Mathematician's AI-generated errata are "slop" but mostly correct

littmath · x · 2026-08-27

In his thread on AI-auditing his own papers, Daniel Litt revealed he also generated semi-automated errata. He openly calls them "slop" and only lightly edited them, but spot-checks showed they were mostly correct, if massively overzealous—often replacing whole paragraphs where a single word would do.

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 →