Maybe. But that sounds like a large amount of bespoke work for what seems like a... | Hacker News

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

sanderjd 3 months ago | parent | context | favorite | on: Claude Sonnet 5

Maybe. But that sounds like a large amount of bespoke work for what seems like a common problem?

manojlds 3 months ago [–]

I was talking about enterprise agents and then realized the question is more about coding agents.

sanderjd 3 months ago | [–]

Ah I see! Yes, I was talking about a coding harness, not an enterprise agent. I entirely agree with you that your suggestion of driving it via evals is the right thing for that use case!

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