<?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>Chain-of-Thought on AI Tech Blog</title>
    <link>https://jesamkim.github.io/ai-tech-blog/tags/chain-of-thought/</link>
    <description>Recent content in Chain-of-Thought on AI Tech Blog</description>
    <generator>Hugo -- 0.147.6</generator>
    <language>ko</language>
    <lastBuildDate>Wed, 01 Jul 2026 14:00:00 +0900</lastBuildDate>
    <atom:link href="https://jesamkim.github.io/ai-tech-blog/tags/chain-of-thought/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>AI가 생각하는 과정을 읽는다는 것 — reasoning trace 논문 4편</title>
      <link>https://jesamkim.github.io/ai-tech-blog/posts/2026-07-01-reading-llm-reasoning-traces/</link>
      <pubDate>Wed, 01 Jul 2026 14:00:00 +0900</pubDate>
      <guid>https://jesamkim.github.io/ai-tech-blog/posts/2026-07-01-reading-llm-reasoning-traces/</guid>
      <description>reasoning model이 쏟아내는 긴 trace를 &amp;#39;읽는다&amp;#39;는 말은 하나가 아닙니다. 사람이 읽기, 인지 단위로 쪼개기, 모델 내부 신호로 보기 — 세 가지 뜻을 논문 4편으로 짚어봅니다.</description>
    </item>
  </channel>
</rss>
