Claude formalized Fermat's Last Theorem in 11 days, writing 13M lines of Lean across 29,500 theorems
dl_weekly · x · 2026-09-13
Anthropic has shared the first complete computer-checked proof of Fermat's Last Theorem, produced by Claude working largely autonomously over 11 days in the Lean proof assistant — roughly 13 million lines of code proving 29,500 intermediate theorems. The effort was initiated by Anthropic researcher Tianyi Peng, whose group at Columbia builds AI formalization tools, to test how far Claude could push FLT formalization. Context: Wiles's original 1995 human proof ran 129 pages; a multi-year community formalization effort led by Kevin Buzzard at Imperial College began in 2024. Buzzard called the result an extraordinary autoformalization achievement, and Anthropic discusses what it could mean for research mathematics.
More from AGI Musings
- StudentBench: AI tutoring matches human GRE gains at 918x lower cost — gharik · 2026-10-31
- Box CEO Aaron Levie: AI progress is 'going vertical,' widening the frontier gap — rohanpaul_ai · 2026-10-31
- Model Collapse May Not Hit LLMs, But Perhaps Human Culture or Souls — generativist · 2026-10-31
- Nina Schick: who builds intelligence and how it's distributed is the defining question of our lives — NinaDSchick · 2026-10-31
- Martin Casado: AI's dazzling 80% makes everyone skip the hard 20% — martin_casado · 2026-10-31
- Cheap intelligence is like cheap bread — an ingredient list satire of mass-produced AI — jsuarez · 2026-10-31