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.
More from Models
- gemini-4-neon surfaces in Gemini web app code as Google's next unreleased model — imjustnewatai · 2026-11-17
- Pangram is polarizing but the author measured ~1 false positive in thousands of runs — ctjlewis · 2026-11-17
- Mystery '4 Hydrogen' Model Spotted in Google AI Mode, Replacing Flash/Pro — Mean_Moan_3495 · 2026-11-17
- GradeBench: best frontier model matches instructors only 57% on real handwritten physics — scaling01 · 2026-11-17
- Kimi K3.1 Pro tops Science's Last Exam among open models at 28.92, trailing only GPT-6.1 Sol and Claude Opus 5 — NielsRogge · 2026-11-17
- Gemini 4 Carbon opens to paying API customers and enterprises, plus 2027 superhuman-coder forecast — thione · 2026-11-17