Related video: Anthropic mathematician claims Claude helped prove Riemann Hypothesis in six weeks, @TheAIGRID
Trending on MIT Technology Review AIMETR updates key AI capability chart, finds continued exponential gains but judgment gaps
MIT Technology Review · · 25-second read
Top comments from YouTube.
November 20, 2026 · Emerging AI
The AI evaluation nonprofit METR released an updated version of its time horizon plot, a widely watched chart tracking AI capability improvements. The new data shows that some AI abilities continue to improve along an exponential trajectory, but the report also reveals a meaningful gap: models perform much better on coding and similar technical tasks than on work requiring judgment.
This update to the influential chart matters because it complicates the narrative around AI progress. While raw capability in certain domains is accelerating, the data suggests different skills progress at different rates—and judgment-intensive tasks remain a stubborn challenge for current systems.
This is an AI-written summary. The original reporting belongs to MIT Technology Review. How we write these · Spot a mistake?
Get the AI brief every morning.
The five AI stories that matter each morning: startups, money, jobs, tech and what's coming next. Free, and one click to unsubscribe. See our Privacy Policy.