This looks to be all about MUDs but when I hear "text-based gaming" I think of infocom style games like zork or even games like Hunt the Wumpus, Legend of the Red Dragon, or the old Palm OS game Space Trader
You can run the original Palm version in a browser with CloudpilotEmu. Works great on my phone when I just have to scratch the itch. https://cloudpilot-emu.github.io/
AI would be good for text adventures in that it could make actions a lot more natural too. Less time hunting for the exact verb and noun you're expected to use.
Yep. AI Dungeon proved this a while ago (you can do anything you say you can), but the engine suffers from a lack of constraints. It's like a D&D game played by drunk edgelords DMed by someone on acid.
You as King Arthur giving up on Excalibur and slaying a dragon with the BFG 9000 before dying on your chamberpot from dysentery is allowed to happen.
That's where Inform[ish] comes in. You can implement a level of sanity to the story that the verbs have to work around. Doing something ridiculous like `ride the Rat King` is still going to kill you if he's flagged as aggressive (as opposed to working through your differences and going on a journey together, bonding with the trusty steed you just subjugated).
You cannot engage in rat diplomacy. They are never to be trusted!
"AI Dungeon" I believe attempted this. I recall hearing it did indeed make a good parser, but the major issue was around context depth.
I wonder what it'd take to use an LLM as a parser, with ground truth available from a separate game instance, and the LLM's role limited to providing descriptions and handling player input. That might be a good way to get structure and consistency while not losing the improvisational, storytelling sort of vibe.
“would be... could...” seems unnecessarily cautious language given that AI text adventures/RP are very much a thing.
(Another strength is that you can have a usable and entertaining one just with little more than text for the starting point, and description of the tone/premise, and a handful of sample interactions.)
That last book looks interesting but I would love if it was available on Amazon, or somewhere more international, usually other places don't deliver correctly on my country. :/
Hello, I am making a text-based based game. Part text adventure, part something else and I am jumping at opportunity to build a community of "testers". Can I email you ?
I love LambdaMOO's parsing system. Especially how it matches verbs, objects, predicates.
I love C#. Especially using Reflection and Attributes. I'm using Method Attributes to decorate like how LambdaMOO has a toy duck you can wind, [Verb("wind", Specifier.This)] void Wind() {}.
I love xterm.js.
I love Web Sockets.
So, I'm trying to cram them all together. I kind of want to make a server that can support multiple single-player Text Adventure games happening at the same time... and I also kind of want to make a MUD.
Slightly off topic, but would love for a blog like this to give insight into. With generative AI becoming more consistent (controlnet etc) and almost certainly faster in the not too distant future. Will we reach a point where MUDs / Text based games of the future are able to deliver dynamic nearly infinite personalized visuals or audio based on player actions?
You can definitely do that now for images as long as people can wait two seconds. But also normally MUDs have most locations already described so they could be pre-generated.
The thing about it is that SDXL understands intent much better so to get the really good visuals you would need to wait for that or DALL-E 3 which isn't quite as fast as the really fast diffusion models.
But still within 10 seconds or so I think you can do that for many things. So I am pretty sure that will be a thing.
I am working on something combining something like a simplistic game engine in an LLM agent and planning to include an action for generating an image.
Actually I think AI Dungeon already demoed something like that for their upcoming release.
