<?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>Vision on jamesm.blog</title>
    <link>https://jamesm.blog/tags/vision/</link>
    <description>Recent content in Vision on jamesm.blog</description>
    <image>
      <title>jamesm.blog</title>
      <url>https://jamesm.blog/papermod-cover.png</url>
      <link>https://jamesm.blog/papermod-cover.png</link>
    </image>
    <generator>Hugo</generator>
    <language>en</language>
    <lastBuildDate>Sat, 09 May 2026 08:00:00 +0100</lastBuildDate>
    <atom:link href="https://jamesm.blog/tags/vision/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Multimodal AI in 2026: Vision &#43; Text &#43; Audio - What&#39;s Actually Useful</title>
      <link>https://jamesm.blog/ai/multimodal-ai-2026/</link>
      <pubDate>Sat, 09 May 2026 08:00:00 +0100</pubDate>
      <guid>https://jamesm.blog/ai/multimodal-ai-2026/</guid>
      <description>Where multimodal AI has actually delivered value in 2026, where it is still demoware, and the patterns that determine whether vision and audio are quietly indispensable in your stack or just an expensive distraction.</description>
    </item>
  </channel>
</rss>
