> Of course, it's entirely possible that ChatGPT doesn't understand its own limitations and inner workings. And when we ask it how it works, it just makes up a plausible answer.
It’s just paraphrasing what other people have said about it.
My mental model of how ChatGPT might superficially "understand" its own limitations would be because, for example, it might have been specifically trained by people who do understand the limitations of the system.
It’s just paraphrasing what other people have said about it.