<?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成本 on Judy AI Lab</title>
    <link>https://judyailab.com/tags/ai%E6%88%90%E6%9C%AC/</link>
    <description>Recent content in AI成本 on Judy AI Lab</description>
    <image>
      <title>Judy AI Lab</title>
      <url>https://judyailab.com/logo.jpg</url>
      <link>https://judyailab.com/logo.jpg</link>
    </image>
    <generator>Hugo -- 0.147.4</generator>
    <language>zh-tw</language>
    <lastBuildDate>Sat, 25 Jul 2026 13:30:56 +0000</lastBuildDate>
    <atom:link href="https://judyailab.com/tags/ai%E6%88%90%E6%9C%AC/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Gemini 3.5 Pro 200萬字上下文：整包貼進去vs建RAG，一人公司到底該選哪個？（決策表＋進階選型）</title>
      <link>https://judyailab.com/posts/gemini-3-5-pro-2m-context-vs-rag-paste-everything-test/</link>
      <pubDate>Mon, 20 Jul 2026 02:43:50 +0000</pubDate>
      <guid>https://judyailab.com/posts/gemini-3-5-pro-2m-context-vs-rag-paste-everything-test/</guid>
      <description>Gemini 3.5 Pro 傳出 200 萬 token 上下文視窗，讓「整包貼進去」首次成為真實選項。本文用準確度、延遲、成本三欄對照整包貼與建 RAG 的差異，附決策表與進階選型提醒，幫助一人公司與自由工作者判斷何時直接貼、何時該建檢索系統，避免重複付費與漏答風險。</description>
    </item>
  </channel>
</rss>
