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.
More from coding & agent
- How OpenAI's Codex went from failed side project to 40M weekly users in under a year — danshipper · 2026-10-16
- Photon 2.0 launches unified messaging API for AI agents across iMessage and more — Scobleizer · 2026-10-16
- Open Nshipyard cleans Canada's messy civic data, exposing $15.1B phantom spend, with MCP tools for agents — RichardsonDx · 2026-10-16
- Claude Opus 5.5 effort levels tested: low reasoning iterates 9x faster than max — tom_doerr · 2026-10-16
- Figma launches Guidelines and Code Sources so AI agents can follow your design system — JaynitMakwana · 2026-10-16
- Ex-DeepMind Eng Lead's AI Calling Agent Fo Cut Hang-Up Rate from 80% to 20-30% — julianweisser · 2026-10-16