I am an alignment researcher at Anthropic and associate professor of philosophy at the University of Illinois at Urbana-Champaign. My research spans epistemology, decision theory, and AI safety, with recent work on whether language models have beliefs and how to make them more truthful. I have two books forthcoming with Cambridge University Press: one on epistemic utility theory (with Jason Konek) and another on AI interpretability (with Daniel Herrmann). I’ve previously held post-doctoral positions at Oxford, Bristol, and Rutgers. I spend most of my free time thinking about how to align the Cubs with winning baseball.