We should first check how accurate is the LLM judge instead of blindly trusting ... | Hacker News

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

efilife 59 days ago | parent | context | favorite | on: Are AI labs pelicanmaxxing?

We should first check how accurate is the LLM judge instead of blindly trusting it. And it seems to be very inaccurate

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