<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0"
     xmlns:atom="http://www.w3.org/2005/Atom"
     xmlns:content="http://purl.org/rss/1.0/modules/content/"
     xmlns:dc="http://purl.org/dc/elements/1.1/"
     xmlns:media="http://search.yahoo.com/mrss/">
  <channel>
    <title>超级个体的装备栈 on 熊鑫伟（cubxxw）的简体中文博客 🇨🇳</title>
    <link>https://cubxxw.com/zh/columns/super-individual-stack/</link>
    <description>AI Builder、开源贡献者、数字游民的技术博客：Kubernetes、Go、AI 开源项目与成长思考。</description>
    <image>
      <title>熊鑫伟（cubxxw）的简体中文博客 🇨🇳</title>
      <url>https://cubxxw.com/assets/og-image.png</url>
      <link>https://cubxxw.com/</link>
    </image>
    <generator>Hugo -- gohugo.io</generator>
    <language>zh-cn</language>
    <lastBuildDate>Sun, 19 Jul 2026 09:00:00 +0800</lastBuildDate>
    <atom:link href="https://cubxxw.com/zh/columns/super-individual-stack/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>当东西人人做得出来，「这是他做的」就成了信号</title>
      <link>https://cubxxw.com/zh/ai-agent/posts/super-individual-stack-reputation/</link>
      <pubDate>Sun, 19 Jul 2026 11:00:00 +0800</pubDate>
      <atom:updated>Mon, 20 Jul 2026 15:13:53 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-agent/posts/super-individual-stack-reputation/</guid>
      <description>当建造成本趋近于零，做出一个东西本身不再能证明任何事，人们只好去看是谁做的。这篇讲装备栈的第一层——声誉层：为什么信任是 AI 唯一抹不平的东西，它靠哪三种载体存在，为什么它永远不会出现在任何一份工具清单里，以及它最难堪的三个真相。最后回答整个系列的问题：怎么把生产、判断、分发、声誉四层接成一个互相喂养的闭环，而不是四件互不相干的事。
</description>
      <category domain="tag">AI</category>
      <category domain="tag">Super Individual</category>
      <category domain="tag">Open Source</category>
      <category domain="tag">Solo Builder</category>
      <category domain="tag">Personal Growth</category>
      <category domain="tag">Product Strategy</category>
      <enclosure url="https://cubxxw.com/images/covers/ai-agent/2026/super-individual-stack-reputation.jpeg" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/covers/ai-agent/2026/super-individual-stack-reputation.jpeg" medium="image"><media:description>当东西人人做得出来，「这是他做的」就成了信号</media:description></media:content>
    </item>
    <item>
      <title>你的产品一夜就能被抄走，你的读者不能</title>
      <link>https://cubxxw.com/zh/ai-agent/posts/super-individual-stack-distribution/</link>
      <pubDate>Sun, 19 Jul 2026 10:30:00 +0800</pubDate>
      <atom:updated>Mon, 20 Jul 2026 01:16:07 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-agent/posts/super-individual-stack-distribution/</guid>
      <description>技术出身的人最容易犯的错，是相信「产品做得足够好，自然会有人来」。这句话在建造昂贵的年代还有几分道理，因为好产品本身就稀缺；在建造趋零的年代它基本失效了——好产品不再稀缺，被看见才稀缺。这一篇拆分发层：为什么受众是唯一还在复利的产能、AI 让内容生产变便宜的同时怎样让分发变贵、怎么把做产品的过程本身变成内容管道，以及 2026 年分发新长出来的那一半——被模型读到、理解、引用。
</description>
      <category domain="tag">AI</category>
      <category domain="tag">Super Individual</category>
      <category domain="tag">Content Strategy</category>
      <category domain="tag">GEO</category>
      <category domain="tag">Solo Builder</category>
      <category domain="tag">Product Strategy</category>
      <enclosure url="https://cubxxw.com/images/covers/ai-agent/2026/super-individual-stack-distribution.jpeg" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/covers/ai-agent/2026/super-individual-stack-distribution.jpeg" medium="image"><media:description>你的产品一夜就能被抄走，你的读者不能</media:description></media:content>
    </item>
    <item>
      <title>AI 提需求不要钱，这才是最危险的地方</title>
      <link>https://cubxxw.com/zh/ai-agent/posts/super-individual-stack-judgment/</link>
      <pubDate>Sun, 19 Jul 2026 10:00:00 +0800</pubDate>
      <atom:updated>Mon, 20 Jul 2026 01:16:07 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-agent/posts/super-individual-stack-judgment/</guid>
      <description>当执行成本趋近于零，做错方向的代价不会变小，只会变成全额。AI 提需求几乎不要成本，队列会被一堆看着合理、实际低价值的任务填满，而 agent 会忠实地全部做完。这篇拆解判断层的三件事：需求闸门怎么守、验收标准怎么写、怎么把判断外化成 agent 每次开工都会读的规则文件——那是这一层唯一能复利的部分。也诚实指出规则装不下的那半判断，以及为什么命中率才是判断力的真实检验标准。
</description>
      <category domain="tag">AI</category>
      <category domain="tag">Agent</category>
      <category domain="tag">Super Individual</category>
      <category domain="tag">Context Engineering</category>
      <category domain="tag">Product Strategy</category>
      <category domain="tag">Solo Builder</category>
      <enclosure url="https://cubxxw.com/images/covers/ai-agent/2026/super-individual-stack-judgment.jpeg" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/covers/ai-agent/2026/super-individual-stack-judgment.jpeg" medium="image"><media:description>AI 提需求不要钱，这才是最危险的地方</media:description></media:content>
    </item>
    <item>
      <title>夜里跑十个 agent，早上收十个 PR，然后我卡住了</title>
      <link>https://cubxxw.com/zh/ai-agent/posts/super-individual-stack-production/</link>
      <pubDate>Sun, 19 Jul 2026 09:30:00 +0800</pubDate>
      <atom:updated>Mon, 20 Jul 2026 15:13:53 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-agent/posts/super-individual-stack-production/</guid>
      <description>《超级个体的装备栈》第二篇，讲最底下那层——生产层。这一层的所有进步都是公共品，同步发放给每个人，所以配到够用就该停手。真正会卡住你的不是执行带宽，而是 review 带宽，它几乎无法用同样的方式扩张。唯一有效的扩张手段是提高一次做对率，把规则前置、验收标准写进工单、让 agent 自己跑到测试全绿再开 PR。后半段给出 AI 代码质量与安全的实证数据，它们正好解释了为什么测试和隔离才是这层真正的装备。
</description>
      <category domain="tag">AI</category>
      <category domain="tag">Agent</category>
      <category domain="tag">Super Individual</category>
      <category domain="tag">Harness Engineering</category>
      <category domain="tag">Testing</category>
      <category domain="tag">Security</category>
      <enclosure url="https://cubxxw.com/images/covers/ai-agent/2026/super-individual-stack-production.jpeg" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/covers/ai-agent/2026/super-individual-stack-production.jpeg" medium="image"><media:description>夜里跑十个 agent，早上收十个 PR，然后我卡住了</media:description></media:content>
    </item>
    <item>
      <title>你的装备，同时也在武装你的对手</title>
      <link>https://cubxxw.com/zh/ai-agent/posts/super-individual-stack-four-layers/</link>
      <pubDate>Sun, 19 Jul 2026 09:00:00 +0800</pubDate>
      <atom:updated>Mon, 20 Jul 2026 01:16:07 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/zh/ai-agent/posts/super-individual-stack-four-layers/</guid>
      <description>几乎所有「AI 时代超级个体装备清单」都在回答同一个问题：怎么做得更快。但当每个人的速度都被同一批模型抬高，快就不再是优势。这篇提出一个更冷的判断标准——这层装备的进步，是只帮你，还是同时帮你所有对手——并据此把装备分成生产、判断、分发、声誉四层。
</description>
      <category domain="tag">AI</category>
      <category domain="tag">Agent</category>
      <category domain="tag">Super Individual</category>
      <category domain="tag">Solo Builder</category>
      <category domain="tag">Product Strategy</category>
      <category domain="tag">Productivity</category>
      <enclosure url="https://cubxxw.com/images/covers/ai-agent/2026/super-individual-stack-four-layers.jpeg" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/covers/ai-agent/2026/super-individual-stack-four-layers.jpeg" medium="image"><media:description>你的装备，同时也在武装你的对手</media:description></media:content>
    </item>
  </channel>
</rss>
