[Johnwbh]

You could also potentially specify constraints on a book and have it generated for you, e.g. generate me a book about a gay dutch vampire in the 1800s. Could open up a whole new concept of hyper speciaised books tailored for individuals particular desires and preferences.

The practical problem with this is that, as I understand it, the deep learning system needs a pretty large data set to work with to infer rules from. You can do this with go because there is a constraint on legal moves and a deterministic win condition, but given how vast the number of potential novels is (If we count the space of all ten thousand word collections of grammatically acceptable sentences) the existing number of novels may no be enough to infer a pattern. (Though possibly you could split the problem up by separately doing the natural language processing and abstractin out the plot)

[saalweachter]

Ignoring the training problem, apply it to movies: I'd like to see this movie, but starring these actors, directed by this director, with a soundtrack by this composer/band.