When I query ChatGPT about a book or show I know well, it will start giving wrong answers after a few questions. I’ve had tell me that I was wrong when trying to correct it. I’ve also had ChatGPT generate syntactically invalid code that it provided results for. And valid code that produced different outputs from its explanation when I ran it. And then there are times when I’m having it generate fiction, and it gives me a nonsensical scenario. It’s also mistaken me for an LLM on one occasion.