about

I'm a Member of Technical Staff at METR, where I develop benchmarks to help us understand advanced AI systems. Previously, I was a researcher at NYU, where I worked with Sam Bowman on benchmarking (GPQA) and scalable oversight (debate) research. I was also an early employee at Cohere, an AI startup based in Toronto, where I helped train large language models.

I like AI/ML, philosophy, science, and doing good things.