logoalt Hacker News

Loughlatoday at 12:30 AM1 replyview on HN

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.


Replies

fragmedetoday at 12:40 AM

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