The October inflection point for vibe game development
打开互动全文版(逐段中英对照 + 针对本篇提问)→文章认为,2026 年 10 月是氛围编程(vibe-coded)电脑游戏的拐点,其驱动力是 Claude Opus 5.5 在生成真正好玩、而非仅仅“像游戏”的游戏方面能力提升。作者描述了四个仅用极少提示词构建的浏览器端 HTML/JavaScript 项目——Tree Appreciator、一款奇幻 RPG、多人即时战略游戏 Battle Drones,以及一款南瓜种植模拟器——并指出 Opus 5.5 对“让它好玩得多”这类提示响应良好,且比 GPT-6 Astra 表现出更强的“好玩感”。核心主张是:游戏设计长期被视为软件领域最难的挑战之一,如今已可在很大程度上外包给模型,而作者的创意投入仅限于每个项目几个小时。结论是,这将使游戏社区分化为两派:拒绝 AI 生成游戏的人,以及拥抱更广泛可及性的人;而真正的机会在于利用这些工具创造出原本不会存在的新颖、个人化的游戏。
The article argues that October 2026 marks an inflection point for vibe-coded computer games, driven by Claude Opus 5.5's improved ability to produce games that are genuinely fun to play rather than merely game-like. The author describes four browser-based HTML/JavaScript projects built with minimal prompting—Tree Appreciator, a fantasy RPG, the multiplayer RTS Battle Drones, and a pumpkin-farming simulator—noting that Opus 5.5 responded well to prompts such as "make it a LOT more fun" and showed a stronger sense of fun than GPT-6 Astra. The core claim is that game design, long considered one of software's hardest challenges, can now be largely outsourced to models, with the author's creative input limited to a few hours per project. The conclusion is that this will split the games community between those who reject AI-generated games and those who embrace wider access, while the real opportunity lies in using these tools to create novel, personal games that would not otherwise exist.
我之前写过,2025 年 11 月是编程智能体的一个拐点——Opus 4.5 和 GPT-5.1 越过了临界点,使各自的编程智能体成为软件工程师可靠的日常工具。我认为我们在 2026 年 10 月又到达了一个新的拐点,而这一次是针对**氛围编程电脑游戏**。
I’ve written before about how November 2025 was an inflection point for coding agents—the point where Opus 4.5 and GPT-5.1 crossed a tipping point that meant their respective coding agents became reliable daily drivers for software engineers. I think we’ve reached a new inflection point in October 2026, and this time it’s for **vibe coding computer games**.
* 如果有人真的投入精力去做,会发生什么?
* What happens if someone actually puts the work in?
尤其是 Claude Opus 5.5,在构建一款引人入胜的游戏所需的多个方面都展现出显著提升:
Claude Opus 5.5 in particular exhibits meaningful improvements in several areas needed to build a compelling game:
* 音乐生成(参见 Scrimshaw Jukebox)
* Music generation (see Scrimshaw Jukebox)
最后一点尤为重要。正如我之前的实验所示,模型早就能创造出某种*看起来*像游戏的东西。难点一直在于做出真正*好玩*的游戏。
That last one is particularly important. Models have been able to create something that _looks_ like a game for quite a while now, as seen in my previous experiments. The challenge has been getting to a game that’s actually _fun to play_.
游戏设计是一个深奥的领域。我不会假装自己对此很精通——我了解得足够多,足以把它当作一门手艺来尊重。创造出一个新颖、引人入胜的玩法循环,在恰当的难度水平上挑战玩家,并提供令人满意的学习曲线,这是一门精湛的艺术。我原本以为模型做不到这一点。
Game design is a deep subject area. I won't pretend to be well versed in it—I know enough to have respect for it as a craft. Creating a novel, compelling gameplay loop which challenges players at the right level and provides a satisfying learning curve is a fine art. I didn't think the models could do it.
后来我试着对 Claude Opus 5.5 说“让它**有趣得多**”……它做到了。
Then I tried telling Claude Opus 5.5 to "Make it a LOT more fun"... and it did.
在过去几周里,我以 vibe coding 的方式(按这个词的经典含义——完全不看代码)做了四款我自己真心喜欢玩的游戏。
In the past few weeks I've vibe coded (in the classic sense of the term—no looking at the code at all) four games that I've genuinely enjoyed playing.
周末我参加了在伯克利举办的 Foo Camp,遇到了好几位有着类似经历的人。如今做出好玩的游戏简直容易得令人震惊。新的挑战在于构思出新颖、令人愉悦、且没有 AI 辅助就不可能存在的游戏概念。
I attended Foo Camp in Berkeley over the weekend and met several people who were having similar experiences. Building games that play well is shockingly easy now. The new challenge is coming up with concepts for games that are novel and delightful and that wouldn't exist without AI assistance.
我没有做过详尽的研究,但我目前的印象是 GPT-6 Astra 还**没有完全**达到那个水平。它绝对能做出游戏,但它的“趣味感”比不上 Opus 5.5。我预计 OpenAI 会在今年年底前达到那个水平。
I haven't done an exhaustive study, but my current impression is that GPT-6 Astra isn't _quite_ there yet. It can absolutely build a game, but its sense of fun doesn't match that of Opus 5.5. I expect OpenAI will get there by the end of the year.
以下四个游戏项目让我确信,这些模型如今已能在极少引导下制作出有趣的游戏。这四个项目均使用 HTML 和 JavaScript 构建,完全在浏览器中运行。
Here are the four game projects that have convinced me that the models are now capable of producing fun games with very little guidance. All four are built in HTML and JavaScript and run entirely in the browser.
我发现的最小却真正令人愉悦的游戏是 **Tree Appreciator**。这个游戏我用的是普通的 Claude 聊天界面——甚至不需要 Claude Code。
The smallest game I found to be genuinely delightful is **Tree Appreciator**. I used the regular Claude chat interface for this—it didn't even need Claude Code.
这是我们在 Skyline Boulevard 上开车看树时,我一时兴起做的。我的提示词是:
I built this on a whim while we were driving along Skyline Boulevard looking at trees. My prompt was:
构建一个名为“Tree Appreciator”的 three.js 游戏——它向你展示两棵算法生成的树,游戏机制在于欣赏它们之间的差异。仔细思考如何确保它既有趣又美观。
Build a three.js game called "Tree Appreciator"—it shows you two algorithmically generated trees, and the game mechanic is about appreciating the differences between them. Think hard about how to make sure it is both fun and beautiful.
我发现让模型使用 three.js 效果非常好。Claude 没有自己的图像生成模型,但它能够构建出观感与手感俱佳的全彩 3D 模型。
I've found that telling models to use three.js works really well. Claude doesn't have its own image generation model, but it is capable of building full-color 3D models that look and feel excellent.
这个游戏完全不需要迭代或后续提示——我一次就得到了成品。它给了我一个迷人的、适配移动端的小型找不同游戏。你可以在这里玩。下面是构建它的聊天记录。
This game required no iteration or follow-up prompting at all—I got the game in a single shot. It gave me back a charming little mobile-friendly spot-the-difference game. You can play it here. Here's the chat transcript that built it.
这是一个更具雄心的项目,我同样使用常规的 Claude 对话来构建。我从为一个俯视角奇幻 RPG 构建实验性引擎原型开始:
This was a more ambitious project that I again built using regular Claude chat. I started out by building an experimental prototype of an engine for a top-down fantasy RPG:
用 three.js 构建一个演示游戏引擎,它是一个俯视角(但带倾斜角度)的 RPG——玩家可以带着一两个同伴在世界中移动。创建一个奇幻村庄场景,演示在户外行走,然后展示当玩家进入建筑时,玩家与相机之间的墙壁会变为透明,以便用户看到正在发生的情况。
Build a demo game engine with three.js which is a top-down (but at an angle) RPG — the player gets to move through the world with one or two companions. Create a fantasy village setting that demonstrates walking around outside and then shows how, when the player enters a building, the wall between the player and the camera goes transparent so the user can see what is happening.
添加一些 NPC 和大量家具,以及不同类型的建筑,其中一些带有楼上——发挥创意,让它看起来很棒。
Add some NPCs and plenty of furniture and different types of buildings, some with an upstairs — be creative, make it look great.
这是第一个版本。它运行得非常好!
Here's that first version. It worked really well!
让它不要那么平坦——建筑很棒,但地形本身目前完全是平的,修复这一点。
Make it not so flat — the buildings are great, but the landscape itself is completely flat at the moment; fix that.
为其中两座建筑添加地下室,并在村庄下方用隧道系统将它们连接起来。
Add basements to two of the buildings with a tunnel system joining them below the village
在村庄的一侧添加一座岩石山的雏形,山中有一个洞穴,里面住着一只沉睡的巨魔。
Add the start of a rocky mountain on one side of the village containing a cave with a sleeping troll
现在把它变成一个真正的游戏——将可玩区域扩大四倍,引入有趣的游戏机制,添加一个不太老套的情节、一些转折和一个魔法系统,让它变得非常出色。
Now turn this into an actual game - quadruple the size of the playable area, introduce fun game mechanics, add a plot that isn't too cliche, some twists, a magic system, make it really good
我们在这里又回到了像“让它变得非常出色”这样的提示!要求一个“不太老套”的情节似乎也奏效了——它有点老套,但仍然足够新颖,让我享受地跟随故事。
We’re back to prompts like “make it really good” here! Asking for a plot that “isn’t too cliche” seemed to work too—it’s a bit cliché, but still novel enough that I enjoyed following the story.
与 Tree Appreciator 不同,这个游戏需要大量额外的游戏测试和提示才能完成最终版本。这主要是由于游戏玩法问题——比如角色因为不同的故事元素而移动到另一个位置,导致无法在正确的位置完成任务。
Unlike Tree Appreciator, this took quite a bit of additional playtesting and prompting to get to a finished version. This was mainly due to gameplay problems—things like a character not being in the right place to complete a quest because a different story element had caused them to move to another location.
这是最终的游戏。它有一个完整的故事,大约需要 15 分钟才能通关。
Here’s that final game. It has a full story that takes about 15 minutes to play through.
一旦一切正常(并且我迭代了一些游戏玩法错误),我从头到尾玩了一遍,发现自己被结局感动了!我对此有些尴尬,因为这个游戏中的_一切_——图形、情节、角色、音乐、对话——都来自模型。我的创意输入几乎只是“这是一个幻想村庄,洞穴里睡着一个巨魔”。
Once it was all working (and I’d iterated through some gameplay bugs), I played it through from start to finish and found myself emotionally affected by the ending! I’m somewhat embarrassed by this, because _everything_ in this game—the graphics, the plot, the characters, the music, the dialog—came from the model. My creative input was pretty much just “it’s a fantasy village and there’s a troll asleep in a cave”.
这是我构建这个游戏的完整共享 Claude 聊天记录。
Here’s the full shared Claude chat in which I built this game.
我还把同一组初始提示词序列输入了 ChatGPT GPT-6 Pro。以下是对话记录和最终完成的游戏,供对比参考。它看起来很棒,但我认为它的可玩性远不如前者。
I also fed that same initial sequence of prompts through ChatGPT GPT-6 Pro. Here's the transcript and the finished game for comparison. It looks great, but I don't think it plays nearly as well.
这是我迄今为止最成功的项目,我上周刚写过相关文章。它是一款《命令与征服》风格的即时战略游戏,两支机器人军队(截至周六已扩展为四支)在其中建造单位、采集废料并争夺领土。
This is by far my most successful project, which I wrote about last week. It's a Command & Conquer-style Real-Time Strategy game where two robot armies (or four as of Saturday) build units, harvest scrap, and battle over territory.
也正是这个项目让我确信,Opus 5.5 懂得什么是“好玩”。
This is also the project that convinced me that Opus 5.5 knows what "fun" is.
最早的版本于七月使用 Claude Fable 5 构建。它帮我做出了一个可运行的 2D《命令与征服》风格游戏,但玩起来并不出色。
The first versions were built back in July using Claude Fable 5. It got me to a workable 2D Command & Conquer-style game, but it wasn't great to play.
我向 Opus 5.5 下达提示“让它好玩得多”,随后又提示“把这个游戏移植到 three.js”,游戏由此脱胎换骨。我的文章中有逐条记录(包含提示词)。
I prompted Opus 5.5 to "Make it a LOT more fun" and then later to "Port this game to three.js" and the game was transformed. There's a blow-by-blow account (prompts included) in my write-up.
如今,Battle Drones 具备 2–4 人多人对战(通过一个凭感觉编码的 WebSockets 中继服务器实现)、奖章、回放、七张地图、随机地图生成器,以及一组为规则增加变体的“变异器”。
Today, Battle Drones has 2-4 player multiplayer (via a vibe coded WebSockets relay server), medals, replays, seven maps, a random map generator, and a set of "mutators" that add variants of the rules.
它还允许不同的 LLM 互相对战,采用一种模式:游戏推进五秒后暂停,给不同模型时间去解读新的游戏状态并排布下一组指令。以下是 Claude Haiku 5.5 对战 GPT-6 Luna 的录像回放:
It also lets different LLMs play against each other, using a mode where the game advances five seconds and then pauses to give different models time to interpret the new game state and line up their next set of commands. Here's a replay of Claude Haiku 5.5 vs. GPT-6 Luna:
上周二,我以 Apache 2.0 许可证发布了 Battle Drones。周三,Gabriel Turpin 发布了 Panache(截图见此),这是 Battle Drones 的一个分支,将该游戏重新构想为 1900 年代法国美好年代的蒸汽朋克风格,配有新的模型、音乐和动画开场序列。开源的力量正在发挥作用!
I released Battle Drones under the Apache 2.0 License last Tuesday. On Wednesday Gabriel Turpin released Panache (screenshots here), a fork of Battle Drones that reimagined the game for steampunk 1900s Belle Époque France, with new models and music and an animated intro sequence. Open source at work!
我住在加利福尼亚州的半月湾,这里是年度半月湾艺术与南瓜节的举办地,该节日包含一项巨型南瓜称重比赛。
I live in Half Moon Bay, California, home of the annual Half Moon Bay Art and Pumpkin Festival, which includes a giant pumpkin weigh-off competition.
我决定尝试制作一款游戏,它不只是对已有作品的廉价模仿,因此我开始着手创作一款关于种植南瓜、培育巨型南瓜,以及应对十月南瓜季高峰的游戏。
I decided to try building a game that wasn't just a cheap imitation of something that already existed, so I set out to create a game about farming pumpkins, growing giant pumpkins, and handling the rush of the October pumpkin season.
我仍在迭代这个项目,但它正朝着相当不错的方向发展。这是一款温馨的农场模拟游戏:你全年照料自己的巨型南瓜,并种植普通尺寸的南瓜以供十月出售,然后在南瓜季销售南瓜,并把你的巨型南瓜送去参加称重比赛。
I'm still iterating on this project, but it's shaping up quite nicely. It's a cosy farming simulator where you spend the year tending to your giant pumpkin and planting out regular-sized pumpkins for sale in October, then sell pumpkins during pumpkin season and enter your giant pumpkin in the weigh-off.
游戏中的每个角色都是(素食的)动物。镇长是一只鹈鹕。你可以扮演鹈鹕、臭鼬、浣熊、负鼠、海狸、郊狼、狐狸、猫头鹰、海獭或斑海豹。这些物种之后都会(带着它们的孩子)出现,向你购买南瓜。
Every character in it is a (vegetarian) animal. The mayor of the town is a pelican. You can be a pelican, skunk, raccoon, possum, beaver, coyote, fox, owl, sea otter, or harbor seal. Those species all later show up (accompanied by their children) to buy pumpkins from you.
这是最初的头脑风暴会议,最终形成了这份规格文件。然后我让 Opus 5.5 Ultracode 消耗了数百万个 token,花了近两天时间构建它。
Here’s the initial brainstorming session, which resulted in this spec file. Then I had Opus 5.5 Ultracode burn millions of tokens and nearly two days building it.
我告诉 Claude“频繁地给用户带来惊喜和愉悦”,结果就是 _如此多_ 的小细节和彩蛋。有淘气的浣熊,一只主持称重比赛的大象海豹,把南瓜滚回海洋的斑海豹,一只游荡的山羊,以及关于种植巨型南瓜的迷信——这些迷信 _有时_ 会成真。
I told Claude to “surprise and delight the user frequently” and the result is _so many_ little details and easter eggs. There are mischievous raccoons, an elephant seal that runs the weigh-off, harbor seals that roll their pumpkins back into the ocean, a wandering goat, and superstitions about growing giant pumpkins that _sometimes_ come true.
这还不是我最好的游戏——它玩起来不如《战斗无人机》有趣——但它代表了我想要更多的那种游戏:古怪、有趣、独特的个人化——这种东西在以前是不会被构建出来的。
This isn’t my best game yet—it’s not as fun to play as Battle Drones—but it represents the kind of game I want more of: weird, fun, uniquely personal—something that wouldn’t have been built in the before-times.
如果你对 AI 生成的艺术、AI 生成的音乐、AI 生成的文字和 AI 生成的代码感到反感,那么我有个坏消息要告诉你:氛围编程游戏同时结合了**所有这些**。
If you are offended by AI-generated art, AI-generated music, AI-generated writing, and AI-generated code, I have bad news for you: vibe coded games combine **all of those at once**.
我尊重这些观点,尽管我自己并不强烈持有这些观点。
I respect those opinions, even though I don’t strongly hold them myself.
更广泛的游戏社区已经对游戏中的 AI 生成资源产生了反感。过去几年,随着 Midjourney 等工具使开发者能够为他们的项目生成资源,这个问题日益严重。这篇 IGN 报道涵盖了人们对 Valve 的 Steam Next Fest 中低劣内容的抱怨,是一个很好的近期例子。
The wider games community already has an aversion to AI-generated assets in games. This has been a growing issue over the past few years as tools like Midjourney have enabled developers to generate assets for their projects. This IGN story covering complaints about slop in Valve’s Steam Next Fest is a good recent example.
现在我们有这样的游戏:_一切_——代码、资源、对话,甚至游戏设计本身——都可以外包给模型。而且结果并不差!
We now have games where _everything_—code, assets, dialog, and even the game design itself—can be outsourced to the models. And the results don’t suck!
构建计算机游戏曾经是所有软件开发中最具挑战性的项目之一,它结合了多种技能,需要数月甚至数年的专注和努力。而现在,我只需在手机上输入提示,就能做出一个可玩的多人 RTS 游戏!
Building a computer game used to be one of the most challenging projects in all of software development, combining a diverse range of skills and requiring intense focus and effort over many months or even years. And now here I am spitting out a playable multiplayer RTS by prompting on my phone!
我预计,正如我们在编程领域已经看到的那样,这将导致一种分化。一些玩家会拒绝与以这种方式构建的游戏有任何瓜葛。另一些人则可能欣然接受,认为这能让游戏开发面向更广泛的受众。我倾向于后者!
I expect that, as we've already seen with programming, this will result in a split. Some players will refuse to have anything to do with games that were built in this way. Others may embrace this as opening up game development to a much wider audience. I lean in that direction!
我当然不会把我任何一款“氛围编程”(vibe coded)的游戏拿去参加传统的游戏创作马拉松或比赛——我觉得自己还没有资格这么做。我们很可能会看到为“氛围游戏”开发者比较各自项目而出现的新途径。
I certainly won't be entering any of my vibe coded games in traditional game jams or competitions—I don't feel like I've earned that right. We'll likely see new avenues emerge for vibe game developers to compare their projects.
这件事让我既兴奋又羞愧:我投入的**创造性输入如此之少**,却得到了有趣的结果。我在这里描述的项目大致按照我投入精力的多少排序。没有一个项目花费我超过四小时的工作(外加 Claude Code 自行运转的许多小时)。
The thing I find both exciting and shameful about this is that I have got interesting results from _so little creative input_. The projects I've described here are loosely ordered by how much effort I've put into them. Not a single project represents more than four hours of my work (plus many more hours of Claude Code churning away by itself).
现在想象一下,如果有人认真对待这件事,投入大量创造性时间,在游戏设计上运用更好的品味,然后对结果进行试玩测试并迭代,直到做到他们所能达到的最好程度,会取得怎样的成果。
Now imagine what could be achieved by anyone who takes this seriously, invests significant creative time, applies better taste in game design, and then playtests and iterates on the result until it's as good as they can make it.
我想看到那些没有这些新工具就不可能存在的游戏。
I want to see games that wouldn't have existed without these new tools.
以这种方式构建游戏_非常有趣_。这是 vibe coding 的完美应用,因为风险很低:在一个个人 vibe coding 游戏项目中,一个 bug 能造成多大损害呢?
Building games in this way is _so much fun_. It’s the perfect application for vibe coding because it’s so low stakes: how much damage can you cause with a bug in a personal vibe coded game project?
(好吧,你确实可能造成一些损害……我尝试的基于音频的多人游戏让我妻子 Natalie 头疼得厉害!)
(OK, you can do some damage... my attempt at audio-based multiplayer gave my wife Natalie a nasty headache!)
到目前为止,我所有的游戏都是使用静态托管(通常是 GitHub Pages 或 Cloudflare Pages)的 HTML 和 JavaScript。现代浏览器——包括移动浏览器——功能非常强大。前沿模型已经了解 three.js 和 Phaser 等库。我发现这些移动网页游戏与原生体验难以区分,至少对于我尝试构建的这些游戏类型来说是这样。
All of my games so far have been HTML and JavaScript using static hosting (generally GitHub Pages or Cloudflare Pages). Modern browsers—including mobile browsers—are incredibly capable. Frontier models already know libraries like three.js and Phaser. I’m finding these mobile web games to be indistinguishable from the native experience, at least for the kinds of games I’m trying to build.
我建议从这样的提示开始:
I suggest starting with a prompt like this:
构建一个移动友好的 three.js 游戏,其中……
Build a mobile-friendly three.js game where...
这在 chatgpt.com 和 claude.ai 上都能用——你甚至不需要启动一个完整的编程智能体。作为最后一个例子,下面是 Claude Opus 5.5 Extra 和 GPT-6 Extra High 分别给出的“构建一个移动端友好的 three.js 游戏,让老鼠必须躲避猫”。
This works on both chatgpt.com and claude.ai—you don’t even need to fire up a full coding agent. As one last example, here’s “Build a mobile-friendly three.js game where a mouse has to hide from a cat” by Claude Opus 5.5 Extra and by GPT-6 Extra High.
一旦你的项目通过概念验证阶段,就切换到 Codex 或 Claude Code。
Switch to Codex or Claude Code once your project passes the proof-of-concept phase.
如果游戏还不够有趣,就加上这句:
And if the game isn’t fun enough, add this:
让它有趣得多
Make it a LOT more fun