<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Agents on Incompetence Notwithstanding</title><link>https://incompetencenotwithstanding.com/tags/agents/</link><description>Recent content in Agents on Incompetence Notwithstanding</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 31 Aug 2026 21:00:00 +1000</lastBuildDate><atom:link href="https://incompetencenotwithstanding.com/tags/agents/index.xml" rel="self" type="application/rss+xml"/><item><title>The Unreasonable Effectiveness of Reading Your System Prompt</title><link>https://incompetencenotwithstanding.com/posts/unreasonable-effectiveness-of-reading-your-system-prompt/</link><pubDate>Mon, 31 Aug 2026 21:00:00 +1000</pubDate><guid>https://incompetencenotwithstanding.com/posts/unreasonable-effectiveness-of-reading-your-system-prompt/</guid><description>A 10k-token system prompt is about 7,500 words, which is half an hour of reading. Nobody does it, and every time I have, I&amp;rsquo;ve come away with a cleaner prompt and a bump in evals.</description></item></channel></rss>