Hi! I’m Haoxing. I am a proud effective altruist trying to help this whole AI thing go well. I’m currently working on a new project on AI behavior evaluations, incubated at Surplus. Please get in touch if you’d like to chat about this!
Most recently, I worked on predicting the weather with AI at a balloon startup called WindBorne. Before that, I evaluated AI models for dangerous capabilities at METR, where we poked at the first AI agents before the term “AI agent” was invented. I also did some research on neural network interpretability at Redwood Research.
Before AI captured my entire attention I wanted to become a theoretical physicist. At Berkeley, I did research at the intersection of machine learning and physics in the amazing Nachman group. Prior to Berkeley, I was fortunate to be part of the Perimeter Scholars International program, and had the privilege of spending the best college years possible at Harvey Mudd College. If not for AI, I might have spent my career thinking about the foundations of quantum theory. A few years ago, I wrote a couple of posts on quantum foundations, hoping to communicate some of my favorite recent advances to a wider audience, which you can find on this site.
When I’m not thinking about the above topics, I like to read, play video games, make music, fly my paraglider, and climb extremely casually.
I’m happily married to Kasey Markel, and we live in San Francisco. We have signed the 🔸 10% Pledge. If you are reading this, please consider doing the same!
EmailGoogle ScholarGitHubTwitter
Last updated: Nov 18, 2026
- Stop telling people to pivot to AI safety, I beg you Oct 08, 2026
- They Are All Henry: On Everything Is Tuberculosis Feb 15, 2026
- Inside the Mind of a Superhuman Go Model: How Does Leela Zero Read Ladders? Mar 01, 2023
- Is the quantum state a state of knowledge? Jun 07, 2022
- Why I am not an Everettian Mar 22, 2022