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.
More from Research
- Best practices for reliable critic training in LLM RL — heghbalz · 2026-08-27
- Tiny 307M-parameter model outperforms 26x larger Qwen in embedding benchmarks — lateinteraction · 2026-08-27
- Study: Generative AI shifts UK students' major choices — RishiBommasani · 2026-08-27
- EvoMax Evolves Compact Genome Editor to 97% Efficiency Using Sparse Data — bravo_abad · 2026-08-27
- Bixbench3: Frontier Agents Score Below 50% in Reproducing Paper Analysis — xeophon · 2026-08-27
- Navigator n2 released: 27B model achieves frontier computer use performance — DhruvBatra_ · 2026-08-27