Claude formalizes Fermat's Last Theorem autonomously in 11 days, 13M lines of Lean
rickasaurus · x · 2026-09-05
Anthropic has announced the first complete computer-checked proof of Fermat's Last Theorem, produced by Claude working largely autonomously over 11 days in the Lean proof language.
- The formalization covers Andrew Wiles's famous 1995 proof, which ran 129 pages and took months to verify by hand.
- Along the way Claude wrote 13 million lines of Lean and proved 29,500 intermediate theorems.
- The project was led by Anthropic researcher Tianyi Peng, whose group at Columbia builds AI formalization tools, building on a community effort started in 2024 by Kevin Buzzard at Imperial College London.
- Buzzard called it an "extraordinary autoformalization achievement."
Fermat's Last Theorem states no positive integers a, b, c satisfy aⁿ + bⁿ = cⁿ for n > 2. The result is being read as a major milestone for AI in research mathematics.
Related event: Claude Produces First Formalized Proof of Fermat's Last Theorem in 11 Days(52 posts)→
More from AGI Musings
- Nat Lambert: AI cyber risk is an ecosystem issue, not an open-weights problem — natolambert · 2026-10-21
- Obesity drugs still out-earn OpenAI and Anthropic combined at $71B a year — HealthcareAIGuy · 2026-10-21
- Is an AI's 'self' just a simulation in the scaffolding layer above the model? — gerardsans · 2026-10-21
- AI can simulate how a self talks, but not what a self is — gerardsans · 2026-10-21
- Musk predicts money will become irrelevant, replaced by 'wattage and tonnage' — Polymarket · 2026-10-21
- zetalyrae quips: post-singularity utopia is so great you need brain surgery to cope — wfithian · 2026-10-21