62 comments

[ 2.1 ms ] story [ 63.3 ms ] thread
This is such a fun concept!
It did not like Backyard Starship, most likely its not something it has in its memory
Really cool! I'm guessing the site is getting hammered currently cause I hit rate limit on first attempt, but looking forward to trying it out later when the hug loosens.

Sorry for the predictable question, but any plans to open source?

I was working in an implementation of a vis novel type game for my own screenplays and manuscripts. I ended up building a deck builder.
I like the idea. Looks like it hit a rate limit. Was trying to try Dungeon Crawler Carl.
Super cool idea! What's your plan for dealing with copyright complaints?
Harry potter Matilda - are you sure there’s no legal risk here ? ( independently of the coolness of the project)
This is so cool, and slick. Unfortunately, the actual adventure part isn't loading so don't know what it feels like
Would love to try this, but it seems like you hit a limit. Is there a working example you can link to?
This is an awesome concept! The latency makes it a rough UX, but the core idea and direction feel right.
This will be amazing with Project Hail Mary!
Feels like only a couple of years before AIs can take a movie and reconstruct it entirely as an "open world" VR experience.
great idea, but I wonder about copyright and also hitting a rate limit
Don't use copyrighted books. Use Gutenberg for these kind of tools.
How do tools like this avoid what I see in many of these types of narrative chat bots: the user becomes the only one steering the narrative, and the AI ends up just an obedient responder? Whenever I try these things it ends up very predictable, shallow, and repetitive, especially as time goes on. And if I have to prompt the AI to be creative or act differently... is that really acting different?
Neat, but it has problems following in-universe rules, i.e. fantasy novels.
If art is communication- and i believe it is- why would i want to read or listen to anything AI generated? Once you are done with consuption there is no point in reflecting on it nor having a conversation about it with other fellow humans. People are not even interested in each others dreams most of the time. Unless the machine is of godlike intelligence there is just zero point.
Well done! I’ve built this same sort of thing for my family to play with. My advice for the best results:

1) Structure the choices offered by the LLM; add “choice_type” and add instructions to the LLM on what those choices should do. E.g. action, dialogue, investigation, whatever makes sense for the genre—the LLM can even generate these at story start—then “choice should direct the narrator to focus on an action-oriented moment”, “choice should direct the narrator to focus on a dialogue between two or more characters in the scene”, etc.

2) Use reasoning whenever making tool calls for choices, summarize the reasoning, and include it in narrative summaries provided as part of the context for future narrative requests. For example, the combined summary might be: “In the last narrative I wrote for the user, Harry and Luna were startled by the noise coming from the edge of the forest. Important scene developments: 1) Luna and Harry had been approaching the edge of the forbidden forest for the last three narrative turns, and in the turn I just wrote they arrived at the edge. 2) Harry seemed to be the more courageous of the two in previous narrative turns, but in the most recent one, the user’s choice resulted in Harry becoming more deferential to Luna. 3) In the most recent narrative turn, the noise that had been emanating from the forest was now accompanied by a flickering light. I then suggested paths that would allow for character development through dialogue between Harry and Luna (I gave two options here), a path to move the story forward by having Harry take Luna’s hand before running into the forest, and another path that would slow the pace by having Luna investigate the flickering light accompanying the sound. The user’s choice: ‘Have Luna investigate the flickering light.’

3) Add an RNG weighted by story length or whatever works for you that will result in choices that lead the story to a conclusion. Include that direction in the tool call for generating choices, along with a countdown to the finale choice.

This is a rough mental sketch of what worked the best for me, i purposefully left out implementation or application details, as I don’t know what you’re wanting to do next.

Good luck, looks great!

I'm curious what happens if you throw something like Ulysses by James Joyce at it.
Now this is going to be amazing if we somehow get a structured thing for Dungeon Crawler Carl, I would imagine myself as a crawler wandering around that would be epic, but this requires a lot of options to be made consistent with everything.

Awesome job and idea!

It's a pretty cool proof of concept. I did run into some weirdness with it right away when trying the Harry Potter book. The app kept switching between 2nd and 3rd person for Harry.

The main thing for me, though, was the feeling of emptiness I got while playing. I love text adventures, having grown up with Infocom games. The thing about them is that you can feel the choices made by the writer / programmer, just like you can feel the human author behind a book.

I'm sure part of what feels empty to me is because I know it was autogenerated. But I feel that even if I was shown this without knowing an LLM was behind it, the gameplay wouldn't be as rewarding as something written by a human using Inform.