<?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>AI面试 on Plbear | 后端架构 · AI工程 · 云原生技术博客</title><link>https://www.plbear.com/tags/ai%E9%9D%A2%E8%AF%95/</link><description>Recent content in AI面试 on Plbear | 后端架构 · AI工程 · 云原生技术博客</description><generator>Hugo</generator><language>zh-cn</language><lastBuildDate>Tue, 25 Mar 2025 09:00:00 +0800</lastBuildDate><atom:link href="https://www.plbear.com/tags/ai%E9%9D%A2%E8%AF%95/index.xml" rel="self" type="application/rss+xml"/><item><title>Prompt 状态机：AI 面试越级率 0% 的工程化</title><link>https://www.plbear.com/posts/2025-03-25-prompt-state-machine/</link><pubDate>Tue, 25 Mar 2025 09:00:00 +0800</pubDate><guid>https://www.plbear.com/posts/2025-03-25-prompt-state-machine/</guid><description>让 LLM 按流程走完一场面试，最大的敌人是模型自己——它会在第 3 步跳到第 8 步。System 强元规则 + User 变量 + Assistant 预填开场，三层结构把流程越级率压到 0%。</description></item></channel></rss>