> LLMs of today copy a lot of human behavior
Funny, I would say they copy almost no human behavior other than writing a continuation of an existing text.
Funny, I would say they copy almost no human behavior other than writing a continuation of an existing text.
An LLM has to predict entire conversations with dozens of users, where each user has his own behaviors, beliefs and more. That's the kind of thing pre-training forces it to do.
LLMs are capable of keeping track of consistent behaviors and beliefs, and they sure try. Are they perfect at it? Certainly not. They're pretty good at it though.