> total 1000+ hours of real life software maintainer work captured in dataset. O... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

keybored 3 months ago | parent | context | favorite | on: FrontierCode: An eval to measure whether you would...

> total 1000+ hours of real life software maintainer work captured in dataset. ON TOP of that, 40+ hours of real human work to turn that real life work into well validated and structured tasks with rubrics (even more work to turn tasks/prompts from devin-infra-specific to pluggable coding agent)

Heartening. We still haven’t automated making the world worse.

swyx 3 months ago [–]

this gives my non tired self a chance to fix the typo:

- “ ON TOP of that, 40+ hours of real human work to turn…”

+ “ ON TOP of that, 40+ hours of real human work PER TASK to turn…”

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact