<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>State Space on Uni Matrix Zero</title><link>https://unimatrixz.com/tags/state-space/</link><description>Recent content in State Space on Uni Matrix Zero</description><generator>Hugo</generator><language>en</language><copyright>Stephan Froede</copyright><lastBuildDate>Sun, 11 Oct 2026 18:58:57 +0200</lastBuildDate><atom:link href="https://unimatrixz.com/tags/state-space/index.xml" rel="self" type="application/rss+xml"/><item><title>The Problem Is Not the Graph</title><link>https://unimatrixz.com/topics/ai-production-architecture/the-problem-is-not-the-graph/</link><pubDate>Sun, 11 Oct 2026 00:00:00 +0000</pubDate><guid>https://unimatrixz.com/topics/ai-production-architecture/the-problem-is-not-the-graph/</guid><description>&lt;p&gt;The wrong conclusion to draw from Harpy is that graphs are the problem. The more consequential limitation was the world in which Harpy could operate: a tightly constrained vocabulary, grammar and task. Its graph encoded that limitation, but was not identical to it.&lt;/p&gt;
&lt;p&gt;That distinction matters whenever knowledge graphs are contrasted with statistical learning. A graph can be brittle. It can be too expensive to curate. It can hard-code a mistaken ontology. None of those facts make graph structure inherently incompatible with learning—or establish that removing explicit structure creates an open-world system.&lt;/p&gt;</description></item></channel></rss>