WorldClaw Agentic 3D open-world generation at scale
tencent-hunyuan.github.io
tencent-hunyuan.github.io
It's mostly "did you know you can attach an LLM to a PCG system?", but there is one idea here you don't see much of: an image model performs the composition (which image models are really good at), and then you extract the objects into 3d via things like SAM3D before placing them in the world, which is pretty interesting.
The rest is standard stuff you'll find in your favorite PCG system/game engine. Still, think most people don't realize how good LLMs are at 3D these days, especially Fable 5 (which this project predates).
Can you explain more? Can I use Fable 5 to generate a 3d model from a couple of photographs?
Things like the red key must be reachable before the red door, and there should be no path that bypasses the red door, etc. written as a set of constraints.
I was working on is because I realized, constraints tend to be similar in nature (graph cut, minimum/maximum shortest path etc.) algorithmically, but its usually quite hard to control designer intent.
The reason I shelved the project, was I asked an LLM a couple years ago, to generate a dungeon room graph, following a similar set of constraints, but stated in plain English, and it did a perfect job.
Which brings me to my final point. LLMs are amazing and flexible constraint solvers, and are woefully underutilized in scenarios like this.
With a hand authored constraint system if the red key is in the wrong place you have a bug in the constraint system that can be deterministically fixed, with a LLM you have to roll the dice on prompting again and go through expensive verification.
It seems to work well generating static 3D models. However typically with way too many triangles and no skeleton unless it is a human.
That's my experience anyway. I would be happy to be proven wrong.
I get that you run this, and then edit it. But the generated villages just aren’t interesting in my opinion. It’s probably great for tencent’s market where you’re mass producing gacha style games, but I don’t think worlds made in this fashion will scratch the open world itch like the best open world games out there.
I wouldn't say we don't need artists or writers, but I think most people will be surprised how quickly fully AI driven pipelines will advance here.
My sneaking suspicion is that there are a lot more cases than get reported, because authors are disincentivized to disclose AI usage, and readers by and large feel icky about reading AI work for reasons unrelated to quality.
I can totally see a weird future where a lot of what people like is AI generated, and everyone lies to each other about it. So it's hard to do research on this phenomenon.
I’ve experimented using AI to prototype game ideas and inevitably once I succumb to the temptation of handing the AI the game design reigns it starts devolving to meaningless slop with a silhouette of a meaningful design. The only way to get something meaningful (that ive found) is for the human to stay in the driver’s seat.
My Unassuming Skill, 'Tidying Up,' is the Strongest! ~A Corporate Slave Office Lady Accidentally Reforms a Country in Another World, and Now She's Doted on by the Knight Commander and His Majesty the Emperor!?~"
I guess I thought you were talking about real awards for great literature not webtoon style romance manga slop.
https://www.theguardian.com/books/2026/jun/20/granta-magazin...
Alternatively: “Here’s my fragile app I made in a few hours that’s 10x too long and won’t survive iteration but it kind of works. Everyone should thank me.”
I love tinkering, I love messing with things and doing cool projects, but 99% of what I make never goes beyond the room I made it in. Maybe I will show it to a friend when they come over. But ultimately they’re not fit for mass consumption and I don’t expect praise and use.
I am not a coder, I am not an engineer, I do not know how to make something that can be applied to a bunch of different machines with different hardware and software and configs. I can just barely put together something that specifically works for me in that moment. I needed to use ChatGPT to finish setting up idrive once ffs. Why on earth would I share that with other people lmao I mean let’s be real, all I’ve built is some crappy clone of something that already exists most likely. But making a quick script on my computer is faster than using Google’s increasingly degraded search to try and find the thing that will work for me, so here we are, me tinkering and screwing around for a couple of hours every month and occasionally getting something that helps me out. That’s enough!
I have never done any story generation and after reading the first couple of paragraphs, I could not tell whether this was AI-generated or not.
Tortured and near-miss metaphors are another thing it likes and it's loaded here. "groaned like a drumskin too tight for the heat" sounds cool but then you think, do drum skins "groan"? And what does heat have to do with it? Or "breath of hills holding their heat like a secret", are they holding the heat or breathing it? At least for me there's the tendency to at first feel like I'm reading something really clever, words that are really tuned and carefully chosen, and then to start feeling like I've been pranked.
Ultimately I don't think there's any way to really be sure though, whether it's AI or just a human but annoying style. This doesn't really read as what GPT would typically drop from a basic writing prompt though, I would guess it's heavily prompted on style or reworked repeatedly.
FWIW though I experiment quite a bit with AI writing for fun, and I think Opus writes pretty nicely in its default voice (prompted mostly for content with little guidance about "how" to write). I'm an engineer so I don't know if real literary connoisseurs would see the slop right through this, but it's coherent, well paced, a little heavy on similes and metaphors but they land unlike the linked passage. Just a sample:
---
Off the port quarter, the darkness lights up orange in a rolling line, gun by gun, and the sound arrives a full second behind the light.
Broadside.
Most of it goes over — a ripping, tearing sound in the air above, like heavy cloth torn by God. Two don’t. One takes the bulwark forward and turns eight feet of oak into a spray of splinters a foot long. One goes into the hull at the waterline abaft the fore chains with a sound you feel through your boot soles, and the sugar barrels in the hold scream as they shift.
A man is down by the foremast, shrieking, and another is not shrieking, and Homer is already running toward both with his hands out.
And Micheal is still aloft.
He’s on the fore topmast crosstrees with the stay gone under him, forty feet up, hanging off a spar that is swinging in a fifteen-degree arc and thumping the mast each time it comes back. You can hear him from the deck. Not screaming. Talking — fast, high, unbroken, reciting the rules to himself. "Touch wood don’t whistle don’t whistle spit to leeward—"
Why? Why on earth do the rules suddenly change when the effort is even less than something they wouldn’t publish to the world for review? They can barely even call it their own work. I refuse to believe that a short story you generated in 30 minutes represents anything resembling quality work. It’s vacuous, repetitive trash that I would be embarrassed to say represents my skills as a writer. Yet here we are, people constantly doing it. Code, writing, music, whatever.
Writing a coherent story =/= good at storytelling
Just look what happened when a studio tries to do a bold move and have a sequel where the protagonist of the first game gets tortured and killed out of revenge, by the daughter of one of the many characters he killed in the first part. This is a direct metaphor involving the player, about grief, revenge, and loss.
They were absolutely shredded by the fans over doing this to their favourite serial killer.
Gamers by and large don’t want a good story.
In the summer example in the hero images, the building placement + small pockets of water on the left looks odd and low attention to detail. A similar poor quality result as if an uncaring human used a scatter brush...
Curious if the examples are cherry-picked and by how much, or if this is one-shoted
Does it matter? Why?
Plenty of Holiday Inn’s have lovely painted landscapes on the walls. People aren’t paying for them to be in their homes.
I would argue the opposite even: this is more personal, as a singular artist can now do more by himself, without relying on others to do the parts that he couldn't do before.
When the artist AI generates it they get a house with wooden house with a straw roof and nothing else has any thought or intention. Its less personal, the viewer previously did not have to question what the artists intention was now they do because its likely the artist had no intention or thought towards a particular part of the art.
Furthermore, before AI, artists also used assets that came from other creators, accepting them wholesale. No intention, then?
The issue I see here is that we're judging the tool, not the artist.
It reminds me so much of the digital photography backlash. But here we are.
When use a LLM tool to write, paint, or generate a photograph, you are not actually writing the words, you are not actually physically painting, and you are not framing a photo. It is literally a different process and medium. You can enjoy that, even I have at times, but it’s not the same thing.
And what I'm learning is, artists are happy.
This is a topic I know very intimately and have strong feelings on. You are welcome to disagree with me, I am not the god of cameras and therefore always right, but I also should not be so quickly dismissed when it comes to this topic simply because you disagree with my take on AI generated “photography.” I use air quotes not to mock you but to emphasize that I do not consider it photography. It’s a different process and medium, it’s a different tool and result. None of this is a reflection of its merits or the people who utilize it.
I believe your metaphor was a very poor one so I expressed it. If you think it’s appropriate than feel free to explain it, but IMO, prompting an image and shooting it with a camera in your hands is not the same thing. So don’t start talking down to me and lecturing me on “being willing to learn” simply because I explained my reasoning on this.
If you're making decisions about what games you're playing based on how good they look, then you've been slurpin' up pure slop for a while.
In modern polished games, the art team spends a lot of time tweaking things to make sure it looks great and coherent. Most people are not willing to have their agent run for a month to do this work. I don't know if it's been tried yet but I would be really interested to see the result.
But as I say this, I realise the tree species seem to change very dynamically from season to season. So I'll have to assume either the temporal rate of change is actually a lot slower than one would expect in a model like this (allowing large tree species to regenerate annually), or there are new coniferous flowering tree varieties in this universe.
It's enormous, but utterly devoid of any soul. Like eating a $3000 subway sandwich.
Peter Steinberger, creator of OpenClaw, just spoke at YC Startup School. The entire thing is worth a view.
> There are 33,000 "claw" named repositories.
But Claude can do this with little prompting.
[edit] Not sure why the downvote, but Claude Design can do this, its just a matter of knowing the exact prompt.
This was created with just the prompt on from their front page and nothing else.
That's literally a cut+paste. If I had spent time on it, you can get it close to what's shown.
Claude also created that as a Blender file with assets for each of the generated items.