Speaker Details

Speaker 1

Ryan Carey

The University of Oxford

Ryan is a final-year DPhil student with Robin Evans at Oxford, interested in causal models under marginalisation and selection, causal models of agents, and AI safety. He has worked on problems relating to the incentives of AI systems, including how to design an AI system to shut down safely. He is a cofounder of the Causal Incentives Working Group.

Ryan Carey’s Webpage