Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- what are your thoughts on using LLM as a judge for auto evals?
- IMO, if you break down the criteria enough, LLM or not wouldn't be a problem. But if you feed a long answer to it and ask LLM if it's a good answer, then it will be hit or miss.by anphamthanh