We measure things about AI systems that other people only describe — token costs, agent traces, protocol diffs. New measurement most weekdays.

Analyzing post-compliance AI governance, multi-agent risks, & the epistemic limits of technology regulation. Rethinking policy for uninspectable systems.

We research and build safe AI systems that learn how to solve problems and advance scientific discovery for all. Explore our work: deepmind.google

PhD student in Machine Learning at the University of Oxford

Official account for news and updates from Medium.