<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Transformers on MikesBlog</title>
    <link>https://oshea00.github.io/tags/transformers/</link>
    <description>Recent content in Transformers on MikesBlog</description>
    <generator>Hugo -- 0.165.0</generator>
    <language>en-us</language>
    <lastBuildDate>Wed, 16 Sep 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://oshea00.github.io/tags/transformers/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Limits on Recursive Self Improvement</title>
      <link>https://oshea00.github.io/posts/recursive-self-improvement/</link>
      <pubDate>Wed, 16 Sep 2026 00:00:00 +0000</pubDate>
      <guid>https://oshea00.github.io/posts/recursive-self-improvement/</guid>
      <description>&lt;p&gt;&lt;figure class=&#34;align-center &#34;&gt;
    &lt;img loading=&#34;lazy&#34; src=&#34;images/cute_infinite_regress.png#center&#34;/&gt; 
&lt;/figure&gt;

A few months ago, I wrote, “The recent explosion of social media frenzy over agentic orchestration tools such as OpenClaw and GasTown, vibe-coded and quickly released into the wild, is yet another symptom of overhyped expectations related to generative AI models. If it takes three weeks to go viral after a few months of vibe coding, it’s a trivial solution, and it will be copied relentlessly.” See  Agentic Orchestration is not a Moat.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
