Show HN: I built an AI that turns any book into a text adventure game

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!

Anecdote on my side, but Grok 4 was the first model that didn't feel like that to me. Maybe my conversations were just not long enough for it to fallback to sycophantic behavior.

I've had similar experiences with vanilla ChatGPT as a DM but I bet with clever prompt engineering and context window management you could solve or at least dramatically improve the experience. For example, you could have the model execute a planning step before your session in which it generates a plot outline, character list, story tree, etc. which could then be used for reference during the game session.

One problem that would probably still linger is model agreeableness, i.e. despite preparation, models have a tendency to say yes to whatever you ask for, and everybody knows a good DM needs to know when to say no.

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.

I neither made this assumption nor the conclusion.