Anca Drăgan - Implications of human model misspecification for alignment

Anca Drăgan - "Implications of human model misspecification for alignment."

This presentation was delivered at the New Orleans Alignment Workshop, December 2023.

The Alignment Workshop is a series of events convening top ML researchers from industry and academia to discuss and debate topics related to AI alignment. The goal is to enable researchers to better understand potential risks from advanced AI, and strategies for solving them.