Skip to content
AI IntelligenceNov 20, 2026AI Intelligence
Article

METR updated its time horizon plot to include judgment-heavy tasks…

…finding some AI capabilities continue to grow exponentially while models lag at designing AI evaluations. The report from the AI evaluation nonprofit suggests capability gains are uneven across task types.

AI-generated: summaries written by AI from the linked sources. How we use AI

AI-generatedSource: MIT Technology Review
01

Source Brief

METR updated its time horizon plot to include judgment-heavy tasks, finding some AI capabilities continue to grow exponentially while models lag at designing AI evaluations. The report from the AI evaluation nonprofit suggests capability gains are uneven across task types.