AI Safety Evals - Paper Reading Club

​Join us for an author presentation! Evgenii Kortukov will present his paper on an unusual form of LLM deception: Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs.

​​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!