<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Feedback on Architect PARK JUN WOO</title><link>https://www.parkjunwoo.com/tags/feedback/</link><description>Recent content in Feedback on Architect PARK JUN WOO</description><generator>Hugo</generator><language>en</language><lastBuildDate>Thu, 14 May 2026 18:00:00 +0900</lastBuildDate><atom:link href="https://www.parkjunwoo.com/tags/feedback/index.xml" rel="self" type="application/rss+xml"/><item><title>Feedback Topology Over Model IQ</title><link>https://www.parkjunwoo.com/opinion/feedback-topology/</link><pubDate>Thu, 14 May 2026 18:00:00 +0900</pubDate><guid>https://www.parkjunwoo.com/opinion/feedback-topology/</guid><description>The same model stalls at 40 or completes all 527. The difference is not the model — it is the feedback structure. LLM performance depends far more on how fast and deterministic the feedback loop is than on the model itself.</description></item></channel></rss>