<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>AI on Liyixian Blog</title><link>https://liyixian06.github.io/tags/ai/</link><description>Recent content in AI on Liyixian Blog</description><generator>Hugo</generator><language>en-us</language><copyright>© LiYixian 2023</copyright><lastBuildDate>Tue, 12 May 2026 11:34:31 +0800</lastBuildDate><atom:link href="https://liyixian06.github.io/tags/ai/index.xml" rel="self" type="application/rss+xml"/><item><title>Agent 01：从 LLM 到 Agent</title><link>https://liyixian06.github.io/2026/05/agent-01/</link><pubDate>Tue, 12 May 2026 11:34:31 +0800</pubDate><guid>https://liyixian06.github.io/2026/05/agent-01/</guid><description>&lt;h2 id="transformer">Transformer&lt;/h2>
&lt;p>今天几乎所有主流大语言模型——GPT、Claude、Gemini、Qwen、DeepSeek——都建立在 Transformer 架构之上。理解 Transformer，本质上是在理解现代 AI 为什么能够出现。&lt;/p></description></item></channel></rss>