<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>DevMindscape</title><link>https://devmindscape.com/</link><description>AI is cheaper than you think, and it's here to stay. Learn to build your own software with it — and the judgment required to actually ship it.</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 02 Sep 2026 12:36:27 +0000</lastBuildDate><atom:link href="https://devmindscape.com/tags/deepseek-v4/index.xml" rel="self" type="application/rss+xml"/><item><title>I Gave DeepSeek V4 Pro Vision</title><link>https://devmindscape.com/post/deepseek-vision/</link><pubDate>Mon, 24 Aug 2026 00:00:00 +0000</pubDate><guid isPermaLink="true">https://devmindscape.com/post/deepseek-vision/</guid><description>&lt;p>You may think DeepSeek V4 Pro is not a multimodal model. It only accepts text, no images. I didn&amp;rsquo;t realize that until I watched &lt;a href="https://www.youtube.com/@t3dotgg">Theo&amp;rsquo;s&lt;/a> video ranking DeepSeek V4 Pro near the bottom, purely because it doesn&amp;rsquo;t have vision.&lt;/p></description></item></channel></rss>