Using the AI in multiple phases is the approach that can handle this.
Similarly to "Deep Research" approach - you can tell it to first generate a storyline with multiple twists and turns. Then ask the model to take this storyline and generate prompts for individual chapters. Then ask it to generate the individual chapters based on the prompts, etc.
But a future chatbot would be able to internally project manage itself through that process, of first emitting an outline, then producing draft chapters, then going back and critiquing itself and finally rewriting the whole thing.
Yes, and that's why many people in the discussion here are very optimistic that chatbots will have solve this problem very soon. Either with the approach you suggest, or with something else (and perhaps more general, and less directly programmed in).
It's not a problem of one-shotting it. It's that the details cause a collapse. Even if you tried breaking it down which i have, you'd run into the same problem unless you tried holding its hand for every single page and then - what's the point ? I want to read the story not co-author it.
I dunno, there's a certain amount of fun in "writing" a book with ChatGPT. Like playing a video game with a bunch of different endings instead of a watch a movie with only one. does the hero save the day? or turn into a villian! you decide!
The etymology is pretty much irrelevant. In eg German, the word for novel is 'Roman'. But German readers don't expect their novels to be anymore romantic, nor do English readers expect their novels to be more novel.
LLMs have been producing new things all the time. The question was always about quality of output, never about being able to produce anything new.
