<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Agentic Coding on BonesMoses.org</title>
    <link>https://bonesmoses.org/tags/agentic-coding/</link>
    <description>Recent content in Agentic Coding on BonesMoses.org</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-us</language>
    <lastBuildDate>Sat, 01 Aug 2026 11:20:58 -0500</lastBuildDate><atom:link href="https://bonesmoses.org/tags/agentic-coding/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Long Live AI Slop</title>
      <link>https://bonesmoses.org/2026/long-live-ai-slop/</link>
      <pubDate>Sat, 01 Aug 2026 11:20:58 -0500</pubDate>
      
      <guid>https://bonesmoses.org/2026/long-live-ai-slop/</guid>
      <description>I&amp;rsquo;ve been &amp;ldquo;busy&amp;rdquo; fiddling around with agentic coding using the Pi agent. This time around, it&amp;rsquo;s to see what the real limits of a local agent and model truly are. Why? I ran out of Claude tokens on an unrelated project, and that made me wonder just how far I could get without using it in a pinch.
As it turns out&amp;hellip; local models are pretty limited, but functional with enough planning.</description>
    </item>
    
  </channel>
</rss>
