AI Safety Evals - Paper Reading Club

​A presentation ripped from the headlines: Andreas Turanski will present Measuring AI Agents' Progress on Multi-Step Cyber Attack Scenarios and Our evaluation of Claude Mythos Preview’s cyber capabilities. Don't miss it!

​​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 [email protected] with questions. Everyone is welcome!