<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>技术科普 on Text Matrix</title><link>https://txtmix.com/tags/%E6%8A%80%E6%9C%AF%E7%A7%91%E6%99%AE/</link><description>Recent content in 技术科普 on Text Matrix</description><generator>Hugo</generator><language>zh-CN</language><lastBuildDate>Tue, 03 Nov 2026 15:55:51 +0800</lastBuildDate><atom:link href="https://txtmix.com/tags/%E6%8A%80%E6%9C%AF%E7%A7%91%E6%99%AE/index.xml" rel="self" type="application/rss+xml"/><item><title>GLM 是怎么在自己修自己的基础设施的？一篇给非专业读者的科普解读</title><link>https://txtmix.com/posts/tech/zai-glm-inference-infrastructure-explained/</link><pubDate>Thu, 17 Sep 2026 19:10:00 +0800</pubDate><guid>https://txtmix.com/posts/tech/zai-glm-inference-infrastructure-explained/</guid><description>&lt;h1 id="glm-是怎么在自己修自己的基础设施的一篇给非专业读者的科普解读"&gt;GLM 是怎么在自己修自己的基础设施的？一篇给非专业读者的科普解读&lt;/h1&gt;
&lt;blockquote&gt;
&lt;p&gt;原文：&lt;a href="https://z.ai/blog/glm-built-its-inference-infrastructure" target="_blank" rel="noopener noreffer "&gt;z.ai/blog/glm-built-its-inference-infrastructure&lt;/a&gt; — Toward Recursive Self-Improvement: How GLM Built Its Own Inference Infrastructure（智谱 GLM 团队，2026 年 9 月）&lt;/p&gt;</description></item></channel></rss>