<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Jannik Agethen</title><description>Jannik Agethen — independent engineer. Open-source models, local inference, security tooling, and agent systems.</description><link>https://jannik-agethen.com/</link><item><title>What I am building: an open cybersecurity agent</title><link>https://jannik-agethen.com/writing/open-cybersecurity-agent/</link><guid isPermaLink="true">https://jannik-agethen.com/writing/open-cybersecurity-agent/</guid><description>A model and a harness for security work, released open source. Written down early so the claims are checkable later.</description><pubDate>Tue, 04 Aug 2026 00:00:00 GMT</pubDate></item><item><title>The decade of the agent</title><link>https://jannik-agethen.com/writing/decade-of-the-agent/</link><guid isPermaLink="true">https://jannik-agethen.com/writing/decade-of-the-agent/</guid><description>Agents are oversold on timeline, not on direction. The gap between a demo and a system that survives a bad Tuesday is where the whole argument lives.</description><pubDate>Tue, 28 Jul 2026 00:00:00 GMT</pubDate></item><item><title>The bottleneck moved</title><link>https://jannik-agethen.com/writing/the-bottleneck-moved/</link><guid isPermaLink="true">https://jannik-agethen.com/writing/the-bottleneck-moved/</guid><description>AI did not kill software engineering. It made writing code cheap, which relocated the hard part to deciding what to build and proving it works.</description><pubDate>Fri, 19 Jun 2026 00:00:00 GMT</pubDate></item><item><title>Cheaper thinking, more work</title><link>https://jannik-agethen.com/writing/cheaper-thinking/</link><guid isPermaLink="true">https://jannik-agethen.com/writing/cheaper-thinking/</guid><description>The mass-unemployment argument assumes demand for cognitive work is fixed. Every previous time we made something dramatically cheaper, it was not.</description><pubDate>Fri, 22 May 2026 00:00:00 GMT</pubDate></item></channel></rss>