Speaker: Benjamin Plaut (Postdoc at CHAI (Center for Human-Compatible AI)) Talk: Safe Learning Under Irreversible Dynamics via Asking for Help

Part of the Guaranteed Safe AI Seminars, a monthly online series on AI systems with quantitative safety guarantees.

Recording: https://youtu.be/nLHmSSG7Y2I

Readings: arXiv:2502.14043

YouTube playlist: https://www.youtube.com/playlist?list=PLOutnjp2BEJeQM2J49_KvdpuZlaQXPboy