I’m currently interested in the intersection of mathematics, computer science, and long-term-focused research.
Recently, I've become especially curious about technical AI safety — how we can reason clearly about systems that learn and adapt in complex environments. I'm part of the Fast Track program at the Cambridge AI Safety Hub (CAISH), where I’ve been connecting with others on a similar path: undergrads, postgrads, and researchers exploring research careers in AI safety.
Alongside this, I’ve been independently studying reinforcement learning — both the theory (MDPs, Bellman equations, function approximation) and its application through self-coded projects. My work so far has focused on environments with hidden information and probabilistic reasoning.