[hackit2]

ChatGPT like all transformers (language models) depends on how well you prime the model as it can only predict the next series of tokens over a finite probability space (the dimensions it was trained on) , it is up to you as the prompt creator to prime that model so it can be used as a foundation for further reasoning.

Normally people who get bad results from it would also get similar results if they asked a domain expert. Similarly different knowledge domains use a different corpus of text for their core axioms/premises, so if you don't know the domain area or those keywords your not going to be able to prime the model to get anything meaningful from it.