News for hackers. Stuff that matters.

A comment on Ask HN: Good LLM Observability Platforms?.

Re:Ask HN: Good LLM Observability Platforms? by uaas on Monday October 27, 2025 @03:26AM (#45718237)
I am curious, what’s the point of re-running these interactions on a UI?
[ Parent | on HN ]
Re:Ask HN: Good LLM Observability Platforms? by muzani on Tuesday October 28, 2025 @05:49AM (#45730896)
Reproduction I suppose. I would like the same things as OP too.

LLM outputs are qualitative; they can't really be automatically scored and prompt enhancements tend to multiply the bug. It can solve a problem, but introduce a new one. It's practical just to do it manually.

[ Parent | on HN ]