<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
  <channel>
    <title>links.lmorchard.com - #vectors</title>
    <link>/tags/vectors/</link>
    <description>Recent bookmarks tagged #vectors</description>
    <lastBuildDate>Mon, 02 Nov 2026 08:24:53 +0000</lastBuildDate>
    <item>
      <title>Vector &amp; Vertex | Roger Boesch | Substack</title>
      <link>https://vectrex.substack.com/</link>
      <description>Building the future on 1982 hardware. A devlog about Vectrex engineering, modern indie dev, and the code that connects them. Click to read Vector &amp; Vertex, by Roger Boesch, a Substack publication with hundreds of subscribers.&lt;br/&gt;&#xA;&lt;p&gt;&lt;strong&gt;Tags:&lt;/strong&gt; #feeds:subscriptions #gaming #retro #vectors #vectrex&lt;/p&gt;</description>
      <pubDate>Wed, 07 Oct 2026 03:08:23 +0000</pubDate>
      <guid isPermaLink="false">linkding-ssg:bookmark:38791</guid>
      <category>feeds:subscriptions</category>
      <category>gaming</category>
      <category>retro</category>
      <category>vectors</category>
      <category>vectrex</category>
      <enclosure url="https://links.lmorchard.com/static/017a92117755a191ddded27a1c6a454a.jpg" type="image/jpeg"></enclosure>
    </item>
    <item>
      <title>VectorVFS: Your Filesystem as a Vector Database</title>
      <link>https://vectorvfs.readthedocs.io/en/latest/</link>
      <description>VectorVFS is a lightweight Python package that transforms your Linux filesystem into a vector database by leveraging the native VFS (Virtual File System) extended attributes. Rather than maintaining a separate index or external database, VectorVFS stores vector embeddings directly alongside each file—turning your existing directory structure into an efficient and semantically searchable embedding store.&lt;br/&gt;&#xA;&lt;p&gt;&lt;strong&gt;Tags:&lt;/strong&gt; #ai #embeddings #llm #ml #search #vectordbs #vectors&lt;/p&gt;</description>
      <pubDate>Wed, 07 May 2025 22:05:49 +0000</pubDate>
      <guid isPermaLink="false">linkding-ssg:bookmark:29533</guid>
      <category>ai</category>
      <category>embeddings</category>
      <category>llm</category>
      <category>ml</category>
      <category>search</category>
      <category>vectordbs</category>
      <category>vectors</category>
    </item>
    <item>
      <title>Vector Databases Are the Wrong Abstraction</title>
      <link>https://www.timescale.com/blog/vector-databases-are-the-wrong-abstraction/</link>
      <description>A more effective abstraction is conceptualizing vector embeddings not as independent tables or data types but as a specialized index on the embedded data. This is not to say that vector embeddings are literally indexes in the traditional sense, like those in PostgreSQL or MySQL, which retrieve entire data rows from indexed tables. Instead, vector embeddings function as an indexing mechanism that retrieves the most relevant parts of the data based on its embeddings.&lt;br/&gt;&#xA;&lt;p&gt;&lt;strong&gt;Tags:&lt;/strong&gt; #ai #databases #dev #embeddings #ml #postgres #vectors&lt;/p&gt;</description>
      <pubDate>Tue, 29 Oct 2024 23:29:14 +0000</pubDate>
      <guid isPermaLink="false">linkding-ssg:bookmark:29939</guid>
      <category>ai</category>
      <category>databases</category>
      <category>dev</category>
      <category>embeddings</category>
      <category>ml</category>
      <category>postgres</category>
      <category>vectors</category>
    </item>
  </channel>
</rss>
