Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

The Gemini IMO result used a specifically fine tuned model for math.

Certainly they weren't training on the unreleased problems. Defining out of distribution gets tricky.



>The Gemini IMO result used a specifically fine tuned model for math.

This is false.

https://x.com/YiTayML/status/1947350087941951596

This is false even for the OpenAI model

https://x.com/polynoamial/status/1946478250974200272

"Typically for these AI results, like in Go/Dota/Poker/Diplomacy, researchers spend years making an AI that masters one narrow domain and does little else. But this isn’t an IMO-specific model. It’s a reasoning LLM that incorporates new experimental general-purpose techniques."


Every human taking that exam has fine tuned for math, specifically on IMO problems.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: