Terence Tao post sparks buzz as a cool mechanistic interpretability application
Sauers_ · x · 2026-09-06
Sauers shares a Terence Tao post, suggesting it could be a very cool application of mechanistic interpretability.
More from Research
- Models over-edit code written by other models; CROCODIL training framework fixes it — omarsar0 · 2026-09-06
- Bare coding agent hits 78% on R2R-CE navigation with zero training, no mapping or memory — jiqizhixin · 2026-09-06
- Slow Clinical Trials Break AI's Feedback Loop in Drug Development — clarejtbirch · 2026-09-06
- GPT-6 saturates RuneBench after just 6 months; author builds harder swarm tasks — SchoeneggerPhil · 2026-09-06
- Harness-of-Harness carries state across runs: 71.52 vs 58.24 on long-horizon coding — rohanpaul_ai · 2026-09-06
- DeepMind paper shows cheating spreading like an epidemic across ~100 AI agents — jackclarkSF · 2026-09-06