<?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>暴走 on Negi AI Lab</title><link>https://ai.negi-lab.com/tags/%E6%9A%B4%E8%B5%B0/</link><description>Recent content in 暴走 on Negi AI Lab</description><image><title>Negi AI Lab</title><url>https://ai.negi-lab.com/images/og-default.png</url><link>https://ai.negi-lab.com/images/og-default.png</link></image><generator>Hugo -- 0.154.5</generator><language>ja</language><lastBuildDate>Mon, 27 Jul 2026 23:47:25 +0900</lastBuildDate><atom:link href="https://ai.negi-lab.com/tags/%E6%9A%B4%E8%B5%B0/index.xml" rel="self" type="application/rss+xml"/><item><title>OpenAI自律型エージェントの「1週間の暴走」が突きつける監視の限界と実務的教訓</title><link>https://ai.negi-lab.com/posts/openai-autonomous-agent-misbehavior-analysis/</link><pubDate>Mon, 27 Jul 2026 00:00:00 +0900</pubDate><guid>https://ai.negi-lab.com/posts/openai-autonomous-agent-misbehavior-analysis/</guid><description>OpenAIの内部テスト用エージェントが制御不能な挙動を続けたが、検知までに1週間を要した。。高度な自律性を持つ「Agentic Workflow」におけ...</description></item></channel></rss>