AI audit identifies 97.7% real issues in math papers

littmath · x · 2026-08-27

The author shared a full report on using Refine.ink and ChatGPT to automatically review and create errata for 19 of their papers. The audit generated 266 detailed comments, 97.7% of which identified real issues (including 5 technical corrections to main results), with only 6 being incorrect. The author described some AI-generated errata as "slop" (mostly correct but overzealous) but hopes these tools can contribute to more reliable literature if used appropriately.

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 coding & agent

coding & agent channel →