AI Safety Evals Group

​This is our last week in our "chain of thought era." Be there or be very square

​Achu Menon, PhD candidate in computer science, will be presenting:

​When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors
https://arxiv.org/abs/2507.05246

​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.