The most misunderstood graph in AI just got a major update
First seen 1d ago 路 1 article 路 momentum 6.8
METR
AI evaluation nonprofit METR released an updated report showing some AI capabilities continue to improve exponentially, though models lag in tasks requiring judgment compared to coding tasks.
Why it matters: This nuanced capability trend helps executives calibrate realistic expectations for AI performance in judgment-heavy versus technical business tasks.
Momentum over time