Terence Tao ran all his published papers through AI error-finding scaffolds

littmath · x · 2026-08-27

Terence Tao says frontier models, appropriately scaffolded, are now pretty good at finding errors in informal mathematics. He decided to "be the change" and ran all his published papers through such a scaffold.

This follows his earlier point: we should use AI to produce better work, not just more PDFs — one simple step now is identifying and fixing many extant errors in the literature.

Original post →

More from Research

Research channel →