Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Research Experience
Currently working on LLM safety at Anthropic. Previously, worked as a data scientist and engineering manager at Automatic Labs (2013-2014) and Uber (2014-2019).
Education
PhD in Cognitive Science from Princeton University, advised by Tom Griffiths, supported by an NDSEG fellowship; had an internship at DeepMind.
Background
Research Interests: Computational models of communication, with an emphasis on the real-world consequences of speech acts. For example, how will an utterance affect a listener's beliefs and actions? And how do people (or LLMs) weigh these outcomes?