What makes you believe people haven't tried? I have yet to find an example that actually works.
The language models have a tendency to not stick to the script (inventing world state that does not exist), be too helpul (provide spoilers), or get stuck on the same confusions as a human would.
You want the language model in the interface -- to parse the input text and convert it to a more structured command language internally.
That would solve the main UX problem with the genre.