
  <rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
    <channel>
      <title>Indo Yoon</title>
      <link>https://devbull.xyz/blog</link>
      <description>Rustacean, Pythonista, and [Type|Java]Scripter</description>
      <language>ko</language>
      <managingEditor>freedomzero91@gmail.com (Indo Yoon)</managingEditor>
      <webMaster>freedomzero91@gmail.com (Indo Yoon)</webMaster>
      <lastBuildDate>Fri, 06 Nov 2026 00:00:00 GMT</lastBuildDate>
      <atom:link href="https://devbull.xyz/tags/ai-agents/feed.xml" rel="self" type="application/rss+xml"/>
      
  <item>
    <guid>https://devbull.xyz/blog/ai-native-language-billing-first-en</guid>
    <title>Look at the bill before you build a language AI prefers</title>
    <link>https://devbull.xyz/blog/ai-native-language-billing-first-en</link>
    <description>Could a language built for AI beat TypeScript and Rust? Decompose a real agent bill and code text is 0.8%. I ran the experiment myself: a 29x larger repo raised input tokens by only 18%. The bottleneck is harness fixed cost, not syntax.</description>
    <pubDate>Fri, 06 Nov 2026 00:00:00 GMT</pubDate>
    <author>freedomzero91@gmail.com (Indo Yoon)</author>
    <category>AI Agents</category><category>LLM</category><category>Cost Analysis</category>
  </item>

    </channel>
  </rss>
