Ideas & society2025 · shared on Hacker News
Measuring AI Ability to Complete Long Tasks
Explore Measuring AI Ability to Complete Long Tasks, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Ybeyarkay ·
Beliefs that are true for regular software but false when applied to AI
537 points452 comments
YLAsteNERD ·
A conversation about AI for science with Jason Pruet
164 points147 comments
Ynopinsight ·
Forecaster reacts: METR's bombshell paper about AI acceleration
49 points74 comments
Ymellosouls ·
Measuring AI Ability to Complete Long Tasks
5 points0 comments
Ymefengl ·
Measuring AI Ability to Complete Long Tasks
4 points0 comments
Ysonabinu ·
Measuring AI Ability to Complete Long Tasks
3 points0 comments
Ychriskanan ·
Measuring AI Ability to Complete Long Tasks
2 points0 comments
Yozozozd ·
Ask HN: Why would we care about "extended time horizons" and LLMs?
2 points0 comments
Ys-macke ·
Measuring AI Ability to Complete Long Tasks
1 points0 comments
YTomte ·
The Sigmoids Won't Save You
1 points0 comments