A mix of evals and vibes. | Hacker News

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

bcherny 4 months ago | parent | context | favorite | on: Issue: Claude Code is unusable for complex enginee...

A mix of evals and vibes.

efields 4 months ago | [–]

"Evals and vibes" can I put that on a t shirt?

giwook 4 months ago | | [–]

What's that ratio exactly

capnchaos 4 months ago | [–]

Are you doing any Digital Twin testing or simulations? I imagine you can't test a product like Claude Code using traditional means.

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