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

OpenAI claims gold-medal performance at IMO 2025

twitter.com

Post reply on HN
Print view View original

571–580 of 737 posts

Re: OpenAI claims gold-medal performance at IMO 2025

#571

Post by saagarjha »

samat wrote: post #176
saagarjha wrote: post #40

Earlier quoted context omitted.

I did competitive math in high school and I can confidently say that they are anything but "basic". I definitely can't solve them now (as an adult) and it's likely I never will. The same is true for most people, including people who actually pursued math in college (I didn't). I'm not going to be the next guy who unknowingly challenges a Putnam winner to do these but I will just say that it is unlikely that someone w…

Thanks for speaking sense. I think 99% of people saying IMO problems are not hard would not be able to solve basic district-level competition problems and are just not equipped to judge the problems. And 1% here are those IMO/IOI winners who think everyone is just like them. I grew up with them and to you, my friends, I say: this is the reason why AI would not take over the world (and might even not be that useful fo…

I feel like people see the question (or even the solution), they can actually understand what it says because it’s only using basic algebraic notation, then assume it must be easy to solve. Obviously it must be easier than that funny math with weird symbols…

Re: OpenAI claims gold-medal performance at IMO 2025

#572

Post by BoorishBears »

signatoremo wrote: post #268
AIPedant wrote: post #41

Earlier quoted context omitted.

It almost certainly is specialized to IMO problems, look at the way it is answering the questions: https://xcancel.com/alexwei_/status/1946477742855532918 E.g here: https://pbs.twimg.com/media/GwLtrPeWIAUMDYI.png?name=orig Frankly it looks to me like it's using an AlphaProof style system, going between natural language and Lean/etc. Of course OpenAI will not tell us any of this.

Why is "almost certainly"? The link you provided has this to say: > 5/N Besides the result itself, I am excited about our approach: We reach this capability level not via narrow, task-specific methodology, but by breaking new ground in general-purpose reinforcement learning and test-time compute scaling.

Also from the thread:

> 8/N Btw, we are releasing GPT-5 soon, and we’re excited for you to try it. But just to be clear: the IMO gold LLM is an experimental research model.

And from Sam Altman:

> we are releasing GPT-5 soon but want to set accurate expectations: this is an experimental model that incorporates new research techniques we will use in future models.

The wording you quoted is very tricky: the method used to create the model is generalizable, but the model is not a general-use model.

If I have a post-training method that allows a model excel at a narrow task, it's still a generalizable method if there's a wide range of narrow tasks that it works on.

Re: OpenAI claims gold-medal performance at IMO 2025

#573

Post by torginus »

dylanbyte wrote: post #16

These are high school level only in the sense of assumed background knowledge, they are extremely difficult. Professional mathematicians would not get this level of performance, unless they have a background in IMO themselves. This doesn’t mean that the model is better than them in math, just that mathematicians specialize in extending the frontier of math. The answers are not in the training data. This is not a mode…

From my vague rememberance of doing data science years ago, it's very hard not to leak the training set.

Basically how you do RL is that you make a set of training examples of input-output pairs, and set aside a smaller validation set, which you never train on, to check if your model's doing well.

What you do is you tweak the architecture and the training set until it does well on the validation set. By doing so, you inadvertedly leak info about the training set. Perhaps you choose an architecture which does well on the validation set. Perhaps you train more on examples more like ones being validated.

Even without the explicit intent to cheat, it's very hard to avoid this contamination, if you chose a different validation set, you'd end up with a different model.

Re: OpenAI claims gold-medal performance at IMO 2025

#574

Post by cycomanic »

logicchains wrote: post #533
bamboozled wrote: post #519

Earlier quoted context omitted.

I’ve used these AI tools for multiple hours a day for months. Not seeing the reasoning party honestly. I see the heuristics part.

I guess your work doesn't involve any maths then, because then you'd see they're capable of solving maths problems that require a non-trivial amount of reasoning steps.

Just the other day I needed to code some interlocked indices. It wasn't particularly hard but I didn't want to context switch and think so instead I asked gpt 4o. After a back and worth for 4 or 5 times, where it gave wrong answers I finally decided to just take a pen and paper and do it by hand. I have a hard time believing that these models are reasoning, because if they are they are very poor at it.

Re: OpenAI claims gold-medal performance at IMO 2025

#575

Post by dang »

tmule wrote: post #434
dang wrote: post #425

Earlier quoted context omitted.

Please don't take HN threads into nationalistic flamewar. It leads nowhere interesting or good. We detached this subthread from https://news.ycombinator.com/item?id=44615783 .

[flagged]

Please don't respond to a bad comment by breaking the site guidelines yourself. That only makes things worse.

https://news.ycombinator.com/newsguidelines.html

Re: OpenAI claims gold-medal performance at IMO 2025

#576

Post by dang »

imiric wrote: post #395
dang wrote: post #308

Earlier quoted context omitted.

Please don't cross into personal attack. We ban accounts that do that. Also, please don't fulminate. This is in the site guidelines: https://news.ycombinator.com/newsguidelines.html .

Noted. General attacks are fine, but we draw the line at personal.

No, that's certainly not the case.

If you see a post that ought to have been moderated but hasn't been, the likeliest explanation is that we didn't see it. You can help by flagging it or emailing us at hn@ycombinator.com.

https://hn.algolia.com/?dateRange=all&page=0&prefix=false&qu...

The other thing, though, is that views differ about how such comments should be classified. What seems like an outrageous "general attack" to one reader (especially if you feel passionately about a topic) may not at all land that way with the rest of the community. For this reason, it's hard to generalize; I'd need to see specific links.

Re: OpenAI claims gold-medal performance at IMO 2025

#577

Post by torginus »

modeless wrote: post #117

Noam Brown: > this isn’t an IMO-specific model. It’s a reasoning LLM that incorporates new experimental general-purpose techniques. > it’s also more efficient [than o1 or o3] with its thinking. And there’s a lot of room to push the test-time compute and efficiency further. > As fast as recent AI progress has been, I fully expect the trend to continue. Importantly, I think we’re close to AI substantially contributing…

Thing is, for example, all of classical physics can be derived from Newton's laws, Maxwell's equations and the laws of Thermodynamics, all of which can be written on a slip of paper.

A sufficiently brilliant and determined human can invent or explain everything armed only with this knowledge.

There's no need to train him on a huge corpus of text, like they do with ChatGPT.

Not sure what this model's like, but I'm quite certain it's not trained on terabytes of Internet and book dumps, but rather is trained for abstract problem solving in some way, and is likely much smaller than these trillion parameter SOTA transformers, hence is much faster.

Re: OpenAI claims gold-medal performance at IMO 2025

#578

Post by dmurray »

xpressvideoz wrote: post #116
tlb wrote: post #85

I encourage anyone who thinks these are easy high-school problems to try to solve some. They're published (including this year's) at https://www.imo-official.org/problems.aspx . They make my head spin.

I didn't know there were localized versions of the IMO problems. But now that I think of it, having versions of multiple languages is a must to remove the language barrier from the competitors. I guess having that many language versions (I see ~50 languages?) may make keeping the security of the problems considerably harder?

The problems are chosen by representatives from all the countries. So every country has someone who knows the full exam before the participants get it. Security is on the honour system, but it seems to mostly work.

Re: OpenAI claims gold-medal performance at IMO 2025

#579

Post by peripitea »

ysavir wrote: post #500
ctoth wrote: post #490

Pre-registering a prediction: When (not if) AI does make a major scientific discovery, we'll hear "well it's not really thinking, it just processed all human knowledge and found patterns we missed - that's basically cheating!"

Less that AI is cheating and more that we basically found a way to take the thousand monkeys with infinite time scenario and condense that into a reasonable(?) amount of time and with some decent starting instructions. The AI wouldn't have done any of the heavy lifting of the discovery, it just iterated on the work of past researchers at speeds beyond human.

It sounds like you're saying AI is just doing brute force with a lot of force, but I can't imagine that's actually what you think, so would you mind clarifying?

Re: OpenAI claims gold-medal performance at IMO 2025

#580

Post by torginus »

rafael859 wrote: post #185

Interesting that the proofs seem to use a limited vocabulary: https://github.com/aw31/openai-imo-2025-proofs/blob/main/pro... Why waste time say lot word when few word do trick :) Also worth pointing out that Alex Wei is himself a gold medalist at IOI.

In transformers generating each token takes the same amount of time, regardless of how much meaning it carries. By cutting out the filler from the text, you get a huge speedup.
Post reply on HN