<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>AI/ML on</title><link>https://www.alexander-koepke.de/categories/ai/ml/</link><description>Recent content in AI/ML on</description><generator>Hugo</generator><language>de-de</language><lastBuildDate>Sat, 31 May 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://www.alexander-koepke.de/categories/ai/ml/index.xml" rel="self" type="application/rss+xml"/><item><title>Crow's NestMQTT</title><link>https://www.alexander-koepke.de/post/2025-06-01_crows_nestmqtt/</link><pubDate>Sat, 31 May 2025 00:00:00 +0000</pubDate><guid>https://www.alexander-koepke.de/post/2025-06-01_crows_nestmqtt/</guid><description>&lt;h1 id="crows-nestmqtt-and-the-vibe-engineering-adventure"&gt;Crow&amp;rsquo;s NestMQTT and the Vibe Engineering Adventure&lt;/h1&gt;
&lt;p&gt;In the world of (Industrial) Internet of Things (IIoT), MQTT is a widely adopted messaging protocol. Whether you’re debugging a flaky device or trying to understand system-wide message flow, a good MQTT client is a lifesaver.&lt;/p&gt;
&lt;p&gt;There are many excellent MQTT clients available—like MqttExplorer, MQTTX, mqttui, and the classic &lt;code&gt;mosquitto_sub&lt;/code&gt;. However, none quite met &lt;strong&gt;my specific needs&lt;/strong&gt;. That kicked off a wild journey: building my own client, &lt;strong&gt;Crow&amp;rsquo;s NestMQTT&lt;/strong&gt;, while exploring how &lt;strong&gt;Generative AI can accelerate software development&lt;/strong&gt;.&lt;/p&gt;</description></item><item><title>Harnessing the Power of Small Language Models in Industrial IoT</title><link>https://www.alexander-koepke.de/post/2024-05-14_slm_for_industries/</link><pubDate>Tue, 14 May 2024 00:00:00 +0000</pubDate><guid>https://www.alexander-koepke.de/post/2024-05-14_slm_for_industries/</guid><description>&lt;h1 id="harnessing-the-power-of-small-language-models-in-industrial-iot"&gt;Harnessing the Power of Small Language Models in Industrial IoT&lt;/h1&gt;
&lt;p&gt;The industrial Internet of Things (IIoT) is revolutionizing how industries operate, bringing connectivity and
data-driven insights to every corner of the manufacturing process. As IIoT devices proliferate, the need for robust,
efficient, and intelligent data processing becomes increasingly critical. This is where small language models come into
play, particularly in the context of intelligent edge scenarios where offline capabilities are paramount.&lt;/p&gt;</description></item></channel></rss>