<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>MINJUN PARK — Technical Publication</title><description>Systems, AI infrastructure, research, mathematics, security, and technical experiments.</description><link>https://0archlinux0.github.io/</link><language>en</language><item><title>I Let AI Agents Run a Nationwide CTF. The Hard Part Wasn&apos;t Solving the Challenges.</title><link>https://0archlinux0.github.io/posts/nationwide-ctf-ai-agent-automation-retrospective/</link><guid isPermaLink="true">https://0archlinux0.github.io/posts/nationwide-ctf-ai-agent-automation-retrospective/</guid><description>I review the AI-agent pipeline I used at Japan&apos;s Ministry of Internal Affairs and Communications nationwide CTF, separating the official 26th-place, 5,701-point result from local tracker data and documenting gaps in orchestration, state, verification, and observability.</description><pubDate>Mon, 05 Oct 2026 00:00:00 GMT</pubDate><category>Systems</category><category>AI Engineering</category></item></channel></rss>