About

I study Computer Science at Georgia Tech 🐝 with concentrations in systems & architecture and theory.

I spent the past year on leave as founding engineer and researcher at Automorphic (YC S23) in San Francisco, conducting research on building steerable, knowledgeable language models. I also work with Confirm Labs on new ways to discover interpretable circuits in language models.

I am generally interested in language models, specifically intepretability, capabilities (e.g. agents and reasoning), and architectural improvements.

I also enjoy rowing my own gears, cycling, music of the past, and a good book or blog.

I have a resume, and you can reach me via email.

Recent Work