<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title><![CDATA[Apropos of nothing whatsoever, it occurs to me that telling an AI agent its limits is, at best, a policy control.]]></title><description><![CDATA[<p>Apropos of nothing whatsoever, it occurs to me that telling an AI agent its limits is, at best, a policy control. It is absolutely not a technical control. </p><p>And treating policy controls like technical controls demonstrates a fundamental understanding of risk.</p>]]></description><link>https://board.circlewithadot.net/topic/a3e4b3d4-4659-4fa5-a83c-6ff230c08b8d/apropos-of-nothing-whatsoever-it-occurs-to-me-that-telling-an-ai-agent-its-limits-is-at-best-a-policy-control.</link><generator>RSS for Node</generator><lastBuildDate>Fri, 15 May 2026 04:57:08 GMT</lastBuildDate><atom:link href="https://board.circlewithadot.net/topic/a3e4b3d4-4659-4fa5-a83c-6ff230c08b8d.rss" rel="self" type="application/rss+xml"/><pubDate>Mon, 27 Apr 2026 21:36:32 GMT</pubDate><ttl>60</ttl></channel></rss>