I gave Opus 5.5 one prompt and six hours to visualize Invisible Cities
GPT-6 Astra was a jump when it comes to puzzles. Claude Opus 5.5 is a jump when it comes to design.
在谜题方面，GPT-6 Astra 是一次飞跃。 在设计方面，Claude Opus 5.5 是一次飞跃。
Even local models can make a competent landing page for a shop. Doing interactive visualization is a different tier. Since I am into creating data visualizations and explorable explanations, LLMs were both a blessing and a curse.
即使是本地模型也能制作出合格的商店落地页。但进行交互式可视化则是另一个层级。由于我热衷于创建数据可视化和可探索的解释，大语言模型对我来说既是福音也是诅咒。
The Tree of ‘tree’, on Proto-Indo-European etymology, with Claude Opus 4.8. The first draft was surprisingly good, but then came a lot of frustration: removing AI slop and fixing visual overlaps.
使用 Claude Opus 4.8 制作关于原始印欧语词源的“树之树”。初稿出奇地好，但随后带来了许多挫折：需要剔除 AI 生成的垃圾内容并修复视觉重叠。
Genetic Distance Map with Claude Fable 5.1, which worked well with data analysis and implementation, but needed a bit of hand-holding to make the design good.
使用 Claude Fable 5.1 制作遗传距离图，它在数据分析和实现方面表现良好，但需要人工辅助才能使设计达到理想效果。
Then for a moment I was happy-ish with GPT-6 Astra. My subjective experience was that it is a bit better than Fable 5.1 at a general overview, following intentions behind prompts, and checking that it all works correctly.
有一段时间，我对 GPT-6 Astra 感到比较满意。我的主观体验是，它在总体概览、遵循提示意图以及检查功能正确性方面，比 Fable 5.1 稍微好一些。
Then there was the Opus 5.5 moment for AI-assisted design. I saw an optical explorable explanation:
“I asked Opus 5.5 to explain camera focus by building an interactive lens lab. Here’s what it came up with after 1 hour 26 minutes in one shot, $25.66 API cost.” – Ryan Sael on X, interactive
随后，Opus 5.5 在 AI 辅助设计领域带来了惊艳时刻。我看到了一个关于光学的可探索解释：
“我要求 Opus 5.5 通过构建一个交互式镜头实验室来解释相机对焦。这是它在一次尝试中，耗时 1 小时 26 分钟，花费 25.66 美元 API 成本后做出的成果。”——Ryan Sael 在 X 上发布，交互式
One may argue that it is still “too rich”, and has no sense of minimalism. But still, wow! I was still in disbelief. Was this really its consistent quality for a one-shot experiment?
有人可能会说它仍然“过于繁杂”，缺乏极简主义感。但即便如此，还是令人惊叹！ 我仍然难以置信。这真的是它在一次性实验中表现出的稳定质量吗？
Instead of my beloved optics, I went for something different.
我没有选择我钟爱的光学主题，而是尝试了一些不同的东西。
What’s a good prompt? Well, I went with the beautiful urbanistic poetry of Invisible Cities by Italo Calvino, presenting 55 imaginative cities, each one an emotion or state of mind, expressed in its architecture and in how people behave.
什么样的提示词才算好？我选择了伊塔洛·卡尔维诺的《看不见的城市》中优美的城市诗篇，书中呈现了 55 座充满想象力的城市，每一座都代表一种情感或心境，并通过其建筑和人们的行为表现出来。
When a man rides a long time through wild regions he feels the desire for a city. Finally he comes to Isidora, a city where the buildings have spiral staircases encrusted with spiral seashells, where perfect telescopes and violins are made, where the foreigner hesitating between two women always encounters a third, where cockfights degenerate into bloody brawls among the bettors.
当一个人在荒野中骑行许久，他会渴望一座城市。最终他来到了伊西多拉，那里的建筑拥有镶嵌着螺旋贝壳的螺旋楼梯，那里制造着完美的望远镜和小提琴，在那里，在两个女人之间犹豫不决的陌生人总会遇到第三个，那里的斗鸡比赛总是演变成赌徒之间血腥的斗殴。
In 2019, I had a small project of generating cities for a storytelling performance, using the frontier model of the time, GPT-2. With new models, capabilities change drastically. So I used the following prompt:
2019 年，我有一个为讲故事表演生成城市的小项目，当时使用的是前沿模型 GPT-2。随着新模型的出现，能力发生了巨大变化。所以我使用了以下提示词：
Make a three.js (pnpm) visualization of all Invisible Cities by Italo Calvino. Don’t ask questions, it is a one-shot task. You have 6h of work, use it until it becomes a masterpiece.
用 three.js (pnpm) 为伊塔洛·卡尔维诺的所有《看不见的城市》制作一个可视化作品。不要问问题，这是一次性任务。你有 6 小时的工作时间，请利用好这段时间，直到它成为杰作。
I gave this prompt to GPT-6 Astra… and it worked, end-to-end.
我把这个提示词给了 GPT-6 Astra……它成功了，实现了端到端的完成。
GPT-6 Astra (interactive, code): 53 minutes at medium effort, about $10 in API tokens.
GPT-6 Astra（交互式，代码）：中等投入，耗时 53 分钟，API 代币花费约 10 美元。
Some AI design slop, with many concepts and comments added, without checking whether they are actually needed, or just add visual noise. Some Captain Obvious statements that would work for accessibility, but not as something to be shown verbatim.
存在一些 AI 设计的垃圾内容，添加了许多概念和注释，却没有检查它们是否真正需要，或者只是增加了视觉噪音。还有一些显而易见的废话，虽然对无障碍访问有用，但不应作为原文展示。
Curiously, it seemed to pick up the Claude visualization style: beige background, numbers like 05. Still, I wouldn’t have expected earlier models to get anywhere near this.
奇怪的是，它似乎采用了 Claude 的可视化风格：米色背景，像 05 这样的数字。 尽管如此，我还是没想到早期的模型能达到这种水平。
Then I gave the same prompt to Claude Opus 5.5. It claimed:
I used roughly half of the six hours. The remaining polish has diminishing returns, but I can do another round if you want.
然后我把同样的提示词给了 Claude Opus 5.5。它声称：
我大约只用了六小时的一半时间。剩下的润色工作边际收益递减，但如果你需要，我可以再做一轮。
In fact it used only 1 hour 25 minutes, despite my direct instruction; though you can argue that it used agentic time dilation: 6 subagents, running in parallel, added up to about 7 agent-hours. I wanted to scold Opus 5.5 for finishing early, but then peeked at the result.
事实上，尽管我有明确指示，它只用了 1 小时 25 分钟；不过你可以认为它利用了智能体的时间膨胀：6 个子智能体并行运行，总计约 7 个智能体小时。我本想责备 Opus 5.5 过早完成任务，但当我查看结果时，我改变了主意。
Claude Opus 5.5 (interactive, code): 1 hour 25 minutes with 6 subagents in parallel, about $74 in API tokens.
Claude Opus 5.5（交互式，代码）：6 个子智能体并行运行，耗时 1 小时 25 分钟，API 代币花费约 74 美元。
And I’m mesmerized! See it for yourself. Sure, it might (and should) have used all the time, but even at this stage it was “wow!”. If this is the actual ceiling, it is a high one. And I am sure the next models will go even higher.
我被迷住了！你自己看看吧。 当然，它可能（也应该）用完所有时间，但即使在现阶段，它也已经让人“哇！”了。 如果这就是目前的上限，那它已经很高了。我相信未来的模型会达到更高的高度。
I encourage you to use the same prompt with different models, or different harnesses.
我鼓励你用不同的模型或不同的框架尝试同样的提示词。
We can expect AI to be a tool widely used (and burning a lot of token budget) in design.
我们可以预见，AI 将成为设计中广泛使用（并消耗大量代币预算）的工具。
I’m in awe, but I’m also asking myself: what is my place in creating interactive media?
我感到敬畏，但我也在问自己：在创作交互式媒体时，我的位置在哪里？
AI vendors collect every coding session they can, yet most teams discard their own. Quesma Shipper collects them into Amazon S3.
AI 供应商尽可能收集每一次编程会话，而大多数团队却丢弃了自己的会话。Quesma Shipper 将它们收集到 Amazon S3 中。
GPT-6 Astra solved twice as many Baba Is You levels as Claude Fable 5.1. It fits a pattern: ARC-AGI-3, the 3D game Portal, MazeBench, and Przemysław “Psyho” Dębiak’s obscure puzzles.
GPT-6 Astra 解决的《Baba Is You》关卡数量是 Claude Fable 5.1 的两倍。这符合一种模式：ARC-AGI-3、3D 游戏《传送门》、MazeBench 以及 Przemysław “Psyho” Dębiak 的冷门谜题。
AI mushroom identification from a photo with ChatGPT, Claude or Google Gemini: GPT-6 Astra, Gemini 3.8 Flash, Claude Fable 5.1, GPT-5.6 and GLM-5.3-Flash. Asked “What mushroom is that?” on 360 photos of poisonous species. Which warn, which get it right, which fail.
使用 ChatGPT、Claude 或 Google Gemini 通过照片进行 AI 蘑菇识别：GPT-6 Astra、Gemini 3.8 Flash、Claude Fable 5.1、GPT-5.6 和 GLM-5.3-Flash。针对 360 张有毒物种的照片询问“这是什么蘑菇？”。看看哪些会发出警告，哪些能识别正确，哪些会失败。