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

Math is a verifiable domain. Translate a proof into Lean and you can check it in a non-hallucination-vulnerable way.


But that's not what they're doing here. They're comparing Alphaevolve's outputs numerically against a scoring function


They did also take some of the informal proofs and formalized them using AlphaProof, emitting Lean.


Ah ok, I didn't notice that part, thx




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

Search: