Choose-Your-Own-Adventure AI Dungeon Games
1–10 of 25 posts
Re: Choose-Your-Own-Adventure AI Dungeon Games
#2I'm an AI dungeon subscriber, and what I like about it is that it reacts to whatever I can think of to say. If it was mostly predefined options, I'd probably not be interested in it: there are plenty of interactive fiction games already, and they're crafted by humans and generally better-written than what AID could ever come up with. Personally, I enjoy the looseness, how you have to kind of hold the AI's hand and steer the scene yourself. I doubt I'm representative of most people, but I think the number of people who would pay for a CYOA text adventure game is pretty low anyway. Latitude might as well stick with weirdos like me for awhile, and pray that the overhead costs come down.
Re: Choose-Your-Own-Adventure AI Dungeon Games
#3You would have to retrain the model to incorporate a global context if you wanted to get a coherent adventure / DMing experience out of it. Once the text tokens (256-2048 depending on the model I believe) go out of scope, they are no longer used for future responses. There's no reason you couldn't build a model around an encoding of a coherent world and then let the GPT part assemble the prose other than actually training and designing such a model. If no man's sky can do procedural worlds, I see no reason why you couldn't do the same thing for text adventures.
Re: Choose-Your-Own-Adventure AI Dungeon Games
#4I'm reasonably confident I've seen a cyoa implemented like this get posted to HN, but I can't find the link offhand.
Re: Choose-Your-Own-Adventure AI Dungeon Games
#5I'm an AI dungeon subscriber, and what I like about it is that it reacts to whatever I can think of to say. If it was mostly predefined options, I'd probably not be interested in it: there are plenty of interactive fiction games already, and they're crafted by humans and generally better-written than what AID could ever come up with. Personally, I enjoy the looseness, how you have to kind of hold the AI's hand and st…
I didn't personally enjoy AI dungeon too much because of how loose it felt - nothing was defined and anything goes - but I hear people describe it like you did, and it sounds similar to how I heard lucid dreaming described - you're simultaneously driving but also part of the experience.
Re: Choose-Your-Own-Adventure AI Dungeon Games
#6You would have to retrain the model to incorporate a global context if you wanted to get a coherent adventure / DMing experience out of it. Once the text tokens (256-2048 depending on the model I believe) go out of scope, they are no longer used for future responses. There's no reason you couldn't build a model around an encoding of a coherent world and then let the GPT part assemble the prose other than actually tra…
I think people are in agreement with this conceptually, and the challenge is figuring out how to effectively implement it. I'd certainly love to see a hybrid like this with a coherent world model, but for example, how do you avoid the existing challenges with procedural worlds where you're basically limited to combinatorial combinations of a small number of primitive features? If the free-form text can't affect more than toggling of predetermined procedural state combinations, it's basically just an interface to a traditional world sim with more window dressing.
Re: Choose-Your-Own-Adventure AI Dungeon Games
#7Many years ago I did some experimentation with the idea of slapping a very crude "parser" (no AI involved, just extremely basic string matching) on top of a Lone Wolf CYOA book which was made public via Project Aon [0]. I wrote about it here [1], and the result is still playable here [2].
[0] https://www.projectaon.org/en/Main/Books
Re: Choose-Your-Own-Adventure AI Dungeon Games
#8You would have to retrain the model to incorporate a global context if you wanted to get a coherent adventure / DMing experience out of it. Once the text tokens (256-2048 depending on the model I believe) go out of scope, they are no longer used for future responses. There's no reason you couldn't build a model around an encoding of a coherent world and then let the GPT part assemble the prose other than actually tra…
I think people are in agreement with this conceptually, and the challenge is figuring out how to effectively implement it. I'd certainly love to see a hybrid like this with a coherent world model, but for example, how do you avoid the existing challenges with procedural worlds where you're basically limited to combinatorial combinations of a small number of primitive features? If the free-form text can't affect more…
I would start with a rogue-like game and the hard part becomes generating the training data to describe in beautifully flowing prose what happens on a per move basis. Enter your patient friend who offers to do this and has run lots of campaigns previously.
It seems like something that could be trained starting with an existing GPT model and specialized to this task to me, but I'm just brain farting here. And by all means steal this idea if you're so inclined.
Re: Choose-Your-Own-Adventure AI Dungeon Games
#9Earlier quoted context omitted.
I think people are in agreement with this conceptually, and the challenge is figuring out how to effectively implement it. I'd certainly love to see a hybrid like this with a coherent world model, but for example, how do you avoid the existing challenges with procedural worlds where you're basically limited to combinatorial combinations of a small number of primitive features? If the free-form text can't affect more…
I would start with a rogue-like game and the hard part becomes generating the training data to describe in beautifully flowing prose what happens on a per move basis. Enter your patient friend who offers to do this and has run lots of campaigns previously. It seems like something that could be trained starting with an existing GPT model and specialized to this task to me, but I'm just brain farting here. And by all m…
It seems like the hardest part isn't world model -> prose (still hard tbc), but prose -> world model. There have been games for a long time that let you interact with a world model via simple verb + object statements (e.g. "get key", "search chest"), but the power of GPT3-style AI dungeons isn't just that it handles longer, more natural text input, it's that there are no restrictions on the (short-term, incoherent) world model they use to generate responses. If you want to "throw key at the biggest goblin", you'll get a response that's coherent (in the short term) instead of an error saying that you can't do that with keys.
When you pair a better, prosier text input-response system with a procedural world model, if the procedural world model is built like existing ones you'll still have to deal with restrictions in the world's content and the valid interactions between constituents. At which point all that fancy AI makes for a more natural parser but doesn't add any richness to the game world, which is the thing we'd like to get at.
If anyone has ideas for how to solve the prose -> world model problem, that could be super fun and rewarding to work on, probably so much so that they wouldn't be sharing them here :(
Re: Choose-Your-Own-Adventure AI Dungeon Games
#10Earlier quoted context omitted.
I would start with a rogue-like game and the hard part becomes generating the training data to describe in beautifully flowing prose what happens on a per move basis. Enter your patient friend who offers to do this and has run lots of campaigns previously. It seems like something that could be trained starting with an existing GPT model and specialized to this task to me, but I'm just brain farting here. And by all m…
It seems like the hardest part isn't world model -> prose (still hard tbc), but prose -> world model. There have been games for a long time that let you interact with a world model via simple verb + object statements (e.g. "get key", "search chest"), but the power of GPT3-style AI dungeons isn't just that it handles longer, more natural text input, it's that there are no restrictions on the (short-term, incoherent) w…
There's a really interesting cross-over here with literary structure. You need to teach a model to recognize tone, theme, and setting in addition to world "facts."
What makes a world like Westeros different than the Shire isn't just facts like "seasons are really long" but elements of tension, political unrest, and the outlook of the people who inhabit it. To do this effectively, you need to be building simulations of literary works. There's always going to be an art to this, but instead of the manuscript, it's going to be about the parts of the model.