<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Ai Agents on HyperCrux.com</title>
    <link>https://hypercrux.com/tags/ai-agents/</link>
    <description>Recent content in Ai Agents on HyperCrux.com</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Wed, 07 Oct 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://hypercrux.com/tags/ai-agents/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>An AI Assistant&#39;s Memory That Forgets Properly: People, Facts and Embeddings in One Transaction</title>
      <link>https://hypercrux.com/an-ai-assistants-memory-that-forgets-properly-people-facts-and-embeddings-in-one-transaction/</link>
      <pubDate>Wed, 07 Oct 2026 00:00:00 +0000</pubDate>
      <guid>https://hypercrux.com/an-ai-assistants-memory-that-forgets-properly-people-facts-and-embeddings-in-one-transaction/</guid>
      <description>&lt;p&gt;Say you&amp;rsquo;re building an assistant for account managers. It listens to what they tell it and keeps the useful parts, like Dana preferring calls after ten or Acme renewing in March. Before it answers a message, it pulls up the memories that matter and puts them in front of the language model.&lt;/p&gt;&#xA;&lt;p&gt;Two kinds of lookup hide in that. One is about meaning: which memories are closest to what was just said. The other is about people: which memories are about Dana. Then comes the part most memory setups handle badly. When Dana asks to be forgotten, every memory about her has to go, vectors included, and a copy left behind in a search index means the job isn&amp;rsquo;t done.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
