Hacker News Reader

Comment by sirtaj | Hacker News Reader

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.

View on HN

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.

I've been playing around with this stuff for around a year too, mixing deterministic-ish simulation with AI comms, decision making and story guidance. There are flashes of cool, but the work to guide it to write good stories with what you have often takes just as much effort as writing the story. Fine, you've written a situation generator. Now you have to tell it what kind of situations are compelling, without them feeling like cookie-cutter templates. Then what you're doing is writing.

Thanks for the Emergent Garden rec, looks interesting.

Reply on news.ycombinator.com