Hello

I’m currently a Master’s student in ML and thinking about how to evaluate and control the alignment properties of powerful AI systems.

Previously, I was the program lead and curriculum developer of ARENA, a ML engineering program for upskilling people in doing technical AI safety work. I co-wrote the ARENA curriculum on LLM Evaluations. I was also the director of Cambridge AI Safety Hub, where I ran educational/research programs like CaMLAB and MARS to grow the AI safety community in Cambridge. I have a BA Hons in neuroscience from the University of Cambridge, where I was interested in computational cognitive neuroscience and Bayesian models.