News for hackers. Stuff that matters.
Re:AI in mathematics is forcing big questions by cdetrio on Friday June 26, 2026 @11:30PM (#48694855)
The article addresses that, a formal verification layer provides a computational check that a proof is correct.

There's an interesting wrinkle though. The formal definitions and statements need to be correct, i.e. need to faithfully translate the human-readable (informal) definitions and statements. A few months ago, Kevin Buzzard created an auto-formalization challenge: https://gist.github.com/kbuzzard/778bc714030b3e974ab5f403878...

It's a handful of human-written lines, a skeleton that defines an "API surface". If you use AI to generate the rest of the code, the API surface (along with the Lean compiler) acts to guarantee that the whole generated solution (tens of thousands of lines) will be correct.

The discussion thread about the challenge, which was solved a couple weeks ago, is here: https://leanprover.zulipchat.com/#narrow/channel/583336-Auto...

Without the human-written or human-audited skeleton, you might get AI-generated slop Lean code that compiles, but contains nonsensical definitions/statements and thus vacuous proofs. Though from what I gather, recent models are much improved in their capability to generate correct statements and definitions and proofs, for both formal math and informal math.

A discussion thread about a different auto-formalization effort without human-written API surface, with some correct output and some slop: https://leanprover.zulipchat.com/#narrow/channel/583336-Auto...

There are no comments on this comment yet.