Discussed risks of AI agents producing unwanted behavior and difficulties in specifying objectives.
This document is a biographical profile of researcher Anca Dragan, appearing on page 97 of a larger House Oversight collection. It details her work at the InterACT Laboratory at Berkeley focusing on human-robot interaction and AI safety, and highlights her collaboration with mentor Stuart Russell. The text includes quotes from an interview she gave to the Future of Life Institute regarding the risks of AI agents producing unintended behaviors.
Discussion 0
No comments yet
Be the first to share your thoughts on this epstein communication