[Loughla]

That is actually what I'm firmly convinced is the most dangerous thing about llm's. No matter what you put, it will always agree with you, and what's worse, it will try to make you think that you're unbelievably smart for saying x.

I used one to help me plan a sales route, and it kept fucking it up. Every time I corrected it, it tried that hand wringing vizier sort of ass kissing. It's very off-putting, but I can see how someone struggling with social interaction could be sucked into that nonsense.

[vonunov]

For what it's worth (or maybe just for the record) I have a counterexample: Gemini once dug in its heels and insisted that some ebay listings for GPUs were scams because the cards they were selling hadn't been released yet (they had been, but its training data was too old, I assume).

I went a few rounds with it and it kept pushing back, which was odd for sure, as I'm also used to being able to essentially just say "no, x = 2". There was a lot happening in that session (it was really someone else's and he just kind of lets his context windows fill up with all sorts of stuff), so I bet it would have sufficed to start a new one, but after a point I just wanted to see what would happen. It didn't concede until I sent it a PDF of some kind of white paper or tech spec sheet or something that included release dates from an authoritative source.

I may need to find that session later, because now I'm wondering if it was entirely the PDF that did it, or if it also helped to point out that the info cutoff could be a factor, and I don't remember whether I tried the latter first.

Also not sure off the top of my head what the situation was as far as model, custom instructions, or whatever else.

[fragmede]

My custom instructions to ChatGPT starts with "Never apologize", which seems to work.