Shopify's Claude Code Warning: Why AGENTS.md Compatibility Matters
Shopify CEO Tobi Lütke may ban Claude Code over AGENTS.md support. See how fragmented agent system prompts and skills affect Codex teams.
阅读文章AI 编程笔记
面向使用 Codex、Claude Code、Cursor 和其他 Agent 的开发者,分享工作流、编程 Agent 现场笔记和真实的大模型评测。
从这里开始
Shopify CEO Tobi Lütke may ban Claude Code over AGENTS.md support. See how fragmented agent system prompts and skills affect Codex teams.
阅读文章Tibo Sottiaux says Codex Reset began as usage compensation after broken builds. He still controls the reset button.
阅读文章I ran Ox Alpha in OpenCode on my 3D globe test. One prompt, a working Three.js page, and a live demo at hqman.me/demo/global-view-pro.
阅读文章最新现场笔记
Grok Build brings Grok 4.6 to the terminal with native Browser Use plugin support for web automation, testing, and full-stack coding workflows.
阅读文章Ox Alpha GLM is a new Z.ai GLM iteration. I still guess GLM-5.3 Flash because this stealth model takes images and video, unlike GLM 5.2 in my tests.
阅读文章A source-map mistake exposed enough of Grok Bot 0.18.0 to reconstruct its runtime, prompts, tools, and model routing.
阅读文章按问题浏览
我关注什么
面向 Codex、Claude Code、Cursor 以及整个 AI 编程工具栈的可复用工作流。
循环、上下文、MCP、技能,以及演示之后才会暴露的失效场景。
亲自动手的模型测试(Claude Opus 4.8/Opus 5/Fable 5、GPT-5.6 Sol、Kimi k3、GLM-5.3、Gemini 3.7 Flash、Grok 4.6/4.7 等):一个新大模型适合用在哪里、成本多少,以及在真实工作中会在哪里出问题。
关于 AI Kai
我在真实项目里测试 AI 编程工具、编程 Agent 和新的大模型,然后分享那些经得起考验的部分,以及会白白浪费一个周末的失效场景。