I’m a computer scientist pursuing a PhD at Brigham Young University (BYU) in AI Safety. Currently I’m most interested in mechanistic interpretability and control! I did my MS in CS at BYU in programming languages and I have worked full time as a software engineer for Awardco.
I think there are a lot of ways that the development and deployment of AI could potentially go wrong, and I want to find ways to make that less likely. I’m hoping to develop new steering methods as part of my PhD. Outside of work, I enjoy hiking, tabletop games, reading fantasy and sci-fi, and studying linguistics.
Some of my Favorite Projects
- A machine learning training framework aimed at unifying the efforts my research lab
- A static analyzer to find all possible database queries a function in a TypeScript could send
- A natural-language-like toy programming language