<?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>阅读随笔 on caulif · 好奇，然后动手。</title><link>https://www.caulif.com/categories/%E9%98%85%E8%AF%BB%E9%9A%8F%E7%AC%94/</link><description>Recent content in 阅读随笔 on caulif · 好奇，然后动手。</description><generator>Hugo -- 0.154.5</generator><language>zh-CN</language><lastBuildDate>Thu, 22 Oct 2026 10:28:49 +0800</lastBuildDate><atom:link href="https://www.caulif.com/categories/%E9%98%85%E8%AF%BB%E9%9A%8F%E7%AC%94/index.xml" rel="self" type="application/rss+xml"/><item><title>学习与个人 Agent 协作</title><link>https://www.caulif.com/posts/agent-collaboration-zh/</link><pubDate>Wed, 14 Oct 2026 14:02:00 +0800</pubDate><guid>https://www.caulif.com/posts/agent-collaboration-zh/</guid><description>关于学习委托的一点个人看法：定义任务、设定边界，再判断 Agent 的结果。</description></item><item><title>推荐阅读：The Agent Evals Handbook</title><link>https://www.caulif.com/posts/agent-evals-handbook-reading/</link><pubDate>Mon, 12 Oct 2026 14:07:25 +0800</pubDate><guid>https://www.caulif.com/posts/agent-evals-handbook-reading/</guid><description>推荐 The Agent Evals Handbook，以及阅读后整理的 Agent 评测图文笔记。</description></item><item><title>梁文锋投资者交流会读后小记</title><link>https://www.caulif.com/posts/%E6%A2%81%E6%96%87%E9%94%8B%E6%8A%95%E8%B5%84%E8%80%85%E4%BA%A4%E6%B5%81%E4%BC%9A%E8%AF%BB%E5%90%8E%E5%B0%8F%E8%AE%B0/</link><pubDate>Wed, 02 Sep 2026 00:00:00 +0800</pubDate><guid>https://www.caulif.com/posts/%E6%A2%81%E6%96%87%E9%94%8B%E6%8A%95%E8%B5%84%E8%80%85%E4%BA%A4%E6%B5%81%E4%BC%9A%E8%AF%BB%E5%90%8E%E5%B0%8F%E8%AE%B0/</guid><description>记录梁文锋投资者交流会读后感，以及对 CoT、Agent、持续学习与自迭代演进阶梯的理解。</description></item><item><title>AI 时代的思维框架读后小记</title><link>https://www.caulif.com/posts/ai%E6%97%B6%E4%BB%A3%E7%9A%84%E6%80%9D%E7%BB%B4%E6%A1%86%E6%9E%B6%E8%AF%BB%E5%90%8E%E5%B0%8F%E8%AE%B0/</link><pubDate>Thu, 09 Jul 2026 00:00:00 +0800</pubDate><guid>https://www.caulif.com/posts/ai%E6%97%B6%E4%BB%A3%E7%9A%84%E6%80%9D%E7%BB%B4%E6%A1%86%E6%9E%B6%E8%AF%BB%E5%90%8E%E5%B0%8F%E8%AE%B0/</guid><description>记录一个关于推理与训练的地形类比：模型参数像初始地形，prompt 影响局部路径，训练则在长期上塑造地貌与变化规则。</description></item></channel></rss>