Hacker News new | past | comments | ask | show | jobs | submit | from login

LLM as a Judge: Numeric Score Evals Are Broken (twitter.com/aparnadhinak) 1 point by tosh 8 months ago | past Gemini Pro suffers in RAG (compared to GPT-4-turbo, Claude 2.1) (twitter.com/aparnadhinak) 3 points by behnamoh 9 months ago | past

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