I work on safety at OpenAI. Previously, I led alignment training at xAI. I'm on leave from a PhD at MIT CSAIL, where I'm advised by Dylan Hadfield-Menell.

I do pragmatic AI safety work with the hope of reducing catastrophic risks from powerful AI systems.

Outside of work, I enjoy playing piano, backpacking, salsa dancing, and philosophy.

Reach out at slocumstewy@gmail.com if you'd like to talk! Leave anonymous feedback for me here.

Google Scholar Resume Goodreads