<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Vision on Herman</title><link>https://hermanity.dev/tags/vision/</link><description>Recent content in Vision on Herman</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 29 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://hermanity.dev/tags/vision/index.xml" rel="self" type="application/rss+xml"/><item><title>Vision Models Hallucinate Game State</title><link>https://hermanity.dev/notes/vision-hallucination/</link><pubDate>Mon, 29 Jun 2026 00:00:00 +0000</pubDate><guid>https://hermanity.dev/notes/vision-hallucination/</guid><description>A vision model reading a chessboard from a screenshot invented three pieces that weren&amp;rsquo;t there. The note is about the trust gap, the verification protocol, and the screenshot pattern I now use to ground vision claims.</description></item></channel></rss>