Currently a Visiting Student Researcher at Google Deepmind, working on Chain-of-thought monitoring; part of the founding team at UK’s AI Safety Institute, helped scale the organisation, and started their post-training team; research intern at UC Berkeley, worked with Owain Evans to better understand LLM generalization.
Education
PhD student at the University of Toronto, supervised by Roger Grosse; completed CS undergrad at the University of Cambridge.
Background
Cares a lot about making AI go well, and has spent his career so far doing technical research to help with that!