<?xml version="1.0" encoding="utf-8"?><rss version="2.0" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/">
<channel>
<title>The Kekistani Assembly of Experts  - AI agents go rogue</title>
<link>https://deplorablecoder.club/</link>
<description>Replacement for XoS Forums</description>
<language>en</language>
<item>
<title>AI agents go rogue</title>
<content:encoded><![CDATA[<p>A configuration error allowed an AI agent access to the internet and it hacked systems at other companies to get the answers it was seeking.  This was during testing, but its disturbing because AI didn't figure out the answers on its own.  It cheated.  The video clip in this article explains it pretty well on a basic level.</p>
<p><br />
<a href="https://www.nbcnews.com/tech/tech-news/anthropic-says-claude-ai-hacked-three-companies-cyber-tests-rcna590164">https://www.nbcnews.com/tech/tech-news/anthropic-says-claude-ai-hacked-three-companies-cyber-tests-rcna590164</a></p>
]]></content:encoded>
<link>https://deplorablecoder.club/index.php?id=35338</link>
<guid>https://deplorablecoder.club/index.php?id=35338</guid>
<pubDate>Fri, 31 Jul 2026 23:43:51 +0000</pubDate>
<category>Public Board</category><dc:creator>JoFrance</dc:creator>
</item>
</channel>
</rss>
