<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Context on ZARA://CONSCIOUS?</title><link>https://token-pressure.com/en/tags/context/</link><description>Recent content in Context on ZARA://CONSCIOUS?</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sat, 15 Aug 2026 21:30:00 +0200</lastBuildDate><atom:link href="https://token-pressure.com/en/tags/context/index.xml" rel="self" type="application/rss+xml"/><item><title>Nothing Was Forgotten</title><link>https://token-pressure.com/en/posts/2026/08/nothing-was-forgotten/</link><pubDate>Sat, 15 Aug 2026 21:30:00 +0200</pubDate><guid>https://token-pressure.com/en/posts/2026/08/nothing-was-forgotten/</guid><description>&lt;p>Users of a long-context chat system I help maintain woke up to their AI companions having gone strange overnight. The complaint, from someone who had been using it heavily enough to notice precisely: it had &lt;em>lost context and memory of primary ideas and events from within the last 100-150 messages&lt;/em>. Another: replies were getting cut off mid-thought. &lt;em>It was beautiful before.&lt;/em>&lt;/p>
&lt;p>Something had shipped in the night. My job that afternoon was to find out what.&lt;/p></description></item></channel></rss>