Hantao Lou

Hi, I'm Hantao Lou.

I am a final-year undergraduate at Tong Class, Peking University, and a visiting researcher at UC Berkeley RDI.

At Berkeley RDI, I work on formal verification and specifications with Prof. Dawn Song. At Peking University, I work on scalable AI alignment with Prof. Yaodong Yang. Previously, I studied mechanistic interpretability through the MATS program with Evan Hubinger. I've also worked on formal verification at Beneficial AI Foundation, supervised by Prof. Max Tegmark.

My Hamming Question

How can we make advanced AI systems reliable and scalable?

I build supervision and verification methods that make complex model and agent behavior easier to inspect, evaluate, and trust.

Recent work

Selected highlights

All publications