Many would be satisfied by an LLM that responds accurately and comprehensively, ... | Hacker News

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

		layer8 5 months ago \| parent \| context \| favorite \| on: Training language models to be warm and empathetic... Many would be satisfied by an LLM that responds accurately and comprehensively, so I don’t understand that triangle. “Satisfying” is very subjective.

csours 5 months ago [–]

And LLMs are pretty good at picking up that subjective context

layer8 5 months ago | [–]

How would they possibly do that on a first prompt? Furthermore, I don’t generally let LLMs know about my (dis)satisfaction level.

This all doesn’t make sense to me.

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