[drunken_thor]

I think AI could reinvent text based games in a fresh way that would be fun. Text based games were always so constrained by what the developer could guess that you would type but with AI it really could read more like an interactive choose your own adventure novel that is easy to navigate.

[jug]

These are kinda popular today in the form of AI Dungeon, NovelAI, FictionLab etc.

Basically you create characters with bios, traits. Then a setting/context. Now, as you write your story, you can have multiple characters involved and they'll act from their perspective and traits.

Then these also have lorebooks with triggers, so if you mention The Barking Dog Inn, the AI and the characters will know what you mean and your characters with an outgoing personality type will be more eager to go there than others etc.

Finally, these systems usually have a long term memory where key events are saved and the AI remembers.

So a lot of this already exists!

[dmarcos]

What's your favorite game of this type?

[bunderbunder]

I'm not so sure.

In earlier text adventures (e.g., Infocom games), some portion of those constraints were due to the authors failing to anticipate legitimate ways that users would try to phrase things and account for them in the game. But that's not nearly such a problem in anything made since the late '90s, especially if you stick to xyzzy award winners.

The more essential reason for that constraint is that it's just good storytelling. The author of a work of IF has an idea they want to explore. That main idea could be narrative (Photopia or Anchorhead), or it could be a gameplay mechanic (Savoir-Faire or Counterfeit Monkey). But in any case, if your goal is to appreciate the creator's vision, those constraints are critical because they telegraph to you, the player, what you should and should not be exploring.

This isn't an idea that's specific to text adventures, either. The creators of the Outer Wilds deliberately made areas flat and boring when there wasn't anything there for the player to do to advance the story, specifically because they didn't want players wasting time on exploration that would ultimately prove to be pointless. This is also why open world games that do go for a more uniformly detailed world also need to hand-hold the player and tell them where they need to go every step of the way. Without that players would tend to get lost, lose their sense of progress, and ultimately end up bored.

I think that, because of this dynamic, using AI to flesh out the unimportant bits of the game would be a cardinal game design sin. Making bloat cheap and easy does not make it good. I just makes more of it.

[vector_spaces]

There are a few companies doing this already -- I think AI Dungeon was one of the first movers in this space. I don't know how it is as a user, though

[jwatermelon]

There is a new text based game using AI called Lifespans. You create a character, and live out a simulated life. You can make any decision or action that you want, and there is a D20 roll mechanic to make sure that your decisions make sense. You can play it at lifespans.app

[Nevermark]

That was one of my first tests of ChatGPU.

It was actually an incredible experience … except for the quick “game” truncation.

Be interesting to see how Claw can improve on that. Give it some serious design time first.

Also thought about how a smart expansion of Zork would play.

[Copyrightest]

As another commenter points out, this sort of exists in the broader sense of "interactive fiction." There's lots of options for scaffolding an LLM into something like a storytelling toy.

But I truly believe an AI-generated equivalent of Zork or Lost Pig is decades away. The "knowing what it is talking about problem" is not even close to being solved, no matter how impressive coding agents have become. It is simply too easy to sabotage clever game design with accidentally adversarial prompting.

More generally: LLMs are still unfunny except in cases of clear plagiarism. This also extends to making fun games.