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

Gemini with Deep Think achieves gold-medal standard at the IMO

deepmind.google

Post reply on HN
Print view View original

191–200 of 254 posts

Re: Gemini with Deep Think achieves gold-medal standard at the IMO

#191

Post by cma »

tough wrote: post #166
cma wrote: post #39

Earlier quoted context omitted.

I think maybe all Altman companies have used tactics like this. > We were trying to get a big client for weeks, and they said no and went with a competitor. The competitor already had a terms sheet from the company were we trying to sign up. It was real serious. > We were devastated, but we decided to fly down and sit in their lobby until they would meet with us. So they finally let us talk to them after most of the…

>> > I think the reason why PG respects Sam so much is he is charismatic, resourceful, and just overall seems like a genuine person. does he? wasn't sama ousted of YC in some muddy ways after he tried to co-opt in into an OpenAI investment arm, was funny to find the YC Open Research project landing page on yc's website now defunct and pointing how he misrepresented it as a YC project when it was his own maybe he fear…

The post was from 14 years ago, before that.

Re: Gemini with Deep Think achieves gold-medal standard at the IMO

#192

Post by CamperBob2 »

cubefox wrote: post #97
shiandow wrote: post #59

Comparing the answers between Openai and Gemini the writing style of Gemini is a lot clearer. It could be presented a bit better but it's easy enough to follow the proof. This also makes it a lot shorter than the answer given by OpenAI and it uses proper prose.

I found the proofs you were referring to: Google https://storage.googleapis.com/deepmind-media/gemini/IMO_202... OpenAI https://github.com/aw31/openai-imo-2025-proofs/

Kind of disappointing that neither provider shows the unsuccessful attack on problem 6.

Re: Gemini with Deep Think achieves gold-medal standard at the IMO

#193

Post by famouswaffles »

kevinventullo wrote: post #91

This year, our advanced Gemini model operated end-to-end in natural language, producing rigorous mathematical proofs directly from the official problem descriptions I think I have a minority opinion here, but I’m a bit disappointed they seem to be moving away from formal techniques. I think if you ever want to truly “automate” math or do it at machine scale, e.g. creating proofs that would amount to thousands of page…

If a Language Model is capable of producing rigorous natural language proofs then getting it to produce Lean (or whatever) proofs would not be a big deal.

Lean use in AlphaProof was something of a crutch (not saying this as a bad thing). Very specialized, very narrow with little use outside any other domain.

On the other hand, if you can achieve the same with general RL techniques and natural language then other hard-to-verify (a whole lot) domains are on the table.

Re: Gemini with Deep Think achieves gold-medal standard at the IMO

#194

Post by bwfan123 »

Problem 6 is puzzling. Neither openai nor deepmind answered it. Humans would put out partial answers - but here we saw no answer which is odd.

Does that mean that the llms realized they could not solve it. I thought that was one of the limitations of LLMs in that they dont know what they dont know, and it is really impossible without a solver to know the consistency of an argument, ie, know that one knows.

Re: Gemini with Deep Think achieves gold-medal standard at the IMO

#195

Post by CamperBob2 »

KaoruAoiShiho wrote: post #38
sxp wrote: post #24

Related news: - OpenAI claims gold-medal performance at IMO 2025 https://news.ycombinator.com/item?id=44613840 - "According to a friend, the IMO asked AI companies not to steal the spotlight from kids and to wait a week after the closing ceremony to announce results. OpenAI announced the results BEFORE the closing ceremony. According to a Coordinator on Problem 6, the one problem OpenAI couldn't solve, "the general s…

OpenAI announced their results after the closing ceremony as was requested. https://x.com/polynoamial/status/1947024171860476264?s=46

OT, but please consider posting links like this using xcancel, so that non-X users can read them.

https://xcancel.com/polynoamial/status/1947024171860476264?s...

Re: Gemini with Deep Think achieves gold-medal standard at the IMO

#196

Post by nightpool »

bwfan123 wrote: post #194

Problem 6 is puzzling. Neither openai nor deepmind answered it. Humans would put out partial answers - but here we saw no answer which is odd. Does that mean that the llms realized they could not solve it. I thought that was one of the limitations of LLMs in that they dont know what they dont know, and it is really impossible without a solver to know the consistency of an argument, ie, know that one knows.

I think it probably just means that they exhausted the competition time limit without completing the "thinking" portion and getting to the "output" stage.

Re: Gemini with Deep Think achieves gold-medal standard at the IMO

#197

Post by killerstorm »

bwfan123 wrote: post #194

Problem 6 is puzzling. Neither openai nor deepmind answered it. Humans would put out partial answers - but here we saw no answer which is odd. Does that mean that the llms realized they could not solve it. I thought that was one of the limitations of LLMs in that they dont know what they dont know, and it is really impossible without a solver to know the consistency of an argument, ie, know that one knows.

That applies only to most basic use of LLM: pre-trained LLM generating text.

You can do a lot of things on top: e.g. train a linear probe to give a confidence score. Yes, it won't be 100% reliable, but it might be reliable if you constraint it to a domain like math.

Re: Gemini with Deep Think achieves gold-medal standard at the IMO

#198

Post by shiandow »

sweezyjeezy wrote: post #153
shiandow wrote: post #131

Earlier quoted context omitted.

Section 2 is a case by case analysis. Those are never pretty but perfectly normal given the problem. With OpenAI that part takes up about 2/3 if the proof even with its fragmented prose. I don't think it does much better.

It's not it being case by case that's my issue. I used do olympiads and e.g. for the k>=3 case I wouldn't write much more than: "Since there are 3k - 3 points on the perimeter of the triangle to be covered, and any sunny line can pass through at most two of them, it follows that 3k − 3 ≤ 2k, i.e. k ≤ 3." Gemini writes: Let Tk be the convex hull of Pk. Tk is the triangle with vertices V1 = (1, 1), V2 = (1, k), V3 = (k…

I'll admit I didn't look to deeply if it could be done simpler, but surely that is still miles better than what OpenAI did? At least Gemini's can be simplified. OpenAI labels all points and then enumerates all the lines that go through them.

Re: Gemini with Deep Think achieves gold-medal standard at the IMO

#199

Post by qnleigh »

gus_massa wrote: post #80
dvh wrote: post #33

Earlier quoted context omitted.

Ok but when reported by mass media, which never used SI units and instead uses units like libraries of Congress, or elephants, what kind of unit should media use to compare computational energy of ai vs children?

4.5 hours × 2 "days", 100 Wats including support system. I'm not sure how to implement the "no calculator" rule :) but for this kind of problems it's not critical. Total = 900Wh = 3.24MJ

100 watts seems very low. A single Nvidia GeForce RTX 5090 is rated at ~600 watts. Probably they are using many GPUs/TPUs in parallel.

Re: Gemini with Deep Think achieves gold-medal standard at the IMO

#200

Post by qnleigh »

aldousd666 wrote: post #144
Dzugaru wrote: post #139

Most critical piece of information I couldn’t find is - how many shot was this? Could it understand the solution is correct by itself (one-shot)? Or did it have just great math intuition and knowledge? How the solutions were validated if it was 10-100 shot?

The solutions were evaluated on their submitted output. You're allowed to use multiple 'shots' to produce the output, but just one submission per question. People are allowed this same affordance.

But were humans involved in picking which answer/shot to submit, or was it only AI?
Post reply on HN