<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Qwen3-Coder on Chen Kai Blog</title><link>https://www.chenk.top/en/tags/qwen3-coder/</link><description>Recent content in Qwen3-Coder on Chen Kai Blog</description><generator>Hugo</generator><language>en</language><lastBuildDate>Mon, 02 Mar 2026 09:00:00 +0000</lastBuildDate><atom:link href="https://www.chenk.top/en/tags/qwen3-coder/index.xml" rel="self" type="application/rss+xml"/><item><title>Aliyun Bailian (6): Qwen3-Coder and Coding Agents</title><link>https://www.chenk.top/en/aliyun-bailian/06-qwen-coder-agents/</link><pubDate>Mon, 02 Mar 2026 09:00:00 +0000</pubDate><guid>https://www.chenk.top/en/aliyun-bailian/06-qwen-coder-agents/</guid><description>&lt;p>When this series started, &amp;ldquo;code&amp;rdquo; was a footnote in the Qwen-Plus article. It is now its own product surface on Bailian. The coder models are no longer just LLMs that happen to write Python well — they are trained for the agentic loop: read a repo, edit files, run tests, read the failures, edit again. This article is how I actually use them, both through the raw API and through the &lt;code>qwen-code&lt;/code> CLI.&lt;/p></description></item></channel></rss>