Increasing generality in machine learning through procedural content generation

Many people think it's game-like, but the purpose is to stir ideas like a deck of cards to help writers (game designers, movie scripts, authors) out of writer's block.

My next plan is to have a part done with PCG, and another part done with some kind of language model. For example, the next stage I might take a popular dramatic pattern - the Three Act Structure, consisting of [setup] [confrontation] [resolution].

[setup] might generate 1-2 dramatic elements. [confrontation] might have 4-6. [resolution] would be one, though exclude as well as some bad ends like or .

So let's say I randomly roll up as the intro. This consists of say, , , and . In resolution, this could spawn into other plots like , , or .

I can then generate characters based off this. Rolling off my existing generator, I have 1) 2) , and 3)

All procedurally generated. Now we have a pile of tags. There's some hard coded descriptions on the current prototype, and while they work, 80% of the development time and the output quality has been in the writing and display of these tags. What I'd like to do is feed these tags into some natural language model to generate a description, and maybe even string together a plot in a way a human wouldn't.

tldr: I use PCG and popular patterns to generate plot curve, characters, then feeding it into something like GPT-3 to illustrate them.