About
I’m an ML researcher, interested in ensuring that AI progress is broadly beneficial—both by minimising AI-induced harms, and ensuring that the benefits are shared outside of the privileged few.
Currently, I’m a PhD student at the University of Toronto, supervised by Roger Grosse, where I’m using influence functions to investigate how LLMs generalize.
Before that I was part of the founding team at UK’s AI Safety Institute— I helped scale the organisation, and started our post-training team. Before that I worked at the Center for AI Safety, was a research intern at UC Berkeley, studied LLM generalization under Owain Evans and completed my CS undergrad at the University of Cambridge.