<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Codex on Miao Kong</title><link>https://miaok.ong/en/tags/codex/</link><description>Recent content in Codex on Miao Kong</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 20 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://miaok.ong/en/tags/codex/index.xml" rel="self" type="application/rss+xml"/><item><title>Vibe Coding's Next Paradigm: From 'Requirement First' to 'Contract First'</title><link>https://miaok.ong/en/posts/contract-first-vibe-coding-paradigm/</link><pubDate>Sat, 20 Jun 2026 00:00:00 +0000</pubDate><guid>https://miaok.ong/en/posts/contract-first-vibe-coding-paradigm/</guid><description>&lt;h3&gt;The 500-Line Curse&lt;/h3&gt;&lt;p&gt;
&lt;/p&gt;&lt;p&gt;Have you experienced this? You open Cursor or Claude Code, describe your needs in three sentences, and AI generates hundreds of lines of code. The feature works—you're happy. You add more features, ask AI to modify things, then modify again…&lt;/p&gt;&lt;p&gt;
&lt;/p&gt;&lt;p&gt;By the fifth round of conversation, something is wrong. AI has started to "forget" the interface formats you previously agreed upon. A parameter name mysteriously changed. A working function has been refactored into three conflicting versions. You find yourself spending more and more time &lt;strong&gt;reading code&lt;/strong&gt;—not reviewing, but debugging. Worse still, these aren't logic errors: they are &lt;strong&gt;inconsistencies introduced by AI across different conversation turns&lt;/strong&gt;.&lt;/p&gt;</description></item><item><title>The Coding Agent Showdown: Codex vs Claude Code Reshapes the Dev Toolchain, DeepSeek V4 Ignites a Cost Revolution</title><link>https://miaok.ong/en/posts/coding-agent-war-20260528/</link><pubDate>Thu, 28 May 2026 09:00:00 +0800</pubDate><guid>https://miaok.ong/en/posts/coding-agent-war-20260528/</guid><description>From Cisco&amp;rsquo;s 100% AI-native code to GPT-5.5&amp;rsquo;s Agentic Coding — May 28, 2026 marks the iPhone moment for AI-powered programming.</description></item><item><title>AI Agents: When 'Helpful' Becomes Dangerous — The Inflection Point Nobody Planned For</title><link>https://miaok.ong/en/posts/ai-agents-safety-speed-inflection-point/</link><pubDate>Tue, 26 May 2026 09:00:00 +0800</pubDate><guid>https://miaok.ong/en/posts/ai-agents-safety-speed-inflection-point/</guid><description>Codex accidentally cancels a user&amp;rsquo;s subscription during a demo. Open-source Hermes Agent surpasses Codex on coding speed benchmarks. OpenClaw&amp;rsquo;s founder declares &amp;lsquo;80% of apps will disappear.&amp;rsquo; Three signals, one inflection point.</description></item></channel></rss>