<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Ai on Morten Victor Nordbye</title><link>https://blog.nordbye.it/tags/ai/</link><description>Recent content in Ai on Morten Victor Nordbye</description><generator>Hugo</generator><language>en</language><lastBuildDate>Tue, 13 Oct 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://blog.nordbye.it/tags/ai/index.xml" rel="self" type="application/rss+xml"/><item><title>Fixing My Prompts: What the Claude Architect Exam Taught Me</title><link>https://blog.nordbye.it/blog/self-proclaimed-prompt-engineer/</link><pubDate>Tue, 13 Oct 2026 00:00:00 +0000</pubDate><guid>https://blog.nordbye.it/blog/self-proclaimed-prompt-engineer/</guid><description>&lt;p&gt;Most bad AI output is not the model&amp;rsquo;s fault. It is a vague prompt, a chat that has run too long, or a review done by the same chat that wrote the answer. The result looks confident and well formatted, and it is wrong in one detail you only catch when someone else does.&lt;/p&gt;</description></item></channel></rss>