Andrej Karpathy said it plainly in 2023: language models do not know they are wrong. They have no internal signal that flags uncertainty. They generate the most probable continuation of whatever you gave them, and they do it with the same confidence whether the output is correct or completely f...
Source: [Dev.to](https://dev.to/gmoustakas/your-ai-assistant-is-not-hallucinating-its-guessing-and-you-asked-it-to-guess-56of)