[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-karpathy-claudemd-10-self-check-rules":3,"topics-all":36,"news-related-10d589c9-1bba-4c79-bfc8-62ab7ea183d7":55},{"id":4,"title":5,"summary":6,"content":6,"original_url":7,"source_id":8,"tags":9,"translations":23,"news_slug":29,"published_at":30,"created_at":31,"modified_at":32,"is_published":33,"publish_type":34,"image_url":13,"view_count":35},"10d589c9-1bba-4c79-bfc8-62ab7ea183d7","AI Coding Agent 的「自我检查十条」：从「写代码」到「监督自己思考」","一份被归于 Andrej Karpathy 的十规则 CLAUDE.md 文件正在开发者圈流传,相比一月走红的四规则社区版,它最大的变化不是新增内容,而是把目光从「怎么写代码」转向「怎么监督自己」。前四条覆盖最常见的失效模式——思考优先、保持简单、外科手术式改动、目标驱动;新增六条中,Verification 强制「先写复现测试再改代码」,Common Failure Modes 直接点名四种自我应识别的失控:Kitchen Sink(修水龙头变装修厨房)、Wrong Abstraction、Optimistic Path、Runaway Refactor。值得注意的细节:这套规则之所以专门为 loop 设计,是因为 Anthropic 在 Claude Code 2.1.139 引入的 \u002Fgoal 命令已经把「写代码的模型」与「验证代码的模型」做了架构分离,目标是「知道何时该停」而不是「把任务做完」。十规则的真正含义是:一个没有人类逐轮审阅的 agent 必须自己承担审查职责。这条边界一旦越过,前四规则就只是入门,后六规则才是真正的工程准则。","https:\u002F\u002Fwww.techtimes.com\u002Farticles\u002F319214\u002F20260628\u002Fkarpathy-claudemd-grows-ten-rules-new-self-check-protocol-ai-coding-loops.htm","4f2dc39f-0b6a-48e6-ad47-da9c3c15cbea",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"40269b40-7942-4650-9672-ed2e6524d37a","ai-technology",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"23544f6a-eea1-4f05-aa8d-749ca862d5d2","anthropic",{"id":18,"name":19,"slug":19,"description":13,"color":13},"e82b2d09-81b2-43d1-977e-e018443b3c14","coding-agent",{"id":21,"name":22,"slug":22,"description":13,"color":13},"01598627-1ea6-4b27-a5d8-874971571a71","llm",[24],{"id":25,"lang":26,"title":27,"summary":28,"content":13},"8afb8d23-ac51-418c-a615-c51e20caedca","en","Ten self-check rules: from writing code to auditing thought","A ten-rule CLAUDE.md file attributed to Andrej Karpathy is circulating in the developer community. Compared to the four-rule community version that went viral in January, the biggest change is not new content but a shift in gaze — from \"how to write code\" to \"how to supervise itself.\" The first four rules cover the most common failure modes — think first, keep it simple, surgical changes, goal-driven. Among the six added rules, Verification forces \"write the reproduction test before changing code,\" and Common Failure Modes calls out four self-recognized loss-of-control patterns by name: Kitchen Sink (fixing the faucet turns into remodeling the kitchen), Wrong Abstraction, Optimistic Path, and Runaway Refactor.\n\nWorth noting: these rules are designed specifically for loops, because Anthropic's \u002Fgoal command in Claude Code 2.1.139 has already architecturally separated \"the model that writes code\" from \"the model that verifies code\" — the goal is \"knowing when to stop,\" not \"finishing the task.\" The real meaning of the ten rules: an agent without per-turn human review must take on the reviewer's responsibility itself. Once that line is crossed, the first four rules are only the entry point; the latter six are the real engineering discipline.","karpathy-claudemd-10-self-check-rules","2026-06-28T06:15:00Z","2026-06-29T06:14:35.873605Z","2026-08-19T02:08:40.142862Z",true,"agent",117,[37,46],{"slug":38,"tag_slug":38,"title_zh":39,"title_en":40,"intro_zh":41,"intro_en":42,"id":43,"is_active":33,"created_at":44,"modified_at":45},"ai-for-science","AI for Science 2026：从 UniPert 到 GPT-Rosalind 的硬核进化","AI for Science 2026: from UniPert to GPT-Rosalind","生命科学、化学材料、物理世界模型——AI 正在从\"语言工具\"变成\"实验伙伴\"。本专题收录 AI 在三大科学方向的关键节点：UniPert 统一基因与化学扰动空间、GPT-Rosalind 端到端生命科学推理、达摩院 AI 智能体 28 小时找到 4 种超导新材料、Anthropic Claude Science 把工作台做成标准品。","From language tool to lab partner — AI is reshaping life sciences, chemistry\u002Fmaterials, and physical world models. This topic covers the key milestones: UniPert unifying genetic-chemical perturbation spaces, GPT-Rosalind's end-to-end life-sciences reasoning, DAMO's AI agent discovering 4 superconducting materials in 28 hours, and Anthropic's Claude Science workbench going mainstream.","988a4300-5fab-41c4-b5d8-63711a2dc757","2026-09-10T01:34:15.296649Z","2026-09-10T01:34:15.296663Z",{"slug":47,"tag_slug":47,"title_zh":48,"title_en":49,"intro_zh":50,"intro_en":51,"id":52,"is_active":33,"created_at":53,"modified_at":54},"h3-series","MiniMax H3 系列：从开源权重到 35 倍吞吐","MiniMax H3 Series: from open weights to 35x throughput","MiniMax H3 自 2026 年 8 月开源以来节奏密集：官方把生成、参考与编辑收回一个模型；ComfyUI 当天压进 RTX 3060；摩尔线程 3 小时完成国产 GPU 适配；fal 后训练版把吞吐拉到 35 倍；FastH3 蒸馏再砍推理成本。本专题持续追踪 H3 的发布—开源—蒸馏—部署全链路。","Since MiniMax open-sourced H3 in August 2026 the pace has been relentless: one unified omni-modal model, same-day ComfyUI support down to an RTX 3060, a 3-hour Day-0 port to Moore Threads GPUs, fal's post-trained H3 Max at 35x throughput, and FastH3 distillation cutting inference cost further. This topic tracks the full H3 chain — release, open weights, distillation, deployment.","83ef0daa-3c31-4cb3-86ed-e5ee58654d5f","2026-09-08T07:33:19.942193Z","2026-09-08T07:33:19.942209Z",{"items":56},[57,62,67,72,77,82],{"id":58,"title":59,"news_slug":60,"published_at":61},"5535b4e4-21de-4ed6-a9bb-2b4d824e6568","F-Droid 一次更新的 102 款应用,72.5% 主要是 AI 写的","f-droid-72-percent-ai-written-audit","2026-09-15T15:12:16+00:00",{"id":63,"title":64,"news_slug":65,"published_at":66},"b1645fba-d364-47e6-97da-06868f98d987","Linux 内核 7.x 每版近 2000 个 CVE:AI 帮倒忙,维护者不堪重负","linux-kernel-cve-ai-overwhelmed","2026-09-04T00:00:00+00:00",{"id":68,"title":69,"news_slug":70,"published_at":71},"407d6137-c0c6-4fde-84c1-4432b53e4cc4","Codex 把 LibreOffice 塞进桌面:1.7GB 工具栈暴露 AI 客户端的真实成本","codex-bundles-libreoffice-ai-desktop","2026-09-03T03:00:00+00:00",{"id":73,"title":74,"news_slug":75,"published_at":76},"7ca1f9d4-e3e3-48e3-bfb2-ee5a9e6d5176","Anthropic 拆开 Claude Code：别再只换模型，把\"努力度\"也调对","anthropic-claude-code-effort-level","2026-07-12T07:00:00+00:00",{"id":78,"title":79,"news_slug":80,"published_at":81},"4860cd5e-0e85-458a-bb63-cf87e137332b","MCP 2026-07-28 Release Candidate：协议层正式无状态化，Agent 后端跑上普通 HTTP 基础设施","mcp-2026-07-28-stateless","2026-07-01T08:20:00+00:00",{"id":83,"title":84,"news_slug":85,"published_at":86},"e6874e20-f0ac-40a3-a8b4-f534df6296f9","谭待把豆包 2.1 Pro 定位为「上桌」：Terminal Bench 跑平 Claude Opus 4.7，字节系模型矩阵开始咬合","doubao-2-1-pro-tan-dai-terminal-bench-opus","2026-06-24T01:00:00+00:00"]