[lukan]

"There's an obvious problem with the concept of training on user prompts; how would training on a bunch of questions cause it to know the answers?"

I imagine by analysing the chat? If the user says thanks in the end, or gives a thumps up, it likely was a useful and correct answer, that could be included in further training. Or at least considered for future training and I cannot imagine them not considering and experimenting with it.