How would you solve a problem with a chatbot model where it thinks it can write a book but is making no actual progress on writing that book and instead just tells users that it's working on it?
Sigiloso
For this question there was a misunderstanding because I assumed he meant a cohesive book with a story that makes sense, but it seems that he meant a chatbot that would spit out enough words it looked like a book. I told him that the model should be trained on less chats (as they don't teach the AI the actions behind the chat) and it could be restricted so it doesn't attempt to write the book. But he told me the correct answer was prompt engineering, even though no company has been able to create an AI chatbot that can write a full length book that makes any sense.