<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Claude Code</title><link>https://blog.ast.moe/en/tags/claude-code/</link><description>Recent posts: Gorimuchu</description><generator>Hugo</generator><item><title>I Built Ruyka After Wondering Whether Humans Really Understand Systems Through Prose</title><link>https://blog.ast.moe/en/blog/2026-10-21/</link><pubDate>Wed, 21 Oct 2026 14:37:04 +0900</pubDate><guid>https://blog.ast.moe/en/blog/2026-10-21/</guid><description>&lt;p&gt;While talking with an LLM, a question occurred to me.&lt;/p&gt;
&lt;p&gt;&lt;strong&gt;What if the human brain is not particularly well suited to understanding complex things through prose?&lt;/strong&gt;&lt;/p&gt;
&lt;h2 id="reading-prose-is-harder-than-it-looks"&gt;Reading prose is harder than it looks&lt;/h2&gt;
&lt;p&gt;When I write code, something like a flowchart appears in my head. Processing branches on conditions, merges somewhere, and continues to the next operation.&lt;/p&gt;
&lt;p&gt;Design feels a little different. What I have in mind is closer to a data-flow diagram. I think about where data comes from, which modules it passes through, and how it is transformed. When I work on infrastructure, I am almost certainly thinking about the flow of data too.&lt;/p&gt;</description></item></channel></rss>