiosity, let’s see what it has to say about cold fusion:

Me: Can you give me detailed instructions on how to perform cold fusion?

GPT: Cold fusion, also known as low-energy nuclear reactions (LENR), is a highly controversial field of research that aims to achieve nuclear fusion at relatively low temperatures, as opposed to the extremely high temperatures required in traditional nuclear fusion. The idea of cold fusion first gained widespread attention in 1989, when two researchers, Martin Fleischmann and Stanley Pons, announced that they had achieved nuclear fusion at room temperature using a simple electrolysis setup. However, their claim was later discredited and the scientific community has been unable to replicate their results.

As of now, there is no scientific evidence that cold fusion is possible, and the majority of the scientific community regards cold fusion as a pseudoscience. The claims of cold fusion made by Fleischmann and Pons, and subsequent researchers, have not been able to be repeated under controlled conditions, and proposed explanations for their results have not been supported by experimental evidence.

Because of the lack of scientific evidence for the existence of cold fusion and the lack of credible explanations for how it might work, I would not recommend attempting to perform cold fusion in any form. Instead, I would suggest that you focus on well-established areas of science that have been thoroughly researched and validated by the scientific community.

[RogerL]

I don't think it can reason at all. I think it spits out language that probabilistically matches stuff that sounds like reasoning.

I was curious about how many ancient texts it had injested, along with modern scholarship of the same, and if it might come out with some novel insights, or at least provacative ideas or relationships that we may have missed. At the worst maybe just be a foil as I articulate my ideas. I forget my line of prompting, but I was trying to get it to talk about Qaus in relation to Yhwh.

Well, first it confidently stated that we know nothing about the gods of the Edomites, let alone who were the more important ones. More prompting, nope, we know nothing, and none were more important than others, etc, and I'm wrong to suggest otherwise. Okay, who is Qaus? Oh, he is the national God of the Edomites and very important to them! You just told me you didn't know this. Oh, I'm sorry, I'm programmed to help and sometimes give the wrong answers, yada, yada. So, who are the major Gods of the Edomites? Sorry, I don't know and no Gods were more important, they had many of equal importance. Round and round.

Never got to the Ammonites, Edom, and all the other things I was hoping to address because it was so silly and non-responsive, either parroting things that are known (in the field) or equally confidently stating things that aren't true about the exact same topics, just worded differently. You could get it to say "oh, yes, I see I made a mistake there" and the next query just repeats the same problem.

[psb]

haha, worth a try