Thomas Broadley

About me

I'm a Canadian living in Berkeley, California.

I work as a Member of Technical Staff at METR. METR's mission is to assess the capabilities of, and the risk of catastrophe from, frontier AI systems.

I'm a co-author of three of METR's recent papers:

• "Measuring AI Ability to Complete Long Tasks", in which we demonstrate that AI performance on certain software tasks is doubling every seven months
• "HCAST: Human-Calibrated Autonomy Software Tasks", a software development benchmark
• "RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts", a machine learning research engineering benchmark

Before METR, I spent 4.5 years as a full-stack web developer at Faire, an online wholesale marketplace. Also, I've interned at Datadog, Zeitspace, Shopify Plus, and Boltmade (since acquired by Shopify).

I have a Bachelor of Computer Science from the University of Waterloo. In September 2020, I attended a one-week mini-batch at the Recurse Center.

Contact me

Email: htbroadley@outlook.com