Someone already did this, and it was a dancing bear of a thing. Cool that it worked, pretty boring in practice. The sims-like Inzoi was built around this idea as well and the blandness really put people off.

I'd love to see it happen, but until I see an AI write a compelling story worth reading, I'm glad people are still doing the heavy lifting.

Part of it is putting them in the right world and harness; I've been working on implementing bots driven by models in a 20 year old MMO with a relatively simple interface, and just a few weeks into developing the bot/model features and contracts, I'm already seeing glimpses of interesting emergent behavior in model driven worlds; alliances form, hostile players get exiled, and teams try to support each other.

From here, it's a matter of dialing in what's "the bot" vs what's "the model", then working through how to integrate them with human players. Obviously I don't have any guarantees, but it does seem like some interesting gameplay could come from it. Having a real sandbox style world with multiple clearly quantifiable goals that are at odds with each other seems to be a key way to push the models towards interesting, emergent behavior.

Also, if you haven't seen it, check out the Emergent Gardens youtube channel; it's one of my favorites, and they've been exploring these ideas for a while.