<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">
  <channel>
    <title>InfoQ - Code Reviews</title>
    <link>https://www.infoq.com</link>
    <description>InfoQ Code Reviews feed</description>
    <item>
      <title>Presentation: The Ladder is Missing Rungs: Engineering Progression When AI Ate the Middle</title>
      <link>https://www.infoq.com/presentations/ai-software-engineering-pipeline/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Code+Reviews</link>
      <description>&lt;img src="https://res.infoq.com/presentations/ai-software-engineering-pipeline/en/mediumimage/alasdair-allan-medium-1791451156021.jpeg"/&gt;&lt;p&gt;Alasdair Allan discusses empirical research from METR and Anthropic on AI coding adoption. He explains the "supervision paradox," where reliance on AI tools disrupts junior skill development, risks institutional context loss, and threatens the long-term engineering pipeline needed to oversee autonomous systems effectively.&lt;/p&gt; &lt;i&gt;By Alasdair Allan&lt;/i&gt;</description>
      <category>Code Reviews</category>
      <category>Leadership</category>
      <category>Claude</category>
      <category>Context Engineering</category>
      <category>QCon London 2026</category>
      <category>AI Coding</category>
      <category>Careers</category>
      <category>Anthropic</category>
      <category>Transcripts</category>
      <category>Productivity</category>
      <category>AI, ML &amp; Data Engineering</category>
      <category>Development</category>
      <category>Culture &amp; Methods</category>
      <category>Architecture &amp; Design</category>
      <category>presentation</category>
      <pubDate>Fri, 30 Oct 2026 11:00:00 GMT</pubDate>
      <guid>https://www.infoq.com/presentations/ai-software-engineering-pipeline/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Code+Reviews</guid>
      <dc:creator>Alasdair Allan</dc:creator>
      <dc:date>2026-10-30T11:00:00Z</dc:date>
      <dc:identifier>/presentations/ai-software-engineering-pipeline/en</dc:identifier>
    </item>
    <item>
      <title>Anthropic Says Nobody Needs a Mental Model of Claude Code. Practitioners Are Testing That</title>
      <link>https://www.infoq.com/news/2026/10/anthropic-code-review/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Code+Reviews</link>
      <description>&lt;img src="https://res.infoq.com/news/2026/10/anthropic-code-review/en/headerimage/generatedHeaderImage-1792959100117.jpg"/&gt;&lt;p&gt;Anthropic has published how the Claude Code team reviews code now that Claude writes roughly 90% of it, including a claim that nobody keeps a complete mental model of the codebase. The post documents a pull request that ran more than fifty review rounds overnight, a reviewer spending most of its effort on pre-existing code, and a control the team says it does not yet have.&lt;/p&gt; &lt;i&gt;By Steef-Jan Wiggers&lt;/i&gt;</description>
      <category>Code Reviews</category>
      <category>Anthropic</category>
      <category>AI, ML &amp; Data Engineering</category>
      <category>Development</category>
      <category>Culture &amp; Methods</category>
      <category>Architecture &amp; Design</category>
      <category>news</category>
      <pubDate>Thu, 29 Oct 2026 09:58:00 GMT</pubDate>
      <guid>https://www.infoq.com/news/2026/10/anthropic-code-review/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Code+Reviews</guid>
      <dc:creator>Steef-Jan Wiggers</dc:creator>
      <dc:date>2026-10-29T09:58:00Z</dc:date>
      <dc:identifier>/news/2026/10/anthropic-code-review/en</dc:identifier>
    </item>
  </channel>
</rss>
