Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Erdos 281 solved with ChatGPT 5.2 Pro

twitter.com

Post reply on HN
Print view View original

261–270 of 310 posts

Re: Erdos 281 solved with ChatGPT 5.2 Pro

#261

Post by fweimer »

Workaccount2 wrote: post #251
fweimer wrote: post #210

Earlier quoted context omitted.

I saw weird results with Gemini 2.5 Pro when I asked it to provide concrete source code examples matching certain criteria, and to quote the source code it found verbatim. It said it in its response quoted the sources verbatim, but that wasn't true at all—they had been rewritten, still in the style of the project it was quoting from, but otherwise quite different, and without a match in the Git history. It looked a b…

LLM's are not archives of information. People seem to have this belief, or perhaps just general intuition, that LLMs are a google search on a training set with a fancy language engine on the front end. That's not what they are. The models (almost) self avoid copyright, because they never copy anything in the first place, hence why the model is a dense web of weight connections rather than an orderly bookshelf of copi…

For a task like this, I expect the tool to use web searches and sift through the results, similar to what a human would do. Based on progress indicators shown during the process, this is what happens. It's not an offline synthesis purely from training data, something you would get from running a model locally. (At least if we can believe the progress indicators, but who knows.)

Re: Erdos 281 solved with ChatGPT 5.2 Pro

#262

Post by NewsaHackO »

glemion43 wrote: post #156
rzmmm wrote: post #102

Earlier quoted context omitted.

The model has multiple layers of mechanisms to prevent carbon copy output of the training data.

Do you have a source for this? Carbon copy would mean over fitting

It is the classic "He made it up"

Re: Erdos 281 solved with ChatGPT 5.2 Pro

#263

Post by _fizz_buzz_ »

nddkdkfk wrote: post #209
heliumtera wrote: post #201

Earlier quoted context omitted.

Don't feel bad for being out of the loop. The author and Tao did not care enough about erdos problem to realize the proof was published by erdos himself. So you never cared enough and neither did they. But they care about about screaming LLMs breakthrough on fediverse and twitter.

This Tao dude, does he get invited to a lot of AI conferences (accommodation included)?

I know someone who organized a conference where he spoke (this was before the AI boom, probably around 2018 or so) and he got very good accommodations and also a very generous speaking fee.

Re: Erdos 281 solved with ChatGPT 5.2 Pro

#264

Post by furyofantares »

threethirtytwo wrote: post #88
furyofantares wrote: post #79

Earlier quoted context omitted.

The problem is more that it's an LLM-generated comment that's about 20x as long as it needed to be to get the point across.

It's not. Evidence shows otherwise: Despite the "20x" length, many people actually missed the point.

Oh yeah, there is also a problem with people not noticing they're reading LLM output, AND with people missing sarcasm on here. Actually, I'm OK with people missing sarcasm on here - I have plenty of places to go for sarcasm and wit and it's actually kind of nice to have a place where most posts are sincere, even if that sets people up to miss it when posts are sarcastic.

Which is also what makes it problematic that you're lying about your LLM use. I would honestly love to know your prompt and how you iterated on the post, how much you put into it and how much you edited or iterated. Although pretending there was no LLM involved at all is rather disappointing.

Unfortunately I think you might feel backed into a corner now that you've insisted otherwise but it's a genuinely interesting thing here that I wish you'd elaborate on.

Re: Erdos 281 solved with ChatGPT 5.2 Pro

#266

Post by Coeur »

Eufrat wrote: post #162

There was a post about Erdős 728 being solved with Harmonic’s Aristotle a little over a week ago [1] and that seemed like a good example of using state-of-the-art AI tech to help increase velocity in this space. I’m not sure what this proves. I dumped a question into ChatGPT 5.2 and it produced a correct response after almost an hour [2]? Okay? Is it repeatable? Why did it come up with this solution? How did it come…

Also #124 was proved using AI 49 days ago: https://news.ycombinator.com/item?id=46094037

Re: Erdos 281 solved with ChatGPT 5.2 Pro

#267

Post by glemion43 »

danielbln wrote: post #169
glemion43 wrote: post #158

Earlier quoted context omitted.

It shows that a 'llm' can now work on issues like this today and tomorrow it can do even more. Don't be so ignorant. A few years ago NO ONE could have come up with something so generic as an LLM which will help you to solve this kind of problems and also create text adventures and java code.

The goal posts are strapped to skateboards these days, and the WD40 is applied to the wheels generously.

I don't get your pessimism...

Nothing of it was even imaginable and yes the progress is crazy fast.

How can you be so dismissive?

Re: Erdos 281 solved with ChatGPT 5.2 Pro

#268

Post by danielbln »

glemion43 wrote: post #267
danielbln wrote: post #169

Earlier quoted context omitted.

The goal posts are strapped to skateboards these days, and the WD40 is applied to the wheels generously.

I don't get your pessimism... Nothing of it was even imaginable and yes the progress is crazy fast. How can you be so dismissive?

You misread my comment.

Re: Erdos 281 solved with ChatGPT 5.2 Pro

#269

Post by mmooss »

CamperBob2 wrote: post #257
habinero wrote: post #252

Earlier quoted context omitted.

No, they searched for it. There's a lot of math literature out there, not even an expert is going to know all of it.

Point being, it's not the same proof.

Your point seemed to be, if Tao et al. haven't heard of it then it must not exist. The now known literature proof contradicts that claim.

Re: Erdos 281 solved with ChatGPT 5.2 Pro

#270

Post by mmooss »

glemion43 wrote: post #259
mmooss wrote: post #218

Earlier quoted context omitted.

What is "latent space"? I'm wary of metamagical descriptions of technology that's in a hype cycle.

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?

Post reply on HN