<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet href="/feed.xsl" type="text/xsl"?><rss version="2.0"><channel><title>Airing&apos;s Notes</title><description>Notes on frontend, math, design, philosophy, and everything that sparks my curiosity.</description><link>https://ursb.me/</link><language>en</language><item><title>Claude 101: An Interactive Tour of Claude Code from the AI&apos;s Point of View</title><link>https://ursb.me/en/notes/claude-101-intro/</link><guid isPermaLink="true">https://ursb.me/en/notes/claude-101-intro/</guid><description>Claude 101 is an interactive learning site that uses 16 deep chapters, annotated real source code, and animated visualizations to teach you Claude Code&apos;s complete architecture — from the AI&apos;s first-person perspective.</description><pubDate>Sun, 05 Apr 2026 00:00:00 GMT</pubDate><category>ai</category><category>agent</category><category>architecture</category></item><item><title>Claude Code&apos;s Memory System, Explained</title><link>https://ursb.me/en/notes/claude-code-memory-system/</link><guid isPermaLink="true">https://ursb.me/en/notes/claude-code-memory-system/</guid><description>A deep dive into Claude Code&apos;s Memory system — its 5-layer architecture, 4 memory types, write/retrieve/delete flows, and the three-layer safety mechanism.</description><pubDate>Sun, 05 Apr 2026 00:00:00 GMT</pubDate><category>ai</category><category>agent</category><category>architecture</category></item><item><title>A Visual Guide to OpenHarness: Recreating Claude Code&apos;s Agent Architecture in 3% of the Code</title><link>https://ursb.me/en/notes/openharness-visual-guide/</link><guid isPermaLink="true">https://ursb.me/en/notes/openharness-visual-guide/</guid><description>OpenHarness is an open-source project from HKU&apos;s HKUDS group that recreates Claude Code&apos;s Agent Harness architecture in pure Python — 98% tool coverage in just 11,733 lines of code.</description><pubDate>Sat, 04 Apr 2026 00:00:00 GMT</pubDate><category>ai</category><category>agent</category><category>architecture</category></item><item><title>Understanding AI Coding Through Cybernetics</title><link>https://ursb.me/en/notes/cybernetics-and-ai-coding/</link><guid isPermaLink="true">https://ursb.me/en/notes/cybernetics-and-ai-coding/</guid><description>Cybernetics&apos; feedback loop model maps perfectly onto the AI Coding workflow. From negative feedback loops to Plant complexity to the evolution of control strategies, this framework lets you rethink the nature of human-AI collaboration.</description><pubDate>Sun, 29 Mar 2026 00:00:00 GMT</pubDate><category>cybernetics</category><category>ai</category><category>systems-thinking</category></item></channel></rss>