News for hackers. Stuff that matters.

A comment on Training language models to be warm and empathetic makes them less reliable. Parent comment

Re:Training language models to be warm and empathetic makes ... by layer8 on Tuesday August 12, 2025 @01:19PM (#44879293)
Many would be satisfied by an LLM that responds accurately and comprehensively, so I don’t understand that triangle. “Satisfying” is very subjective.
[ Parent | on HN ]
Re:Training language models to be warm and empathetic makes ... by csours on Tuesday August 12, 2025 @02:03PM (#44879786)
And LLMs are pretty good at picking up that subjective context
[ Parent | on HN ]
Re:Training language models to be warm and empathetic makes ... by layer8 on Tuesday August 12, 2025 @05:43PM (#44882131)
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.

[ Parent | on HN ]