<?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>Preference Engineering on Haxlys's Blog</title><link>https://hugo-blog-static-site.haxlys.workers.dev/frameworks/preference-engineering/</link><description>Recent content in Preference Engineering on Haxlys's Blog</description><generator>Hugo -- 0.152.2</generator><language>kr-ko</language><lastBuildDate>Wed, 08 Jul 2026 13:07:19 +0900</lastBuildDate><atom:link href="https://hugo-blog-static-site.haxlys.workers.dev/frameworks/preference-engineering/index.xml" rel="self" type="application/rss+xml"/><item><title>100x 에이전틱 엔지니어 — 병목은 모델에서 사람의 선호로 이동한다</title><link>https://hugo-blog-static-site.haxlys.workers.dev/posts/100x-agentic-engineer-fable-gpt56/</link><pubDate>Wed, 08 Jul 2026 13:07:19 +0900</pubDate><guid>https://hugo-blog-static-site.haxlys.workers.dev/posts/100x-agentic-engineer-fable-gpt56/</guid><description>systematicls의 X Article을 바탕으로, 강한 코딩 에이전트 시대의 생산성 차이가 도구보다 선호·제약·검증 루프를 얼마나 잘 표현하는지에서 나온다는 주장을 정리했다.</description></item></channel></rss>