The Rise of Computer Games, Part I: Adventure
Key topics
The nostalgic world of text adventures is getting a modern reboot, with commenters reminiscing about mapping out game worlds on graph paper and exploring the potential of AI-powered text adventures. Some enthusiasts are experimenting with large language models (LLMs) to create immersive experiences, with suggestions ranging from using multiple LLMs to build and run campaigns to storing game state in files to improve memory. The conversation also touched on the similarities between text adventures and MUDs (Multi-User Dungeons), with some users fondly recalling their early internet experiences and others highlighting the limitations of real-time roleplaying with humans. As the discussion unfolds, a fascinating vision emerges: a truly open-world text adventure that's both dynamic and interactive.
Snapshot generated from the HN discussion
Discussion Activity
Very active discussionFirst comment
2h
Peak period
35
12-24h
Avg / period
15.2
Based on 76 loaded comments
Key moments
- 01Story posted
Dec 13, 2025 at 3:19 PM EST
25 days ago
Step 01 - 02First comment
Dec 13, 2025 at 5:31 PM EST
2h after posting
Step 02 - 03Peak activity
35 comments in 12-24h
Hottest window of the conversation
Step 03 - 04Latest activity
Dec 19, 2025 at 9:47 AM EST
19 days ago
Step 04
Generating AI Summary...
Analyzing up to 500 comments to identify key contributors and discussion patterns
Want the full context?
Jump to the original sources
Read the primary article or dive into the live Hacker News thread when you're ready.
It lost track of things almost immediately. But the foundation was there.
Maybe if we had a MUD-tuned model...
If it has an approximate way to track state, and a "pre-caching" method where it can internally generate an entire town all at once, room by room, so hallucinations are rarer... actually starts to sound like a traditional DM's method of world building for a campaign.
Maybe something like an LLM-assisted Inform (interactive fiction engine). https://ganelson.github.io/inform-website/
Side note: been playing Aesir, then the Aesir 2 MUD since 1994. It's still up!
I think the challenge of trying to make an "endless" game using an LLM is the same challenge that all procgen games face - they are boring for people who are seeking a well-paced narrative. There are players who enjoy the mechanics of looting/crafting/trading/etc who will gladly play games where the story is incidental or emergent, but if you're specifically looking for something with a bit more narrative depth, I'm not sure procgen will ever work. Even if there is a system that tries to project coherent storylines onto the generated world, you still need the player to do things that fit into a storyline (and not break the world in such a way that it undermines the storyline!), otherwise the pacing will be off. But if the system forces the player into a storyline, then it breaks the illusion that the world was ever truly open. So you can't have it both ways - either there is a narrative arc that the player submits to, or the player is building their own narrative inside a sandbox.
AAA games try to have it both ways, of course, but it's always pretty clear when you are walking through procgen locations and leafing through stacks of irrelevant lore vs when you are playing a bespoke storyline mission that actually progresses the state of the world.
You can do this with regard to a MUD too, but typically out of character and not every MUD would allow OOC chatting within the game world, as that is disruptive to those players who seek immersion.
It seems to me as if you may not have found a good roleplaying MUD back when you played MUDs. You may be missing out on that experience. I retired from playing MUDs about 11 years ago permanently, but the in-world roleplay was the only thing that was interesting to me since it was the creation of a unique storyline potentially involving many other playercharacters.
The thing I love about computer games is that I can go through them at my own pace, pause whenever I like, hang around looking at a cool visual, go back to an old save and try something different, whatever. Multiplayer takes all that freedom away because everything has to progress on somebody else's timetable, which isn't as fun for me. Nowadays being expected to perform on a time limit just reminds me of work, which is the last thing I want when I'm playing a game.
In this way I imagined in time a world larger and richer than any that had come before it—where you could really just keep going, keep playing, never see all of it.
So the tools already exist, but it seems to me that they primarily appeal to a very specific type of gamer, one that doesn't have much overlap with the type of gamer who would like an "endless" open world or the type of gamer who would like a tightly-plotted narrative experience. I think it's more something that appeals to fans of table-top RPGs, people who are looking for a collaborative storytelling environment.
I think many gamers have the imagination of an epic infinite metaverse style game, but then when they actually get the opportunity to participate in one, it turns out that that's not really what they wanted after all, because it requires a level of creative labor that they weren't expecting. This is why I think the market has naturally segmented into sandbox builders, survival/roguelikes, traditional narrative adventures etc.
Those are MOOs. Here's the original MOO: https://lambda.moo.mud.org/
There's no point to a MOO other than to be itself, although LambdaMOO does have an RPG game in it you can play among other things: https://en.wikipedia.org/wiki/LambdaMOO
That is more like "computer tabletop", however, and doesn't scale beyond a small number of players.
LLMs are limited today, but one day they may be able to provide the well-paced narrative you're talking about. The LLM would be a skilled fiction writer that would introduce interesting events as I explore the world.
If I decide to go to a bar and talk to random strangers, it could give me interesting life stories to listen without any action. But, suddenly, a mysterious man walks in, gives me a sealed envelope and departs without saying a word... What is in the envelope?
https://www.avalon-rpg.com/intro/mud
In my experiment with ChatGPT, I was walking around in a museum (that was the scenario) and decided to flirt with a woman who happened to be there. The flirting was something I decided to do on the spot with no prompting from the AI. The woman had just been part of the room description up to that point. But it reacted to this new situation in a semi-realistic way, essentially creating a new "adventure" on the spot. I met her on the next day, brought a gift (and so did she), but then it started hallucinating... :(
Sometimes it will even match what the prompt author intended.
Typing isn’t even required any more, but as a book of templates, there are more possibilities than the average LLM user can conceive of in the moment.
https://en.wikipedia.org/wiki/The_Hitchhiker%27s_Guide_to_th...
https://www.filfre.net/2013/11/douglas-adams/
For my money the "best" adventure game was and is The Hobbit, but that may well be because it's the first one I was haunted by.
Similar two-part writeup starts here :
https://www.filfre.net/2012/11/the-hobbit/
I think we've learned that creativity comes from constraints. Early computing platforms certainly were replete with that.
And if you look at this best-selling video games list, there's only a single FPS in the top ten (PUBG, which is technically also third-person):
https://en.wikipedia.org/wiki/List_of_best-selling_video_gam...
Pretty much the definition of an old 'point and click' aventure with action points.
Even just looking at "game uses 3D engine" we don't really have many great things. There's portal, and while some of the other stuff have promising ideas (like infinifactory), for all of them the controls tend to get in the way of fun.
For ease of use and fun pretty much all simulations - even as far back as the 90s - just using isometric projection are still unbeaten by attempts to go full 3D.
[0] https://www.metacritic.com/browse/game/ps5/all/current-year/... [1] https://www.metacritic.com/browse/game/xbox-series-x/all/cur... [2] https://www.metacritic.com/browse/game/all/all/current-year/...
https://en.wikipedia.org/wiki/The_Crimson_Diamond
But adventure gaming never went away, it just became more and more of a niche. There are lots of high-quality amateur games, but there's been a steady tricky of high-quality "indie" commercial games since the '90s. I'd recommend Wadjet Eye Games' entire catalog: https://wadjeteyegames.com/games/
The biggest, most advertised titles are often very good-looking and very "bubblegum", for the exact same reason that the most popular genres of pop are like they are. To appeal to the widest audience, you have to file off all the sharp corners, and if that's the market you see then modern games can seem soulless.
But that's not all of the market! No matter what genre you are interested in, there's probably more work ongoing in it and better games coming out right now that there ever has been in history. Most of them are less refined and sell a lot less than the mainstream games, but occasionally one succeeds well enough to expand past the small niche audience, which inevitably brings a lot more people into the niche, followed by imitators which grow the niche.
[1] https://www.cgwmuseum.org/
It is a lovely, very enjoyable game but it is _incredibly_ derivative.
As the saying goes, "good artists borrow, great artists steal."
Huh? That is also an artifact of what kind of games you follow. Just of the top of my head:
- colony sims - strategy games (tactical/operational/grand-, with rt, rt+pause, turnbased options for each) - racing games - 4x games - flight sims - spaceflight sims (whatever that means) - rpgs - survival games - shmups/ bullet hell - roguelike/roguelite - exploration - rhytm games - horror - factory builder / management sim
are all having a great time.
The Monkey Island that came out a few years ago sadly felt like a puzzle-free story for children and their parents to sit together to play. Elaine lacked humor and cynicism, there was a child's voice in some of the narration, the graphics were strangely cubic and stylistic instead of warm, and the characters seemed caricatures of themselves (like season 5 of a comedy series where the writing devolves into self-referential insider jokes about the past seasons).
I feel terrible saying that.
Will Adventure games come back, or are we lost on the new ADHD world of interruptible short content?
Nothing feels really novel. Where the innovation is seems to focus on graphical realism, which of course I love.
I'm strongly attached to Kingdom Come Deliverance 2 and while I'm near the end of the game, I'm dragging my feet so I don't have to go back to the drawing board of sorting through endless terrible FPS and retro hack and slash games on Steam that don't interest me and are copies of 20 year old games.
Adventure games (the topic here) are my favorite though, and it's very rare that anything comes out. The Sierra and LucasArts days are over (RIP). That said a few gems come out here and there, like Lucy Dreaming.
Many of the genres are baloney, at least the stuff that comes back in search results as recent - it's all Work Simulator, a slow grind, the ubiquitous first person shooter, horror or everyone's favorite hack and slash genre.
We're drowning in numbers, is all you're really telling me.
Just started KCD2 last night by the way.
I'm not sure it's worth lamenting that the most popular games today tend to have addictive mechanics and otherwise little novelty. Clearly that's what people enjoy. If you are interested in experimental or avant garde games, then that stuff is still out there in the indie scene. Lots of them are bad games, but they still might be good ideas.
There's plenty of examples I am sure people can share on the thread, but here's one that comes to mind for me as interesting but not very fun: Bokida - Heartfelt Reunion. It's a gigantic monochromatic world with impenetrable puzzles and weird geometry that reminded me of those old freescape games like Driller. I don't think I enjoyed it very much but somehow I did play it all the way through and it still sticks in my mind today because no other game I played really did the same stuff. But, then, it's possible that that's just my subjective experience and for someone who plays Minecraft or something similar, Bokida was just derivative and forgettable? I dunno.
There's a lot out there, though. I think we're in a golden age of games, as a kid I could never have imagined having a literal "backlog" of dozens of games I've already bought but not even started yet because there's so much to play.
- Darren Franich, "Metal Gear Solid: The strangest great videogame franchise"
https://ew.com/article/2015/09/04/metal-gear-solid-strangest...
In his book, Wonderland: How Play Made the Modern World, Steven Johnson applies this thesis to pretty much all the things. Enjoyable book, but the thesis probably does not hold up too much scrutiny.
http://literateprogramming.com/adventure.pdf
I recently investigated text based adventure games in Python as a possible tool to teach and evaluate outdoor wilderness safety knowledge and awareness (backpacking and overnight camping) for wilderness therapy.
While doing the research I recalled a friend showing me a text adventure game on his i386 PC. I could not understand the appeal. The possibilities the game suggested were vast, but the effective actions were unattainable--I was not able to see even the most basic level of progress before I became bored.
Now, outlining the wilderness safety "game", its obvious to me some understanding of software and programming would have made the game accessible. Then maybe a key in a room would be better understood as a metaphor of the code. In other words, a game at text level can be an attempt to model a complicated problem in an interactive program. If you can write a game where the final product is convincing (suspend disbelief), then maybe the game's model can be useful for other things. In my case instruction and evaluation of basic domain knowledge.
Jokes on me though, since now he can type at over 100 wpm (and uses dvorak)