AI Safety Evals - Paper Reading Club

An author presentation this week: Morgan Sinclaire will present his paper When can we trust untrusted monitoring? A safety case sketch across collusion strategies. This is very recent research following up on the foundational control paper discussed on April 7. Please come to both! ​Every week, someone will present for up to 20 minutes followed by 40 minutes of discussion. RSVP to join, sign up to present, or contact us at evalsreadinggroup@gmail.com with questions. Everyone is welcome!