Axiom releases 16M-line Lean formalization of the entire Stacks Project using AI agents
kimmonismus · x · 2026-11-05
Axiom announced a 16-million-line Lean formalization of the entire Stacks Project, the critical infrastructure underlying modern algebraic geometry — a strong counterexample to the claim that AI-generated code at scale is sloppy.
Key points:
- Structure preserved: Axiom likens it to the Louvre's glass pyramid — every definition and proof must connect, so results proved in one chapter are reusable in another.
- More than translation: a human-led swarm of AI agents built a reusable, machine-checkable foundation that AI agents can now use to do mathematics.
- Formalization at this scale was long considered beyond AI's reach; this is a landmark AI4Math result.
Related event: Axiom Formalizes Entire Stacks Project into 16M Lines of Verified Lean Code(6 posts)→
More from Research
- Engram: brief training fixes long-run models' increasingly inscrutable notes — scott_linderman · 2026-11-05
- JITEngine synthesizes custom LLM inference engines, 2.7x faster on Apple Silicon — CShorten30 · 2026-11-05
- NMSLIB author publicly slams new vector search preprint for downplaying prior work — srchvrs · 2026-11-05
- NMSLIB author: new preprint cites us to back an unsubstantiated claim — srchvrs · 2026-11-05
- Foresight-SWE benchmark: coding agents solve 60.7% of issues but only 14.8% without introducing bugs — OfirPress · 2026-11-05
- Paper: "bottleneck pressure" shows work AI can't do gets more valuable as AI spreads — soumitrashukla9 · 2026-11-05