Dimitris Papailiopoulos - "The challenge of monitoring covert interactions and behavioral shifts in LLM agents."
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.
If you're a machine learning researcher interested in attending future workshops, please fill out the following expression of interest form to get notified about future events: [ Ссылка ]
Find more talks on this YouTube channel, and at [ Ссылка ]
