AI audit not infallible: Refine missed a known lemma error in paper

littmath · x · 2026-08-27

Evaluating the completeness of the Refine reports, Daniel Litt noted they are definitely not perfect. The tool missed an error in a lemma in one of his published papers, previously found by Jordan Ellenberg and Alex Smith (and subject to an erratum, though it didn't affect a main result). This indicates that while AI audits are highly effective, human review is still necessary to catch missed nuances.

Related event: Mathematician Daniel Litt Audits His Own 19 Papers with AI: 97.7% of Comments Flag Real Issues(6 posts)→

Original post →

More from Research

Research channel →