Back to All Events

AI Control with Monika Jotautaitė

AI Control: Science of Monitoring / Monitor Red-Teaming. 30-minute prepared talk with Q&A.

Monika Jotautaitė (Apollo Research) is an AI control researcher focused on monitor red-teaming. Previously, she led an independent two-person research team focused on MonitoringBench, a benchmark for evaluating AI control monitors that has been used in Anthropic's Claude Mythos Preview Risk Report and OpenAI's Auto-Review for Codex. She also organizes Women in AI Safety London, a series of networking events for women in the field.

Previous
Previous
August 2

The AI Safety Research Landscape with Kiana Jafari

Next
Next
September 1

Coaching to Success Pathways with Liz Mohler