Claude wrote the first computer-checked proof of Fermat's Last Theorem in 11 days
An internal Anthropic research model roughly comparable to Claude Fable 5.1 burned about six billion output tokens over 11 days to produce 13 million lines of Lean — over 5x the size of Mathlib — proving 30,300 theorems, 29,500 of which appear in the final proof of Fermat's Last Theorem. Lean verified it using only its three standard axioms, and Kevin Buzzard of Imperial College London, who kicked off the community formalization in 2024, called the artefacts robust enough to build on. The novelty is verification speed, not new mathematics: a formalization the field expected to take years closed in under two weeks, putting automatic formalization of the modern mathematical literature within reach.
Source: anthropic.com ↗
If the automatic formalization of FLT is possible now, then we have taken a big step towards automatic formalization of the modern mathematical literature.
Why this matters
- → Machine verification of 350-year-old conjecture collapses years-long project to 11 days
- → Autoformalization now fast enough to check modern mathematics as it's published
- → Opens path to catch errors in published proofs without months of manual review