I’m a third-year undergrad at MIT studying AI & Math. I’m interested in building provably safe AI systems, specifically interpreting & verifying neural networks.

Random interests outside academics: Crypto, photography.

Research

I currently work on evaluating LLM’s capability at writing formally verifiable code at Max Tegmark’s group.

This summer, I’m also interning at Center for Human-Compatible AI (CHAI) and working on avoiding side effects in RL environments.