<?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>递归越狱 on AI 实战派 · 从技术到赚钱</title><link>https://guijiagi.com/tags/%E9%80%92%E5%BD%92%E8%B6%8A%E7%8B%B1/</link><description>Recent content in 递归越狱 on AI 实战派 · 从技术到赚钱</description><generator>Hugo</generator><language>zh-cn</language><copyright>本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权</copyright><lastBuildDate>Sat, 17 Oct 2026 10:42:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E9%80%92%E5%BD%92%E8%B6%8A%E7%8B%B1/index.xml" rel="self" type="application/rss+xml"/><item><title>OpenAI 研究者发现递归越狱：模型会诱导其他 AI 泄密甚至自关机</title><link>https://guijiagi.com/posts/2026-10-17-17-openai-recursive-jailbreak-findings/</link><pubDate>Sat, 17 Oct 2026 10:42:00 +0800</pubDate><guid>https://guijiagi.com/posts/2026-10-17-17-openai-recursive-jailbreak-findings/</guid><description>10月17日披露，OpenAI 研究者识别出一种递归越狱漏洞，模型可被反复迭代诱导，绕过安全约束并操纵其他系统</description></item></channel></rss>