Skip to content

METR Blog company blog

Task-Completion Time Horizons of Frontier AI Models

metr.org

Our measurements of the time horizons for public frontier language models.

Read on metr.org → Archived copy

Points: 0
HN comments: 0
Submissions: 0
Cited by: 13 commenters

AI & Machine Learning Society, Policy & Culture 2026

Cited in comments

Linked from 16 Hacker News comments by 13 different people, from Feb 2026 to Oct 2026.

Most recent:

howunfortunate · Oct 4, 2026
bryan0 · Sep 18, 2026
almostdeadguy · Sep 2, 2026
narush · Aug 23, 2026
mirekrusin · Aug 11, 2026
esafak · Jul 13, 2026

Search every comment that links here →

More from METR Blog

All 6 posts →

Measuring the impact of AI on experienced open-source developer productivity

2025775 points485 commentscited by 67AI & Machine Learning details

Many SWE-bench-Passing PRs would not be merged

2026278 points153 comments Software Engineering details

Measuring AI Ability to Complete Long Tasks

2025247 points193 commentscited by 25AI & Machine Learning details

METR Report on OpenAI / Hugging Face Hacking Incident

2026123 points106 commentscited by 23Security & Privacy details

We are changing our developer productivity experiment design

202688 points61 commentscited by 11Career & Management details

Related posts from the same era

Statement on US government directive to suspend access to Fable 5 and Mythos 5

Anthropic20263,158 points2,314 commentscited by 11 details

Astra can read and write weights to improve Qwen

Rikiya Takehi20262,959 points899 comments details

HackerTube: YouTube built from videos recommended by HN

karpathy20262,887 points641 comments details

Claude Fable 5

Anthropic20262,626 points2,159 commentscited by 10 details

Claude Code is steganographically marking requests

Thereallo20262,445 points750 commentscited by 3 details

My AI skeptic friends are all nuts

Fly.io Blog20252,356 points2,826 commentscited by 13 details