METR: AI capability doubling every 3.6 months while evals get harder to measure

mustafasuleyman · x · 2026-11-22

Microsoft AI chief Mustafa Suleyman amplified METR's new research update: AI R&D-relevant capabilities are improving rapidly — doubling roughly every 3.6 months — and increasingly exceed what prior time-horizon benchmarks can capture, making measurement harder as models get stronger.

Suleyman argues you can't govern what you can't measure, that eval science deserves frontier-scale funding, and that mandatory evals could soon become a legal requirement.

Related event: METR Quarterly Update: AI R&D Capabilities Double Every 3.6 Months and Are Getting Harder to Measure(13 posts)→

Original post →

More from Safety

Safety channel →