Mmorpg World of ClaudeCraft, vibe coded with Fable 5
worldofclaudecraft.com
worldofclaudecraft.com
I'd say demos like these stand to profit the most from LLMs, if the goal is to make as much as possible in a few days: a barrage of quests are easy to generate, so are gear choices, and some skills for the initial 9 classes to pick from. A human would generally spend a lot of time here, thinking about whether the class/skill choices fit their world, what type of progression is fun and isn't. It's also where player testing would be important for a game to set good pacing and balance the difficulty.
Of course, the game itself is barely playable, it randomly stutters when I walk too far away from camp, the character controls are unintuitive, etc. A lot of this stuff could be chipped away by spending more time on the project and testing it yourself, getting a feel for what you want the game to be. That by itself should require a game to take more than a few days, if we expect others to play it and enjoy it. Something simple like movement controls could take many game iterations to iron out, and those aren't hard technical tasks.
Still, I can't entirely wrap my head around the fact that I live in a world where a machine can create this with minimal intervention by humans, and do a somewhat OK job at it, to the point where I'm willing to spend 10 minutes playing it.
"Create" is doing a lot of lifting here. As you (and the original author) mentioned, almost everything was assembled from downloaded free assets and libraries. Almost everything is a copy-paste. The Fable part is linking and debugging until it doesn't crash.
The main value proposition of LLMs is to wash the credit away from the giants and take it for yourself.
I wish we would give credit to Kenney [1] for making sick asset packs, mrdoob for making THREE.js [2], etc. than Fable for running curl/wget...
It gets said ad nauseam but a lot of software development is remixing. Think about how much gaming innovation happened in the Warcraft and StarCraft map editors. The Birth of tower defense, moba, and probably many more.
You no longer need another human to consume content, you just prompt your AI for the dopamine you want in that moment instead!
LLMs are similarly chaotic, hence why so many have coined them as slot machines.
Don't get cute.
Now to answer substantially, no frankly unless I'm legally required to I don't credit things. I usually specifically go for licenses that let me do whatever I want. I don't think I've ever credited a library I didn't have to I just use them and make things with them. That's the point of them and no one would raise your point in a pre LLM world imo.
Edit: Like as the point of absurdity no one is thanking the creators of postgres for every project that happens to use postgres. You still made a thing even if you didn't write your database from scratch.
Frankly I think this is faux outrage now that a lot of people are getting wise to the fact a substantial amount of modern programming is basically simple pipefitting.
It was always true that the amount of people providing the foundations the rest of us do work on was super tiny and that was just kind of accepted as fact at least from my > 11 years in industry and overall 20+ years of programming now. It's only now that the pipefitting may be devalued are people getting in a tizzy.
No, it's not.
And assets will be generated soon, too.
Stop downplaying how absolutely fucking magical this is.
We are at an inflection point in civilization.
This is the most amazing time in all of human history.
Also, I don't think we're at an inflection point when companies are starting to wisen up to just how much this shit costs.
This thinking sand did your job 5x faster. And you could have used the opportunity cost to do other things.
The engineers and artists in this country that are dunking on AI are insane. Asia is openly embracing this tech. They're going to leapfrog us if we keep shooting ourselves in the foot.
As opposed to when humans get into game dev and roll everything themselves from scratch?
> a human would generally spend a lot of time here,
This was always the hard part - game engines, asset libraries and all other services / SDKs were always making code-generation cheaper every generation.
Releasing a bug-free, thoughtfully built product requires a lot of attention and product skill.
Always interesting reading threads about topics you know deeply and everyone else has no familiarity or understanding about what they are seeing. Stark reminder of how easy it is to be impressed when you don't understand a topic.
Yeah that sounds like WoW retail heh.
Kill 200 boars.
Kill 300 boars.
Kill 250 boars and use this sword.
Kill 251 boars and use this special sword.
I heard about a better sword over there. You have to get past the 200 boars.
Wow, thank you for saving me from the boars. Please take this Boar Bane sword. You should try it out on 200 boars.
kill 200 brown boars.
kill 300 black boars.
“We tried everything to cure the boars, but we couldn’t. If they go any farther, they’ll infect everything. Kill 200 to stop them from infecting the forest.”
“You are inside your own mind. Your fears surround you. Fear of the boar. Free yourself. Kill 200 dream boars.”
:upsidedownface:
Does this excite you?
I don't know what that means. I can post something random on social media and there is a chance some person will spend 10 minutes on it. I don't need an LLM nor any money for that effect.
Yea it's buggy and janky in places, but equally it's coherent from a 3d perspective and 2d UI one
I don't know how many people have been trying to get claude to vibe code games, but it's really not good at it, I've been fiddling about and trying to make it work for a few months now
Yes, you can make flappy bird or snake level stuff, but anything much bigger honestly just falls over after a while
And that's after lots of prompting and feedback
Now what I'm really interested in here is how much of this was "strongly steered" vs oh that's cool, let's do that, ie trying to "sculpt" and fit an artistic vision of some kind that the driver is envisioning vs liking what it outputs and just asking for more of the same
The distinction between using it as a tool vs just being excited to take whatever it gives you
The other thing I'm wondering is how much of this is strongly indicative of claude's capability with typescript, I personally don't use it, so that might be hampering me more than I realised
This may be an unpopular thing to point out, but to those that are saying it's blindly copying code, I'm pretty sure most of the Wow code on the internet wasn't written in typescript, so there's some transformation going on there, how meaningful it is I'm less that certain about
I'm beginning to feel like I just wasn't ambitious enough[0], I was thinking of this as a good opportunity to see if Fable was capable enough to teach an abstract skill like game design
Though I am happy that the code it's generated so far is actually quite tractable, ie it's been working hard to keep itself maintainable, which honestly is new from my perspective, not sure what other people's experiences have been, but I tend to find that agent's in general are just a bit too willing to increase LOC without enough in the way of features to justify that line count in my mind, it makes the juice just not worth the squeeze in my mind
-[0]: Here's what 45% gets you on a 5x plan (https://github.com/Folcon/inkstain-engine)
Anyone who thinks that this makes it a bad WoW clone has probably not played very much WoW. There have always been lots of weird bugs, and recent expansions have only gotten worse.
It's tale as old as time at this point: the LLM produced something sort of shaped like some other software, and did it in an impressively short amount of time, but it's basically impossible to bring a codebase made in this way up to production standards, or to maintain it in any reasonable way. Nobody's gonna pay money for this, or want to play it instead of Warcraft. Why should anybody care?
nobody made anything interesting. all the arr sham was from people trying it out for a month and then realizing it sucks.
coding agents are only really useful in the hands of competent engineers.
there will be these type of projects by tourists that 99% of people will find useless and become throwaway wasteful projects.
hoping to FF to 2029 or whatever to see what’s next.
Edit: didn't realize you were the author, asking a practical question about how to describe your project. Sorry about that. For that, I personally think you're fine. You're trying to tell people what it is, not be super technically accurate.
So if they weren’t the author you’d be tickety-boo with this smart-ass rude reply? Christ almighty.
On the contrary, if you're trying to convey to a mass audience that what you have built resembles something else, the best strategy is to reference that thing by its most familiar name.
Sorry if I came off as petty. Was just trying to answer honestly, and realized I didn't have the right context.
Most shooters have rounds that restart, breaking the persistence quality of the game. Other games like Minecraft emphasize individual / private servers and break the "single gamestate" proposition. The "Massively" word refers to that single gamestate that many users can interact with, not how many do actually play.
To me, The "play offline" option is more against the MMO definition than the actual number of players.
And here I am watching my 5-hour window disappear over a couple simple tasks in a CRUD app.
I am using some llm work to help me bring my mmo project (2013-present) to prod, but my project is much more about pushing the edge of the mmo technology space, and my strategy has as one of its pillars the importance of owning the IP, which means adhering to the current laws in my production pipeline, so I only use unix/linux philosophy and have the llm do small tiny things in skeleton mode so I can rewrite them enough to claim they are actually mine, which they are. Even though I intend to open source the client fully, and the assets, I have to have the copyright so I can assign it to those licenses.
Technically, according to current SCOTUS rulings and precedent set so far (hopefully better things and changes to come, but here we are), this can not be copyrighted by the person who paid for the compute to make it.
When money starts hitting these kinds of projects, the legal wolves will be soon at the door, and it's going to get messy I think. So I still support open source gaming projects, but pure agentic or vibed games are probably going to face tons of challenges in the not too distant future based on my analysis.
This is not how I'd design much of this. Does that matter? AI and whatever training data used seems to differ.
Building a CAD kernel one of the essential pieces in getting from vaguely working to closing an extremely large number of gaps was some rather strict separation of concerns – without it we were just stuck on perpetual rearchitecting switching from methodology to methodology opening new gaps with each attempt to close others.
Pure vibe coding pretty much limits the max scope of your project to the capability of the agent, and if you're trying to make something real and maintainable, you'll always end up with something worse than the person who guides it at a lower level.
That being said, there are certainly going to be systemic/built in ways to have coding agents generate coherent architectures. Just it isn't really baked in right now.
Probably an ideal model with current tech is the main coding agent thread that implements things, and a secondary thread that constantly compacts/prunes and cleans up according to specific style rules.
Problem with doing both in same context via AGENTS.md is the LLM often won't adhere to all rules if it's overloaded with many competing instructions. But you can scope the code styling agent prompt tightly and get much higher focus and adherence.
Indeed. All you have to do is say “and make it good”, and it will make it good.
I do use AI extensively and get it to spit out vaguely acceptable designs. But I'm doing the design. Even when i have another agent trying to simplify or such the design details are still me.
I don't think people understand how this runs in contrast to the claims of intelligence.
Some people will see this and think "wow, in 5 more years I'll actually be able to make World of Warcraft". Some will see this and think "Wow, I can make World of Warcraft now with 1/100th the cost and engineers". Neither of these thoughts are right, though. The reality is more like "Wow, someone can make a game 10 times as good as World of Warcraft for the same[1] cost and number of engineers".
[1] - roughly $63 million, 5 years, 60 engineers
What? Writing code is not the bottleneck for how good a game is
Also your figure about there being 60 engineers on the team that launched WoW is completely incorrect. That was the total size of the team near the end and only about five of those were actual developers. Most of those were artists and other designers. I suggest you read the world of Warcraft development diary book it's actually very good. A lot of the development time went into writing tools to support the artists and designers. The actual amount of time that went into coding the game itself was a very small percentage of the overall time spent on the game
It's all about how a game actually feels which comes down to art, balance, progression, music, gameplay, lore, and so much else where you need people with obsessive levels of detail to perfect. I'm not saying LLMs can't help but it's ridiculous to make claims like this
I built this with Fable over a couple of days, on the side. It's a vanilla-WoW-flavoured micro-MMO in the browser: nine classic classes, three zones, a 5-player instanced dungeon, parties/duels/trades, and persistent characters. Free to play: https://worldofclaudecraft.com — and fully open source (MIT):
https://github.com/levy-street/world-of-claudecraft
Honestly the most mind-blowing part for me was how much it shipped that I never asked for. The level of polish and completeness coming out of the model genuinely surprised me — quest logs, threat metrics in the combat log, eating/drinking, spirit release on death.
We already have some contributors on GitHub!
One time though, I hit the limit when not running a sub-agent, and the agent resumed after the limit expired. Weird.
hugged to death?
> nginx/1.24.0 (Ubuntu)
commenting so I remember to check again later when it's back.
If you'd like to play the actual game with other SWEs I'd invite you to help me start a guild for SWEs: https://unplanned-downtime.com/