Published multiple papers on artificial intelligence, deep reinforcement learning, and beneficial AI, including 'Adversarial Policies Beat Superhuman Go AIs' and other significant works.
Research Experience
Worked at Google DeepMind with Jan Leike and Geoffrey Irving.
Education
PhD in Artificial Intelligence from UC Berkeley in 2022, supervised by Stuart Russell; MPhil in Advanced Computer Science from the University of Cambridge in 2016; BA (Hons) in Computer Science from the University of Cambridge in 2015.
Background
Founder & CEO at FAR.AI, an AI safety research institute working to ensure advanced AI is safe and beneficial to humanity. Board member of the Safe AI Forum, the London Initiative for Safe AI, and METR. Previously worked at Google DeepMind.
Miscellany
Interests include Artificial Intelligence, Deep RL, and Beneficial AI.