The goal of my research is to make foundation models, particularly language models, a more trustworthy and easy to use technology. In particular, I’ve been interested in making language models more factual, up-to-date, and able to understand user intent. I’m also quite interested in scalable oversight as well as improving the reasoning & planning abilities of language models. Much of my PhD has been generously supported by a Knight-Hennessy Graduate Fellowship and a Stanford Accelerator for Learning grant for Generative AI for the Future of Learning.