I’m mathematician and agent foundations researcher. My work involves thinking hard about what agents and their goals and beliefs “are”. I ultimately aim to help understand human and AI cognition, as well as the complex multi-agent systems that emerge from their interactions. I pursue this agenda as a research fellow at MATS 9.0, mentored by Richard Ngo. I also follow more empirical AI safety research and eventually hope to contribute to it. Some legible output related to my current (Feb ‘26) work can be found here; this website features some of my older writing on the philosophy of math and some applied AI safety topics.
On the side I play go competitively at the top ~10 level in Europe. I have also spent a significant amount of time teaching and lecturing on the game.