<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Memory on AI Notes</title>
    <link>https://ai.ngchi.online/tags/memory/</link>
    <description>Recent content in Memory on AI Notes</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Wed, 23 Sep 2026 13:30:21 +0700</lastBuildDate>
    <atom:link href="https://ai.ngchi.online/tags/memory/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Why Turning Off AI Memory Can Be an Upgrade</title>
      <link>https://ai.ngchi.online/posts/why-turning-off-ai-memory-can-be-an-upgrade/</link>
      <pubDate>Wed, 23 Sep 2026 13:30:21 +0700</pubDate>
      <guid>https://ai.ngchi.online/posts/why-turning-off-ai-memory-can-be-an-upgrade/</guid>
      <description>A developer turned off Claude Code automatic memory and called it his best upgrade - because inferred memory is an invisible layer between a decision and its reason.</description>
    </item>
    <item>
      <title>Hippo: Memory That Knows What to Forget</title>
      <link>https://ai.ngchi.online/posts/hippo-memory-that-knows-what-to-forget/</link>
      <pubDate>Wed, 23 Sep 2026 13:30:12 +0700</pubDate>
      <guid>https://ai.ngchi.online/posts/hippo-memory-that-knows-what-to-forget/</guid>
      <description>An open-source memory layer where memories fade on a 7-day half-life unless retrieval keeps them alive - and an unrelated arXiv paper that independently landed on the same idea.</description>
    </item>
  </channel>
</rss>
