CoT May Be Highly Informative Despite “Unfaithfulness”
Amy Deng, Sydney Von Arx, Ben Snodin, Sudarsh Kunnavakkam, Tamera Lanham — 2025-08-08 — METR, Gray Swan
Source
- Link: https://metr.org/blog/2025-08-08-cot-may-be-highly-informative-despite-unfaithfulness/
- Listed in the Shallow Review of Technical AI Safety 2025 under 1 agenda(s):
- chain-of-thought-monitoring — Black-box safety (understand and control current model behaviour) / Iterative alignment