One part that's kind of boring when playing a text adventure is trying things the original authors did not anticipate and getting a boring standard response. LLMs could make this part more interesting by adding more playful, hopefully even witty responses. If you're playing in the browser, this could even be using the Prompt API utilizing a small LLM that's running locally!
Also you could use LLMs for NPCs and for certain areas of the game, like mazes.
I'm sure there are way more possibilities. We're still at the very beginning. Just think about it: Everyone is complaining about LLMs hallucinating. Text adventures are an area where such hallucinations are desired.
> One part that's kind of boring when playing a text adventure is trying things the original authors did not anticipate and getting a boring standard response.
This happens mostly with old text adventures. Modern Interactive Fiction is really sophisticated, and you don't get many boring responses.
Example: in "Spider and Web", you're a captured spy being interrogated by your captors. If you say random gibberish, your interrogator will tell you (playing the role of the parser, but in a more interesting way). If you say something nonsensical, your interrogator will say "I'm losing my patience. No, that's not how it went", etc. Parsers are really, really sophisticated and they can make sense of contextual, unsaid information (or ask for clarification).
For more than a few decades, parsers no longer reply "you cannot do that".
Thanks for mentioning Spider and Web. It's by far my favorite modern take on a text adventure. There were a few moments that really blew my mind when I figured out how to progress.
Highly recommend anyone who is intrigued by the premise to just jump in and give it a go!
It's enjoyable to read the responses when you cannot do something. It's part of the game, baked into it.
More importantly, you and me will get the same shared experience we can discuss, unlike if we were playing with an LLM going on different, random tangents.
> Arguably, different responses would increase replayability.
Yes, but I don't think we're talking about the same kind of replayability. Certainly, not the kind I care about.
To me, replayability is a carefully constructed experience, by an author, and you explore it and find different things about it (say, like Adam Cadre's "9:05" [1]). But you can share your experience with another human, you can both go the same way and experience the same thing, and discuss it -- "hey, remember when you face the trolls in the cave, and...".
With an unconstrained LLM, you lose this. Plus, with no authorial voice behind it, I don't really care what a glorified stochastic automaton can produce.
(In case you're wondering, I find myself distancing from classic sandbox games as well... I used to like them, now I find them "too much work" for not enough payoff. With some exceptions, I much prefer a carefully curated gameplay experience).
But boring standard replies are also useful information that you do not need to do that, or that some object is not worth experimenting with. I can imagine it could become very difficult to solve puzzles in a game where the parser tried to be helpful and invent a clever reply to everything you try.
You will have to read more text as a result, but hopefully it is enjoyable. It's as if the authors of the game had anticipated your action and wrote something interesting.
# take mirror
Here are responses that gemma 3 27b just came up with:
1.
You peer closely at the mirror, running a hand over its ornate, dust-covered frame. It's… a mirror. A perfectly serviceable, if somewhat antique, looking glass. You study your reflection – slightly disheveled, perhaps a little heroic, definitely in need of a shave. After a moment of intense self-assessment, you realize it's just… a mirror. It reflects things. Fascinating, truly. But ultimately, not particularly useful for your current quest. You turn your attention back to the room, hoping for something a little more… engaging.
2.
You give the mirror a thorough examination. It's remarkably good at reflecting things. Truly a marvel of… glassmaking. You spend a full minute admiring your own adventurous visage, then decide that, while aesthetically pleasing, it doesn't exactly scream "essential adventuring gear." You move on, slightly disappointed in your own vanity.
3.
You study the mirror, tracing the intricate carvings around its edge. It feels… cold. Not just from the stone of the room, but a deeper, unsettling chill. As you gaze into its depths, you think you see something flicker at the edge of your vision, but when you focus, it's gone. It's a beautiful object, certainly, but it feels like it's watching you as much as you're watching it. Perhaps some things are best left undisturbed.
4.
You examine the mirror. Solidly mounted, and frankly, quite heavy. It's a beautiful piece, but entirely impractical to carry on your adventure. You decide to leave it be.
5.
You give the mirror a quick once-over. Just a mirror. Reflects things. Nothing to see here. You turn your attention back to the more promising corners of the room.
> Here are responses that gemma 3 27b just came up with
I think nobody doubts an LLM can come up with responses. But can it understand when it should NOT respond? Can it reign in its baked-in impulse to be "helpful"?
Most of the responses Gemma gave you are not appropriate for many kinds of games. What if the tone of the game is, on purpose (authorial choice), to be "unhelpful"? Or what if it's meant to be helpful but ONLY if you previously unlocked something? [1]
And how can you keep consistency long term? LLMs have a tendency to go off the rails and forget context.
[1] There's an Interactive Fiction game, whose name escapes me now, where you're trying to communicate with a derelict spaceship, with one survivor. The parser is the survivor. For reasons I won't spoil, garbled communications and misunderstandings are part of the game. It's your mission to figure this out and what the survivor really wants. If the LLM becomes "helpful" in its replies, it will spoil the game!
If you give the LLM more context (i.e. the player's past actions) and some directions such as "don't make any suggestions", I think you can get good results. Yes, they may not always be perfect.
For the types of responses, needed long term context shouldn't be required.
Anyway, I noticed that on a standard laptop, getting a response from the Chrome Prompt API running Gemini nano takes a rather long time.
I guess I'm skeptical you can steer current LLMs in this way, or at least, this hasn't been my experience.
I also worry not only about the loss of a shared experience among players, but also about the authorial voice... I find LLMs (even when prompted) tend to have an instantly recognizable style that I find unappealing.
Yes, all of this -- voice, tone, narrative direction -- could in theory be fixed with the right prompts, but I remain skeptical. From theory to practice seems such a long way...
oh gawd, peak LLM here. Have a local LLM talking to another LLM via API. Why? What's the point of you being there. Just wire up to computers to play Tic-Tac-Toe against each other. Maybe one of them will "learn" something after all.
Also you could use LLMs for NPCs and for certain areas of the game, like mazes.
I'm sure there are way more possibilities. We're still at the very beginning. Just think about it: Everyone is complaining about LLMs hallucinating. Text adventures are an area where such hallucinations are desired.