<?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/"><channel><title>Agent on Chuanxilu for Skilled Homo sapiens</title><link>https://blog.chuanxilu.net/en/tags/agent/</link><description>Recent content in Agent on Chuanxilu for Skilled Homo sapiens</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Sat, 18 Apr 2026 10:00:00 +0800</lastBuildDate><atom:link href="https://blog.chuanxilu.net/en/tags/agent/index.xml" rel="self" type="application/rss+xml"/><item><title>Context Rot: An Easily Overlooked Problem in AI Coding</title><link>https://blog.chuanxilu.net/en/posts/2026/04/managing-context-length-in-ai-coding-sessions/</link><pubDate>Sat, 18 Apr 2026 10:00:00 +0800</pubDate><guid>https://blog.chuanxilu.net/en/posts/2026/04/managing-context-length-in-ai-coding-sessions/</guid><description>Someone in a group chat complained that GPT-5.4 performed worse than Doubao, ByteDance&amp;#39;s chatbot—the model would give irrelevant answers without even reading the question. After asking some follow-up questions, I learned they had fed it many documents and the conversation had gone on for a long time. This probably wasn&amp;#39;t the model&amp;#39;s problem—it was context rot. The conversation had gotten so long that the model could no longer &amp;#39;see&amp;#39; the current task clearly. This raises an overlooked problem: in the process of vibe coding or writing, how do you manage context effectively to avoid token and time wasted on model performance degradation?</description></item><item><title>Looking Back: Seven Human-AI Collaboration Patterns in the Aristotle Project</title><link>https://blog.chuanxilu.net/en/posts/2026/04/seven-human-ai-collaboration-patterns-in-aristotle/</link><pubDate>Thu, 16 Apr 2026 21:00:00 +0800</pubDate><guid>https://blog.chuanxilu.net/en/posts/2026/04/seven-human-ai-collaboration-patterns-in-aristotle/</guid><description>Looking back at the Aristotle project—from initial design to the GEAR protocol—I identified seven distinct collaboration patterns between myself and AI. As AI gets more capable, human judgment doesn&amp;#39;t become less important. It becomes more critical.</description></item><item><title>A Markdown's Three Lives: From Static Rules to Git-Backed MCP Server</title><link>https://blog.chuanxilu.net/en/posts/2026/04/from-markdown-to-mcp-server-gear-protocol/</link><pubDate>Thu, 16 Apr 2026 19:00:00 +0800</pubDate><guid>https://blog.chuanxilu.net/en/posts/2026/04/from-markdown-to-mcp-server-gear-protocol/</guid><description>Aristotle&amp;#39;s reflection rules started as a flat Markdown file — append-only, forgotten, no rollback. When dozens of rules accumulated, I realized the file wasn&amp;#39;t enough. This started a design iteration path from append-only to Git-backed MCP Server. That path led to something called GEAR.</description></item><item><title>From Scars to Armor: Harness Engineering in Practice</title><link>https://blog.chuanxilu.net/en/posts/2026/04/from-scars-to-armor-harness-engineering-practice/</link><pubDate>Sat, 11 Apr 2026 01:00:00 +0800</pubDate><guid>https://blog.chuanxilu.net/en/posts/2026/04/from-scars-to-armor-harness-engineering-practice/</guid><description>The first version of Aristotle looked smooth. In practice, it exposed four architectural problems. Fixing them validated the trust model and harness engineering framework from Part 3 — every constraint encodes a trust judgment.</description></item><item><title>Trust Boundaries: The Same Idea on Open and Closed Platforms</title><link>https://blog.chuanxilu.net/en/posts/2026/04/a-trust-boundary-design-experiment/</link><pubDate>Mon, 06 Apr 2026 18:00:00 +0800</pubDate><guid>https://blog.chuanxilu.net/en/posts/2026/04/a-trust-boundary-design-experiment/</guid><description>The same reflection mechanism on different platforms, their complexity differing by an order of magnitude — but the complexity itself reveals a deeper question: when should we trust AI&amp;#39;s judgment, and when should we step in?</description></item><item><title>claude-code-reflect: Same Metacognition, Different Soil</title><link>https://blog.chuanxilu.net/en/posts/2026/04/claude-code-reflect-different-soil/</link><pubDate>Mon, 06 Apr 2026 14:56:00 +0800</pubDate><guid>https://blog.chuanxilu.net/en/posts/2026/04/claude-code-reflect-different-soil/</guid><description>The same reflection mechanism lands on different platform foundations with very different landing postures and paths—from plugin installation to permission pitfalls to API concurrency, documenting the actual development process on Claude Code.</description></item><item><title>Aristotle: Teaching AI to Reflect on Its Mistakes</title><link>https://blog.chuanxilu.net/en/posts/2026/04/aristotle-ai-reflection/</link><pubDate>Mon, 06 Apr 2026 10:00:00 +0800</pubDate><guid>https://blog.chuanxilu.net/en/posts/2026/04/aristotle-ai-reflection/</guid><description>Installing reflection capability into AI coding assistants—when the model makes a mistake, immediately trigger root cause analysis and transform the correction into persistent rules.</description></item></channel></rss>