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

641–650 of 737 posts

Re: OpenAI claims gold-medal performance at IMO 2025

#641

Post by ysavir »

colinplamondon wrote: post #504
ysavir wrote: post #500

Earlier quoted context omitted.

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.

Honest question - how is that not true of those past researchers? IE, they... - Start with the context window of prior researchers. - Set a goal or research direction. - Engage in chain of thought with occasional reality-testing. - Generate an output artifact, reviewable by those with appropriate expertise, to allow consensus reality to accept or reject their work.

The difference is that human researchers have agency--for better or for worse.

Re: OpenAI claims gold-medal performance at IMO 2025

#642

Post by Tainnor »

bko wrote: post #628
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 like watching youtube videos solving these problems. They're deceptively simple. I remember reading one: x+y=1 xy=1 The incredible thing is the explanation uses almost all reasoning steps that I am familiar with from basic algebra, like factoring, quadratic formula, etc. But it just comes together so beautifully. It gives you the impression that if you thought about it long enough, surely you would have come up wit…

This is slightly tedious to do by hand but there isn't really anything interesting going on in that problem - it's just solving a quadratic equation over the complex numbers.

Re: OpenAI claims gold-medal performance at IMO 2025

#644

Post by jfengel »

jebarker wrote: post #400
jebarker wrote: post #183

Earlier quoted context omitted.

I disagree with this assessment. We don’t know the steps we have to take. We know a set of steps we could take but they’re societally unpalatable. Technology can potentially offer alternative steps or introduce societal changes that make the first set of steps more palatable.

I feel I should clarify as clearly this is an unpopular opinion: I’m not saying climate change can be solved by technology alone, but I do believe that enabling the societal changes needed to deal with climate change requires using every tool we have at our disposal and that includes technology. I don’t really see why this is controversial and would love to hear that perspective.

My perspective is that no technology can do much while the social problem is so intractable.

If somehow we could get past the social problem, technology will happen. Probably quickly, once we had some agreement that it was a thing worth doing. But until then the technology is largely moot.

Re: OpenAI claims gold-medal performance at IMO 2025

#645

Post by quirino »

sigbottle wrote: post #621
quirino wrote: post #302

Earlier quoted context omitted.

All you said is true. Keep in mind this is the "Heuristics" competition instead of the "Algorithms" one. Instead of the more traditional Leetcode-like problems, it's things like optimizing scheduling/clustering according to some loss function. Think simulated annealing or pruned searches.

Dude thank you for stating this. OpenAI's o3 model can solve very standard even up to 2700 rated codeforces problems it's been trained on, but is unable to think from first principles to solve problems I've set that are ~1600 rated. Those 2700 algorithms problems are obscure pages on the competitive programming wiki, so it's able to solve it with knowledge alone. I am still not very impressed with its ability to reas…

Not completely sure how your reply relates to my comment. I was just mentioning the competition is on Heuristics which is different from what you find on CF or most coding competitions.

About the performance of AI on competitions, I agree what's difficult for it is different from what's difficult for us.

Problems that are just applying a couple of obscure techniques may be easier for them. But some problems I've solved required a special kind of visualization/intuition which I can see being hard for AI. But I'd also say that of many Math Olympiad problems and they seem to be doing fine there.

I've almost accepted it's a matter of time before they become better than most/all of the best competitors.

For context, I'm a CF Grandmaster but haven't played much with newer models so maybe I'm underestimating their weaknesses.

Re: OpenAI claims gold-medal performance at IMO 2025

#646

Post by roenxi »

Tainnor wrote: post #642
bko wrote: post #628

Earlier quoted context omitted.

I like watching youtube videos solving these problems. They're deceptively simple. I remember reading one: x+y=1 xy=1 The incredible thing is the explanation uses almost all reasoning steps that I am familiar with from basic algebra, like factoring, quadratic formula, etc. But it just comes together so beautifully. It gives you the impression that if you thought about it long enough, surely you would have come up wit…

This is slightly tedious to do by hand but there isn't really anything interesting going on in that problem - it's just solving a quadratic equation over the complex numbers.

That isn't much of an argument; nothing in math is truly interesting if you take that approach. exp(i\pi)+1=0 could be said to be dis-interesting because it is just rotation on the complex plane. But it is the opposite - it is interesting because it turned out to be rotation on the complex plane but approached from summing infinite series.

Similarly you can say that solving a quadratic over complex numbers is dis-interesting, but it is actually an interesting puzzle because it is trying its best to pretend it isn't a quadratic. In many ways succeeding, it isn't a quadratic - there is no "2" in it.

Re: OpenAI claims gold-medal performance at IMO 2025

#647

Post by lukebechtel »

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.

whoah, very very interesting / telling.

Re: OpenAI claims gold-medal performance at IMO 2025

#648

Post by queenkjuul »

Bjorkbat wrote: post #330
chairhairair wrote: post #77

OpenAI simply can’t be trusted on any benchmarks: https://news.ycombinator.com/item?id=42761648

Somewhat related, but I’ve been feeling as of late what can best be described as “benchmark fatigue”. The latest models can score something like 70% on SWE-bench verified and yet it’s difficult to say what tangible impact this has on actual software development. Likewise, they absolutely crush humans at sport programming but are unreliable software engineers on their own. What does it really mean that an LLM got gold…

Far as i can tell here, the actual advancement is in the methodology used to create a model tuned for this problem domain, and how efficient that method is. Theoretically then, making it easier to build other problem-domain-specific models.

That a highly tuned model designed to solve IMO problems can solve IMO problems is impressive, maybe, but yeah it doesn't really signal any specific utility otherwise.

Re: OpenAI claims gold-medal performance at IMO 2025

#650

Post by cyberax »

rjtobin wrote: post #351
bwfan123 wrote: post #329

Earlier quoted context omitted.

To me, this is a tell of human-involvement in the model solution. There is no reason why machines would do badly on exactly the problem which humans do badly as well - without humans prodding the machine towards a solution. Also, there is no reason why machines could not produce a partial or wrong answer to problem 6 which seems like survivor bias to me. ie, that only correct solutions were cherrypicked.

There is at least one reason - it was a harder problem. Agreed that which IMO problems are hard for a human IMO participant and which are hard for an LLM are different things, but seems like they should be positively correlated at least?

IMO problems are not hard. They are merely tricky. They test primarily pattern recognition capabilities, requiring that flash of insight to find the hidden clue.

So it's no wonder that AI can solve them so well. Neural networks are great at pattern recognition.

A better test is to ask the AI to come up with good Olympiad problems. I went ahead and tried, and the results are average.

Post reply on HN