LLMs reward expertise

Re:LLMs reward expertise by lagrange77 on Monday August 03, 2026 @08:01PM (#49162905)

I thought exactly the same at first. But then i wondered if that still holds true with today's advanced thinking, RLHF involved, frontier models. I guess to a certain extend it did indeed behave better, as a reaction to his self description into account.

EDIT: I mean, those systems accumulated so much complexity around the attention based next token predictor.

[ Parent | on HN ]

Re:LLMs reward expertise by beering on Monday August 03, 2026 @09:48PM (#49163534)

Training the LLM to do things that the user didn’t explicitly ask for is a good way to get complaints from the users. Doesn’t matter if those things are best practices.

[ Parent | on HN ]

Re:LLMs reward expertise by PaulStatezny on Tuesday August 04, 2026 @01:24AM (#49164617)

Yeah, in my experience, there's nothing about:

1. LLM thinking 2. RLHF 3. The latest frontier models

that does anything to change this fundamental "suggestibility" of LLMs.

But who knows, maybe I'm wrong.

[ Parent | on HN ]