I grew up on the Infocom games and when microsoft actually open-sourced Zork 1/2/3 I really wanted to figure out how to use LLMs to let you type whatever you want, I always found the amount language that the games "understood" to be so limiting - even if it was pretty state of the art at the time.
So I figured out how to wrap it with Tambo.. (and run the game engine in the browser) basically whatever you type gets "translated" into zork-speak and passed to the game - and then the LLM takes the game's output and optionally adds flavor. (the little ">_" button at the top exposes the actual game input)
What was a big surprise to me is multi-turn instructions - you can ask it to "Explore all the rooms in the house until you can't find any more" and it will plug away at the game for 10+ "turns" at a time... like Claude Code for Zork or something
But when I tried this, I literally couldn't stop. I could just write some random action.
It's actually amazing to me how many situations they were able to consider in the game, but having the LLM translate my language into the right action made the game feel way more natural.
I'd be interested in seeing how people can dress up these games with images, or more complex interactions. It could be a whole sub-genre.
reply