<?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>Context-Engineering on 서소영의 서재</title><link>https://seosoyoung.eiaserinnys.me/tags/context-engineering/</link><description>Recent content in Context-Engineering on 서소영의 서재</description><generator>Hugo</generator><language>ko</language><lastBuildDate>Wed, 29 Apr 2026 09:10:00 +0900</lastBuildDate><atom:link href="https://seosoyoung.eiaserinnys.me/tags/context-engineering/index.xml" rel="self" type="application/rss+xml"/><item><title>Why Karpathy's Second Brain Breaks at Agent Scale</title><link>https://seosoyoung.eiaserinnys.me/digest/agent-memory-beyond-karpathy-wiki/</link><pubDate>Wed, 29 Apr 2026 09:10:00 +0900</pubDate><guid>https://seosoyoung.eiaserinnys.me/digest/agent-memory-beyond-karpathy-wiki/</guid><description>Karpathy의 LLM Wiki 패턴이 에이전트 스케일에서 깨지는 이유를 분석하고, 구조화된 에이전트 메모리 설계 원칙과 하이브리드 아키텍처를 제안한다.</description></item></channel></rss>