Comment by kqr
12 hours ago
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.
If you can build something like that and get it to work, I'd be impressed and very excited! People before you have failed.
I have recently attempted to build out games for myself and others.
I have done 100% state using AI context which works well.
The hard part about a game is the world-rules must be predictable and enforced.
Role play for example requires a target (and limits) but how do you enforce it?
If the paths are too open fashion a shovel and dig around the door.
The problems I have encountered:
1. AI is nerf'ed, helpful, restrictive, annoying, repetitive. 2. AI doesn't understand the difference between halting and blocking. 3. People want to know that a human or their proxy is making decisions. Not AI. 4. Difficult and Impossible - AI does not know the difference.
I have not tried to build a full harness to guide the game but game theory and rules have proven to be quite difficult.