<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Taskfile on Janik von Rotz</title>
    <link>https://janikvonrotz.ch/tags/taskfile/</link>
    <description>Recent content in Taskfile on Janik von Rotz</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Mon, 27 Jan 2025 16:28:35 +0100</lastBuildDate>
    <atom:link href="https://janikvonrotz.ch/tags/taskfile/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Work with LLMs on the command line</title>
      <link>https://janikvonrotz.ch/2025/01/27/work-with-llms-on-the-command-line/</link>
      <pubDate>Mon, 27 Jan 2025 16:28:35 +0100</pubDate>
      <guid>https://janikvonrotz.ch/2025/01/27/work-with-llms-on-the-command-line/</guid>
      <description>&lt;p&gt;I used VSCodium and Codeium to develop Python code. VSCode is my editor of choice and Codeium is a well integrated AI-tool that helps writing code. While it solved a lot of problems for me, especially writing boilerplate code, I became more and more frustrated using this setup.&lt;/p&gt;&#xA;&lt;p&gt;No longer I wanted to understand the actual problem or piece of code, but just to prompt out a solution. Often I was eagerly waiting for the auto-complete feature to fix my code. I copied pieces of code to LLM chats in the browser and then updated the code in the editor. This workflow didn&amp;rsquo;t feel right. This isn&amp;rsquo;t coding.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
