Mathematician digs into GPT Pro's proof repair: 'clever and even beautiful'

IgorCarron · x · 2026-11-17

Researcher akoz33 reports he is still studying GPT Pro (Astra 6)'s 'repair' of his proof, and the more he understands it the more impressed he is — calling the fix genuinely clever and even beautiful. Igor Carron reshares with the comment 'And they fall...', implying frontier models are cracking proofs once considered out of reach.

Original post →

More from Models

Models channel →