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.
Ehhh better to be safe that have a discussion on religion and persecution in the issues board. Then it doesnt linger as an open ticket.
I feel like discussion about something like this is better suited for like a forum or a dedicated discussion channel. They discuss in a followup on the issue thread that they think even one offended person is too many, and they want to be as neutral as possible, which I think is commendable.
I think even if its a troll, its better to err on the side of “what if it is a real person, and they are offended.” Obviously, this needs to be taken within reason, like intolerance is not a valid reason etc etc.