Hello

I’m currently the program lead and curriculum developer of ARENA, a ML engineering program for upskilling people in doing technical AI safety work. I’m developing curriculums for LM evaluations in collaboration with Apollo Research. I’m also the director of Cambridge AI Safety Hub, where I ran educational/research programs like CaMLAB and MARS and spend time growing the AI safety community in Cambridge.

My research interests are to build tools that increase our control over AI systems. I do independent research projects on evaluations, steering, and robustness. I have a BA Hons in neuroscience from the University of Cambridge, where I was interested in computational cognitive neuroscience and Bayesian models.