login sign up

Measuring AI Ability to Complete Long Software Tasks

metr.org
saved by
0 people
related read on
Andrej Karpathy — AGI is still a decade away from the discussion
I analyzed 180M jobs to see what jobs AI is actually repl... from the discussion
The Junior Hiring Crisis from the discussion
Vibe coding a bookshelf with Claude Code from the discussion
2025: The year in LLMs from the discussion
Where are the vibecoded Photoshops? from the discussion