<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>EntropyOS on Stack Research</title><link>https://stackresearch.org/tags/entropyos/</link><description>Recent content in EntropyOS on Stack Research</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sat, 14 Mar 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://stackresearch.org/tags/entropyos/index.xml" rel="self" type="application/rss+xml"/><item><title>Memory Should Decay</title><link>https://stackresearch.org/research/memory-should-decay/</link><pubDate>Sat, 14 Mar 2026 00:00:00 +0000</pubDate><guid>https://stackresearch.org/research/memory-should-decay/</guid><description>&lt;p&gt;An agent memory run started with 50 stored facts. Each fact had a half-life of 10 ticks. After 30 ticks of a task loop, 8 memories remained.&lt;/p&gt;
&lt;p&gt;Those 8 were the ones the agent kept using. The other 42 expired automatically. No cleanup script. No manual pruning. No summarization pass pretending stale facts were still useful.&lt;/p&gt;
&lt;p&gt;The experiment is small, but the shape is important. Agent memory does not need to be an attic where every fact waits forever. It can behave more like working state: reinforced by use, weakened by neglect, and removed when confidence falls below a threshold.&lt;/p&gt;</description></item></channel></rss>