The AI would build a proof of correctness, which would be then verified in a pro... | Hacker News

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

		js8 19 days ago \| parent \| context \| favorite \| on: Hypothesis, Antithesis, synthesis The AI would build a proof of correctness, which would be then verified in a proof checker (not AI).

Groxx 19 days ago [–]

And how do you prove that the proof of correctness is not just a proof that 1=1? LLMs "cheating" on things is rather common.

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