<?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>记忆巩固 on AI 实战派 · 从技术到赚钱</title><link>https://guijiagi.com/tags/%E8%AE%B0%E5%BF%86%E5%B7%A9%E5%9B%BA/</link><description>Recent content in 记忆巩固 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>Sun, 18 Oct 2026 13:30:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E8%AE%B0%E5%BF%86%E5%B7%A9%E5%9B%BA/index.xml" rel="self" type="application/rss+xml"/><item><title>人必须靠遗忘来巩固，AI不遗忘反而是缺陷吗</title><link>https://guijiagi.com/posts/2026-10-18-15-ebbinghaus-forgetting-curve-ai-memory/</link><pubDate>Sun, 18 Oct 2026 13:30:00 +0800</pubDate><guid>https://guijiagi.com/posts/2026-10-18-15-ebbinghaus-forgetting-curve-ai-memory/</guid><description>艾宾浩斯遗忘曲线与间隔重复显示遗忘是自适应功能，大模型倾向全量保留，不遗忘的系统失去了提炼与取舍压力，需要重新评价。</description></item></channel></rss>