An AI Dark Horse Is Rewriting the Rules of Game Design | WIREDSkip to main contentThe Big Interview - December 4Learn MoreMenuSECURITYPOLITICSTHE BIG STORYBUSINESSSCIENCECULTUREREVIEWSMenuAccountAccountNewslettersSecurityPoliticsThe Big StoryBusinessScienceCultureReviewsChevronMoreExpandThe Big InterviewMagazineEventsWIRED InsiderWIRED ConsultingNewslettersPodcastsVideoMerchSearchSearchSign InSign InWill KnightBusinessDec 3, 2025 2:00 PMAn AI Dark Horse Is Rewriting the Rules of Game DesignThe Chinese video game giant Tencent is now building some of the world’s best 3D AI models. This could have implications far outside gaming.Photo-Illustration: WIRED Staff; Getty ImagesCommentLoaderSave StorySave this storyCommentLoaderSave StorySave this storyThe video game Valorant, a fast-paced team-based shooter, has recently become a testing ground for a promising new direction in artificial intelligence research. The game’s developers at Riot Games (a Tencent subsidiary) are using 3D-native AI models to prototype new characters, scenes, and storylines, according to a researcher familiar with the company’s efforts who spoke on the condition of anonymity.While many AI models can generate text, images, and video, Tencent’s Hunyuan (混元 or “first mix”) family of models can dream up 3D objects and interactive scenes. The source says that Tencent’s models are also being used by the developers of another Tencent game, GKART, and by some independent developers, too. Tencent declined to comment.“The games industry requires a lot of investment,” the source says. “Previously you would need a month to design a character. Now you can just type in some text, and Hunyuan can give you four choices in 60 seconds.”The news is an early signal that models capable of understanding and re-creating the physical world could become a standard ingredient in game design. In addition to generating game content, these models could also enable more advanced virtual and augmented reality and help robots learn to do new things.“There’s a real explosion of 3D vision research nowadays,” says Alexander Raistrick, a graduate student at Princeton University working on novel approaches to generating 3D content. “There are many killer applications: There's content creation, there’s self driving, and there’s a whole stack of problems involved in augmented reality.”Raistrick adds that video games are an obvious application for 3D AI models. “Outputting 3D meshes [a standard way of representing 3D objects] is your typical kind of bread and butter of game development,” he says.But, as in other creative fields, using AI to create video games is controversial. Concerns about AI-fueled job loss loom large. Some developers say games should be labeled when they contain AI-made content. Others say it’s too late: The technology is already ubiquitous in the industry.Tencent released HunyuanWorld 1.0, a model that generates interactive scenes, in July. I tested it a few months back, exploring a scene that looked like it was part of a Lego movie—a valley of brightly colored blocks disappearing into the distance. More recently, I’ve been playing with a more basic model, Hunyuan 3D, which can conjure up 3D objects. I used it to generate some very nice custom Dungeons & Dragons characters to 3D print. In October, Tencent released a new version of HunyuanWorld that lets users upload video to generate 3D scenes.Tencent’s Hunyuan models point to a broader shift happening in AI research. Many experts believe that AI models will need a deeper understanding of the physical world to advance. Because of this, Tencent is far from alone in building 3D-native AI models. Microsoft, Meta, Stability AI, and Bytedance all offer 3D models, but Hunyuan sits at the top of one leaderboard designed to rank such tools.A number of startups are doing interesting work in this space, too. World Labs, founded by Fei-Fei Li, a Stanford computer scientist who played a key role in building modern AI, has developed a tool called Marble that produces fully consistent and persistent 3D scenes. This could be useful for generating games on the fly or producing reliable training data for robots.3D AI is also an exciting area for academic research. A Stanford University project called 3D Generalist used an LLM to decide how to modify scenes with new objects. Raistrick, the graduate student at Princeton, is developing a way of generating 3D scenes using code, an approach that makes it possible for LLMs to generate and interact with scenes in a more powerful way. And projects like Google DeepMind’s SIMA 2 show how AI agents could interact with virtual worlds to create new forms of gameplay.As 3D-capable AI becomes more important, Tencent may emerge as an increasingly important player among a host of Chinese AI firms clamoring to win in this space. Besides producing some of the world’s most popular video games and movies, it operates WeChat, a chat app with a wide range of other functions, that is ubiquitous in China. Tencent also has its own chatbot, called YuanBao, which is integrated into WeChat. But Tencent’s video game skills may give it a distinct edge in an increasingly 3D AI world.Courtesy of TencentCourtesy of TencentThis is an edition of Will Knight’s AI Lab newsletter. Read previous newsletters here.CommentsBack to topTriangleYou Might Also Like …In your inbox: Will Knight's AI Lab explores advances in AIThe first radio signal from Comet 3I/Atlas ends the debateBig Story: How Gen Z toppled Nepal’s leaderIf the US has to build data centers, here’s where they should goEvent: Join some of the most influential voices in tech and beyondWill Knight is a senior writer for WIRED, covering artificial intelligence. He writes the AI Lab newsletter, a weekly dispatch from beyond the cutting edge of AI—sign up here. He was previously a senior editor at MIT Technology Review, where he wrote about fundamental advances in AI and China’s AI ... Read MoreSenior WriterXTopicsAI Labartificial intelligenceTencentChinaGamingmodels3dvideo gamesRead MoreAnthropic’s Claude Takes Control of a Robot DogAnthropic believes AI models will increasingly reach into the physical world. To understand where things are headed, it asked Claude to program a quadruped.Game Theory Explains How Algorithms Can Drive Up PricesRecent findings reveal that even simple pricing algorithms can make things more expensive.Meet the Chinese Startup Using AI—and a Team of Human Workers—to Train RobotsAgiBot is using AI-powered robots to do new manufacturing tasks. Smarter machines may transform physical labor in China.Hands On With Google’s Nano Banana Pro Image GeneratorGoogle’s latest AI image model is vastly better than the previous release at generating text in images. You can expect companies to go buck wild with this update.What Is Adobe Firefly? Here’s How to Use This Powerful Generative AI ToolAdobe Firefly is a deceptively powerful AI playground to generate images, videos, and more. Here’s how to make the most of it.The US Needs an Open Source AI Intervention to Beat ChinaDepending on foreign-made open models is both a supply chain risk and an innovation problem, experts say.Microsoft’s Agent 365 Wants to Help You Manage Your AI Bot ArmyMicrosoft still sees AI agents as the future of work, and the enterprise software giant wants companies to be able to manage those agents just like human employees.This Home Robot Clears Tables and Loads the Dishwasher All by ItselfSunday Robotics has a new way to train robots to do common household tasks. The startup plans to put its fully autonomous robots in homes next year.Poems Can Trick AI Into Helping You Make a Nuclear WeaponIt turns out all the guardrails in the world won’t protect a chatbot from meter and rhyme.Google DeepMind Hires Former CTO of Boston Dynamics as the Company Pushes Deeper Into RoboticsDeepMind’s chief says he envisions Gemini as an operating system for physical robots. The company has hired Aaron Saunders to help make that a reality.Nvidia CEO Dismisses Concerns of an AI Bubble. Investors Remain SkepticalRecord sales, a strong financial forecast, and CEO Jensen Huang’s impassioned arguments on his company’s earnings call weren’t enough to push Nvidia shares back to their October high.The AI Boom Is Fueling a Need for Speed in Chip NetworkingNext-gen networking tech, sometimes powered by light instead of electricity, is emerging as a critical piece of AI infrastructure.WIRED is where tomorrow is realized. It is the essential source of information and ideas that make sense of a world in constant transformation. The WIRED conversation illuminates how technology is changing every aspect of our lives—from culture to business, science to design. The breakthroughs and innovations that we uncover lead to new ways of thinking, new connections, and new industries.SubscribeNewslettersTravelFAQWIRED StaffWIRED EducationEditorial StandardsArchiveRSSSite MapAccessibility HelpReviewsBuying GuidesMattressesElectric BikesSoundbarsStreaming GuidesWearablesTVsCouponsGift GuidesAdvertiseContact UsManage AccountJobsPress CenterCondé Nast StoreUser AgreementPrivacy PolicyYour California Privacy Rights© 2025 Condé Nast. All rights reserved. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad ChoicesSelect international siteUnited StatesLargeChevronItaliaJapónCzech Republic & SlovakiaFacebookXPinterestYouTubeInstagramTiktok

Tencent, a dominant force in the video game industry, is undergoing a significant shift in its technological approach, largely driven by the development of its “Hunyuan” family of AI models. These models, particularly those focused on 3D generation, represent a potential disruption far beyond the gaming sector. The core innovation lies in Tencent’s ability to create and manipulate 3D objects and interactive scenes using AI, a capability where existing models had previously lagged.

Previously, the creation of characters, environments, and storylines within video games required substantial investment and considerable time—often a month or more—for developers. The Hunyuan models, however, can now generate these elements in approximately 60 seconds based on textual input. This dramatically accelerates the creative process and opens up novel approaches to game development. The technology’s utility extends beyond simple game creation, potentially impacting virtual and augmented reality experiences and even contributing to advancements in robot learning and adaptation.

The development is being utilized across multiple Tencent game titles, including Valorant and GKART, as well as by several independent developers. This widespread adoption signals a broader trend: AI models capable of understanding and recreating the physical world are poised to become essential tools in a variety of creative and technical domains.

Several experts have highlighted the importance of this shift, with Alexander Raistrick noting the “explosion of 3D vision research.” He further emphasizes that such advancements are not limited to gaming, encompassing sectors like self-driving vehicles and augmented reality. The output of these models often relies on “3D meshes,” a standard method for representing three-dimensional objects in computer graphics.

Despite the potential, the use of AI in video game creation inevitably raises concerns. Fears of job displacement among game developers are prevalent, leading to calls for labeling games that incorporate AI-generated content. Some argue that the technology is already deeply integrated into the industry, making the issue unavoidable.

Tencent’s HunyuanWorld 1.0, released in July, provided a tangible example of this technology, showcasing a vibrant, Lego-like valley disappearing into the distance. Subsequent iterations, such as Hunyuan 3D, allow users to generate custom Dungeons & Dragons characters to 3D print. The release of HunyuanWorld that allows users to upload video to generate 3D scenes further demonstrates the versatility of the models.

Tencent’s foray into 3D AI models represents a broader trend within the AI research landscape. Many experts believe that AI models will need a deeper understanding of the physical world to continue progressing. This conviction contributes to the growing prominence of Tencent in this field. Companies like Microsoft, Meta, Stability AI, and Bytedance are also developing similar 3D models, positioning Tencent as a leader in this emerging space.

Beyond Tencent’s gaming operations, the company’s WeChat platform and associated chatbot, YuanBao, further underscore the potential of its AI technology. Furthermore, this technological advancement is fueled by startups such as World Labs, founded by Stanford computer scientist Fei-Fei Li, who has developed a tool called Marble that produces fully consistent and persistent 3D scenes—a crucial element for scenarios involving dynamic game generation or reliable training data for robots. Additional research, like the Stanford University project 3D Generalist, employs an LLM to modify scenes with new objects, while Google DeepMind’s SIMA 2 explores how AI agents could interact with virtual worlds.

The rise of 3D-capable AI is likely to cement Tencent’s position as a significant player within China’s burgeoning AI industry, complementing its existing dominance in gaming and digital communications.