They work much better off a test that must pass. That they can “see”. Without it... | Hacker News

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

mattarm 6 months ago | parent | context | favorite | on: Opus 4.5 is not the normal AI agent experience tha...

They work much better off a test that must pass. That they can “see”. Without it they are just making up some other acceptance criteria.

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