I do a mix of interface design, data collection, and data analysis for Anthropic’s human feedback program. We want to use use human feedback data to align large language models with human intent.

As an academic, I studied philosophy of mind, epistemology, and philosophy of science. My work focused on cognitive architecture (“What’s the functional relationship between perceptual modalities, working memory, and central cognition?”) and methodology in cognitive science (“What kind of evidence counts as evidenc of conscious experience, and why?”). I lectured at MIT during the Spring 2020 term, after receiving my PhD from UC Berkeley.

I procastinated in grad school by building tools for academics.

I occasionally write posts.