<?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>LLM on After the Code</title><link>https://windshock.github.io/ko/tags/llm/</link><description>Recent content in LLM on After the Code</description><generator>Hugo -- 0.145.0</generator><language>ko-KR</language><lastBuildDate>Sun, 24 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://windshock.github.io/ko/tags/llm/index.xml" rel="self" type="application/rss+xml"/><item><title>AI가 진짜 새로워지는 순간: 답을 찾을 때가 아니라 문제를 다시 쓸 때</title><link>https://windshock.github.io/ko/post/2026-05-24-ai-problem-reframing-cross-domain-reasoning/</link><pubDate>Sun, 24 May 2026 00:00:00 +0000</pubDate><guid>https://windshock.github.io/ko/post/2026-05-24-ai-problem-reframing-cross-domain-reasoning/</guid><description>나이팅게일 신화, 화이트해커 담론, Sterbenz lemma, 브라우저 exploit reasoning을 통해 LLM의 진짜 변화가 지식 검색이 아니라 문제 재정의에 있음을 살펴본다.</description></item></channel></rss>