Stephane Hatgis-Kessell

Hello!

I am an incoming Ph.D. student at Stanford University and a recipient of the NSF Graduate Research Fellowship. My research interests center around

(1) building safe AI systems that do what humans actually want.
(2) preventing unsafe decision-making systems from being deployed.

I completed my undergraudate degree in computer science at the University of Texas at Austin, where I worked closely with Prof. Brad Knox, Prof. Peter Stone, and Prof. Scott Niekum on problems in reinforcement learning from human feedback (RLHF). Please see my publications for more information, and don’t hesitate to reach out!