AI Safety Evals - Paper Reading Club

​We are reading:

​Chain-of-Thought Reasoning In The Wild Is Not Always Faithful
https://arxiv.org/abs/2503.08679

​Author Iván Arcuschin will be joining us for a talk and discussion!

​Every week, someone will present for up to 20 minutes followed by 40 minutes of discussion. RSVP to join, check our schedule, volunteer to present, pick one paper from our suggested list or propose your own.

Note: Formerly scheduled, but delayed to next week:
CoT May Be Highly Informative Despite “Unfaithfulness”

https://metr.org/blog/2025-08-08-cot-may-be-highly-informative-despite-unfaithfulness/