Erdos 281 solved with ChatGPT 5.2 Pro

Post by cubefox » Sun, Jan 18, 2026, 8:32 PM UTC

cwnyth wrote: post #258

cubefox wrote: post #243

Earlier quoted context omitted.

"You replied by saying "So what? There are probably also many cases where seemingly useless science became useful later." You seemed to be treating the latter as if it negated the former" No, "so what" doesn't indicate disagreement, just that something isn't relevant. Anyway, assume hot dogs taste not good at all, except in rare circumstances. It would then be wrong to say "hot dogs taste good", but it would be right…

It really speaks to the weakness of your original claim that you're applying this level of sophistry to your backpedaling.

Post by Ar-Curunir » Sun, Jan 18, 2026, 8:53 PM UTC

drob518 wrote: post #202

cubefox wrote: post #144

Earlier quoted context omitted.

The difference is that Claude Code actually solves practical problems, but pure (as opposed to applied ) mathematics doesn't. Moreover, a lot of pure mathematics seems to be not just useless, but also without intrinsic epistemic value, unlike science. See https://news.ycombinator.com/item?id=46510353

I’m an engineer, not a mathematician, so I definitely appreciate applied math more than I do abstract math. That said, that’s my personal preference and one of the reasons that I became an engineer and not a mathematician. Working on nothing but theory would bore me to tears. But I appreciate that other people really love that and can approach pure math and see the beauty. And thank God that those people exist becaus…

Post by pfdietz » Sun, Jan 18, 2026, 9:06 PM UTC

mlpoknbji wrote: post #221

pfdietz wrote: post #205

Earlier quoted context omitted.

They're finding them very effective at literature search, and at autoformalization of human-written proofs. Pretty soon, this is going to mean the entire historical math literature will be formalized (or, in some cases, found to be in error). Consider the implications of that for training theorem provers.

I think "pretty soon" is a serious overstatement. This does not take into account the difficulty in formalizing definitions and theorem statements. This cannot be done autonomously (or, it can, but there will be serious errors) since there is no way to formalize the "text to lean" process. What's more, there's almost surely going to turn out to be a large amount of human generated mathematics that's "basically" corre…

Post by TZubiri » Sun, Jan 18, 2026, 9:24 PM UTC

mikaraento wrote: post #143

TZubiri wrote: post #118

Earlier quoted context omitted.

forgive the skepticism, but this translates directly to "we asked the model pretty please not to do it in the system prompt"

That might be somewhat ungenerous unless you have more detail to provide. I know that at least some LLM products explicitly check output for similarity to training data to prevent direct reproduction.

Post by glemion43 » Sun, Jan 18, 2026, 10:09 PM UTC

mmooss wrote: post #270

glemion43 wrote: post #259

Earlier quoted context omitted.

I'm disappointed that you had to add the 'metamagical' to your question tbh It doesn't matter if ai is in a hype cycle or not it doesn't change how a technology works. Check out the yt videos from 1blue3brown he explains LLMs quite well. .your first step is the word embedding this vector space represents the relationship between words. Father - grandfather. The vector which makes a father a grandfather is the same ve…

> It doesn't matter if ai is in a hype cycle or not it doesn't change how a technology works. It does change what people say about it. Our words are not reality itself; the map is not the territory. Are you saying people should take everything said about LLMs at face value?