METR Blog company blog

Measuring AI Ability to Complete Long Tasks

We propose measuring AI performance in terms of the length of tasks AI agents can complete. We show that this metric has been consistently exponentially increasing over the past 6 years, with a doubling time of around 7 months. Extrapolating this trend predicts that, in under a decade, we will see AI agents that can…
Points
247
HN comments
193
Submissions
1
Cited by
25 commenters

AI & Machine Learning2025

On Hacker News

SubmittedTitle on HNPointsComments
Dec 21, 2025Measuring AI Ability to Complete Long Tasks by spicypete247193

Cited in comments

Linked from 34 Hacker News comments by 25 different people, from Apr 2025 to Jun 2026.

Most recent:

Search every comment that links here →

More from METR Blog

All 6 posts →

Related posts from the same era