<?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>Claude Mythos on Peter's Blog</title><link>https://peter-blog.pages.dev/tags/claude-mythos/</link><description>Recent content in Claude Mythos on Peter's Blog</description><generator>Hugo</generator><language>zh-tw</language><lastBuildDate>Wed, 08 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://peter-blog.pages.dev/tags/claude-mythos/index.xml" rel="self" type="application/rss+xml"/><item><title>Anthropic 最新 AI 模型揭發軟體防禦漏洞</title><link>https://peter-blog.pages.dev/tech/anthropic-ai-model-software-vulnerabilities/</link><pubDate>Wed, 08 Apr 2026 00:00:00 +0000</pubDate><guid>https://peter-blog.pages.dev/tech/anthropic-ai-model-software-vulnerabilities/</guid><description>Anthropic 的 Claude Mythos AI 模型發現數千個未修補的軟體漏洞，與網路安全專家合作展開防禦計畫</description></item></channel></rss>