<?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>知识存储 on AI 实战派 · 从技术到赚钱</title><link>https://guijiagi.com/tags/%E7%9F%A5%E8%AF%86%E5%AD%98%E5%82%A8/</link><description>Recent content in 知识存储 on AI 实战派 · 从技术到赚钱</description><generator>Hugo</generator><language>zh-cn</language><copyright>本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权</copyright><lastBuildDate>Wed, 28 Oct 2026 07:17:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E7%9F%A5%E8%AF%86%E5%AD%98%E5%82%A8/index.xml" rel="self" type="application/rss+xml"/><item><title>参数里固化与上下文里流动：硅基知识的两种存储哲学</title><link>https://guijiagi.com/posts/2026-10-28-12-silicon-knowledge-two-storage-philosophies/</link><pubDate>Wed, 28 Oct 2026 07:17:00 +0800</pubDate><guid>https://guijiagi.com/posts/2026-10-28-12-silicon-knowledge-two-storage-philosophies/</guid><description>大模型把知识焊进参数、又在推理时靠上下文临时装配，解读这两种存储方式的分工与权衡。</description></item></channel></rss>