Description

Can AI agents misbehave while carrying out actions autonomously? At this event, Giles Edkins will guide us through a look at and critique some research by Anthropic that demonstrates blackmail and other phenomena when an agent is threatened with shutdown or reprogramming.

​​​Event Schedule
6:00 to 6:45 - Food & Networking
6:45 to 8:00 - Main Presentation & Questions
8:00 9:00 - Discussion