Tom Tseng

I'm a research engineer at FAR.AI where I work on infrastructure for our AI safety research. You can reach me at tom@tomhmtseng.com.

I previously spent several years on FAR's research team studying the robustness and guardrails of AI models. My most prominent project was finding adversarial attacks against superhuman Go AIs, which showed that superhuman capabilities in a domain don't automatically provide robustness.

Before FAR, I was a software engineer at Gather and Cruise, and I worked on parallel algorithms research when I was a student at MIT and Carnegie Mellon.