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.
More from Safety
- Lawyers Argue AI Notetakers Shouldn't Waive Attorney-Client Privilege — sebkrier · 2026-11-22
- Ex-MIRI researcher Jessica Taylor cites her 2016 talk backing task-directed AGI — jessi_cata · 2026-11-22
- Palmer Luckey on weapons AI: 'If I were putting ChatGPT in the head of my missile, you'd be right to be terrified' — justin_hart · 2026-11-22
- Maryland's 1,300 MW coal plant can't retire until a transmission line Sierra Club opposes gets built — paulnovosad · 2026-11-22
- Reflection AI lets its Beam agent run a real vending machine to probe autonomy risk — alexpolozov · 2026-11-22
- AI Horizons Forum to convene experts on AI safety, policy and security ahead of pivotal 2027 — austinc3301 · 2026-11-22