Axiom 发布 Stacks Project 的 1600 万行 Lean 形式化成果，把代数几何中高度互联的基础内容转成计算机可校验的数学。作者指出，这项成果的关键在于结构而非规模，每个定义和证明都必须彼此衔接，因此某一章的结论可以在另一章复用。该成果由人类主导的 AI 智能体集群完成，形成了一套可复用的机器可校验基础，供 AI 智能体继续做数学研究。
AI-generated code at scale usually gets written off as sloppy. Axiom's new release is a strong counterexample.
Axiom says it has formalized the Stacks Project in Lean, a huge, deeply interconnected foundation of algebraic geometry, turning it into mathematics a computer can check.
The impressive part isn't just the size, it's the structure. Axiom compares it to the Louvre's glass pyramid: individual pieces that only work because they fit together into something much bigger. Every definition and proof has to connect, so a result proved in one chapter can be used in another.
That's what makes it more than a translation. A human-led swarm of AI agents built a reusable, machine-checkable foundation that AI agents can now use to do mathematics.
Congrats to the Axiom team!
Most think vibecoding at scale is slop. Here’s a counterexample. Today we release a 16M-line formalization of the entire Stacks Project, critical infra underlying modern math, with optimized code quality and its highly interconnected structure preserved. A mathematical city 🌆在 X 查看被引用的帖子
来源：Chubby♨️ · x.com