About
I'm a researcher at METR. My current focus is on "embedded monitoring stress-testing"—I go into frontier AI companies and figure out how their internal agents are going to break their security and AI monitoring systems.
I think there's a very good chance that humanity is on track to create AI systems substantially smarter and more capable than us. We need to be really careful about this, because it's an open scientific question whether we can control such systems.
Previously, I created GPQA, a widely used AI capability benchmark, I developed scalable oversight methods (i.e. for supervising systems smarter than their overseers), and I was one of the first few employees at Cohere, where I trained embedding models for semantic search.
Research highlights
-
2026
(METR) Frontier Risk Report (February to March 2026) -
2025
(METR) Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity -
2025
(METR) Measuring AI Ability to Complete Long Tasks -
2023
(NYU) GPQA: A Graduate-Level Google-Proof Q&A Benchmark -
2023
(NYU) Debate Helps Supervise Unreliable Experts
In the news
Writing & talks
Essays
7
Research
5