I don’t think we’ll see this any time soon, because corpos probably won’t listen to any creative that presents this, but I want something where the LLM runs locally and is just used to interpret what you are asking for but the dialogue responses are all still written by a writer. Then you can make the user interaction feel more intuitive, but the design of the story and mechanics can just respond to the implied tone, questions, prompts, keywords from the user.
Then you could have a dialogue tree that responds with a nice well constructed narrative, but a user who asked something casually vs accusatory might end up with slightly different information.
Now I love boiling down the pitfalls of modern western society into large statements like “capitalism bad” and “communism good” as much as anyone, but having dealt with a bunch of people dismiss good change as “that’s communism” has made me rethink how I talk about topics online and in person.
Now the accelerationist are gonna be mad about this for sure, but maybe you should start small, and discuss topics at a more local level. Then again the internet is world wide and everyone wants to talk about grand scale things.
Basically, I’ve stopped telling people outside of my direct circle that leftism cool, and instead talk about socialised medicine programs, pushing for support of worker owned productions and business, getting involved with coop housing. Lot easier when you don’t have to bump up against the red scare.