AI 导读
有人逆向拆解了 OpenAI 新推出的 ChatGPT 智能化 UI（生成式 UI）的工作原理。架构要点：智能体不写原始代码，而是生成自定义 UI 语言 DIL，由服务端编译并流式输出，客户端在沙箱 iframe 加 Web Worker 的运行时中执行，用约 70 个原生 UI 组件渲染，交互无需额外的 AI 调用。
正文
Someone just reverse-engineered how OpenAI's new Intelligent UI actually works.
And the architecture is fascinating.
ChatGPT generates working interfaces using:
- A custom UI language (DIL)
- Server-side compilation
- A sandboxed runtime
- ~70 native UI components
- Interactions without additional AI calls
The full engineering breakdown is worth reading.
ChatGPT launched their version of Generative UI yesterday. We took it apart tldr; the agent never write raw code. It emits DIL (a new language), the server compiles and streams it, the client renders it using a component set so that it feels native https://x.com/i/article/2108220775568404480在 X 查看被引用的帖子
来源：Rohan Paul · x.com