AI labs should compete on a bench that's adversarial, such as go or Starcraft | Hacker News

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

kimjune01 4 months ago | parent | context | favorite | on: SWE-bench Verified no longer measures frontier cod...

AI labs should compete on a bench that's adversarial, such as go or Starcraft

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