👋 Hi!

I’m Tom, and I’m on the Safety team at Mistral AI. I work on post-training, evals and guardrails.

I previous worked at the intersection of 🔍 interpretability and 🎯 alignment at the J.P. Morgan Explainable AI Center of Excellence. During my PhD at the University of Bristol and Alan Turing Institute, I worked on both problems (🔍, 🎯) with a focus on 🤖 reinforcement learning agents.

Fancy a chinwag? You can reach me at the links in the sidebar (or under the “Connect” button above if you’re on mobile).