<?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>The Super Individual&#39;s Gear Stack on Xinwei Xiong (cubxxw) - AI, Open Source &amp; Nomad Blog</title>
    <link>https://cubxxw.com/columns/super-individual-stack/</link>
    <description>Tech blog by Xinwei Xiong — AI Builder, open source contributor and digital nomad sharing Kubernetes, Go, AI projects and travel.</description>
    <image>
      <title>Xinwei Xiong (cubxxw) - AI, Open Source &amp; Nomad Blog</title>
      <url>https://cubxxw.com/assets/og-image.png</url>
      <link>https://cubxxw.com/</link>
    </image>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-us</language>
    <lastBuildDate>Sun, 19 Jul 2026 09:00:00 +0800</lastBuildDate>
    <atom:link href="https://cubxxw.com/columns/super-individual-stack/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>When Anyone Can Build the Thing, &#34;He Built It&#34; Becomes the Signal</title>
      <link>https://cubxxw.com/ai-agent/posts/super-individual-stack-reputation/</link>
      <pubDate>Sun, 19 Jul 2026 11:00:00 +0800</pubDate>
      <atom:updated>Wed, 22 Jul 2026 15:01:53 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/ai-agent/posts/super-individual-stack-reputation/</guid>
      <description>When the cost of building approaches zero, having built something no longer proves anything, so people go look at who built it. This essay covers the first layer of the gear stack — reputation: why trust is the one thing AI cannot flatten, the three carriers it lives on, why it will never appear on any tool list, and its three most uncomfortable truths. It closes by answering the question the whole series has been building toward: how to wire production, judgment, distribution, and reputation into one loop that feeds itself, instead of four unrelated chores.
</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>When Anyone Can Build the Thing, &#34;He Built It&#34; Becomes the Signal</media:description></media:content>
    </item>
    <item>
      <title>Your Product Can Be Copied Overnight. Your Readers Can&#39;t.</title>
      <link>https://cubxxw.com/ai-agent/posts/super-individual-stack-distribution/</link>
      <pubDate>Sun, 19 Jul 2026 10:30:00 +0800</pubDate>
      <atom:updated>Wed, 22 Jul 2026 15:01:53 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/ai-agent/posts/super-individual-stack-distribution/</guid>
      <description>The mistake engineers fall for most easily is believing that &#34;if the product is good enough, people will come.&#34; That line held some truth back when building was expensive, because good products themselves were scarce; in the era of near-zero building costs it has mostly stopped working — good products are no longer scarce, being seen is. This essay takes apart the distribution layer: why an audience is the only capacity that still compounds, how AI makes content production cheap while making distribution expensive at the same time, how to turn the act of building your product into a content pipeline, and the new half of distribution that grew in 2026 — being read, understood, and cited by models.
</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>Your Product Can Be Copied Overnight. Your Readers Can&#39;t.</media:description></media:content>
    </item>
    <item>
      <title>AI Writes Requirements for Free, and That&#39;s the Most Dangerous Part</title>
      <link>https://cubxxw.com/ai-agent/posts/super-individual-stack-judgment/</link>
      <pubDate>Sun, 19 Jul 2026 10:00:00 +0800</pubDate>
      <atom:updated>Wed, 22 Jul 2026 15:01:53 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/ai-agent/posts/super-individual-stack-judgment/</guid>
      <description>When execution cost approaches zero, the price of building the wrong thing doesn&#39;t shrink — it becomes payable in full. AI generates requirements at near-zero cost, so your queue fills with tasks that look reasonable and deliver little, and agents will faithfully complete every one. This essay takes apart the three jobs of the judgment layer: how to guard the requirement gate, how to write acceptance criteria, and how to externalize judgment into rules files the agent reads on every run — the only part of this layer that compounds. It&#39;s also honest about the half of judgment that rules can&#39;t hold, and why hit rate is the only real test of judgment.
</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 Writes Requirements for Free, and That&#39;s the Most Dangerous Part</media:description></media:content>
    </item>
    <item>
      <title>I Ran Ten Agents Overnight, Woke Up to Ten PRs, and Then I Got Stuck</title>
      <link>https://cubxxw.com/ai-agent/posts/super-individual-stack-production/</link>
      <pubDate>Sun, 19 Jul 2026 09:30:00 +0800</pubDate>
      <atom:updated>Wed, 22 Jul 2026 15:01:53 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/ai-agent/posts/super-individual-stack-production/</guid>
      <description>Part two of &#34;The Super Individual&#39;s Gear Stack,&#34; on the bottom layer — production. Every advance in this layer is a public good, handed to everyone at the same moment, so once it&#39;s good enough you should stop investing. What actually blocks you isn&#39;t execution bandwidth but review bandwidth, which cannot be scaled the same way. The only lever that works is raising first-pass correctness — front-loading rules, writing acceptance criteria into tickets, and letting agents run tests to green before opening a PR. The back half lays out empirical data on AI code quality and security, which happens to explain exactly why testing and isolation are the real gear of this layer.
</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>I Ran Ten Agents Overnight, Woke Up to Ten PRs, and Then I Got Stuck</media:description></media:content>
    </item>
    <item>
      <title>Your Gear Is Arming Your Competitors Too</title>
      <link>https://cubxxw.com/ai-agent/posts/super-individual-stack-four-layers/</link>
      <pubDate>Sun, 19 Jul 2026 09:00:00 +0800</pubDate>
      <atom:updated>Wed, 22 Jul 2026 15:01:53 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/ai-agent/posts/super-individual-stack-four-layers/</guid>
      <description>Almost every &#34;AI-era super individual gear list&#34; answers the same question: how to build faster. But when the same batch of models raises everyone&#39;s speed at once, fast stops being an advantage. This essay proposes a colder test — does this layer&#39;s progress help only you, or all of your competitors at the same time — and uses it to split gear into four layers: production, judgment, distribution, and reputation.
</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>Your Gear Is Arming Your Competitors Too</media:description></media:content>
    </item>
  </channel>
</rss>
