<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
  <channel>
    <title>links.lmorchard.com - #codex</title>
    <link>/tags/codex/</link>
    <description>Recent bookmarks tagged #codex</description>
    <lastBuildDate>Mon, 02 Nov 2026 08:24:55 +0000</lastBuildDate>
    <item>
      <title>Just Talk To It - the no-bs Way of Agentic Engineering | Peter Steinberger</title>
      <link>https://steipete.me/posts/just-talk-to-it</link>
      <description>My current approach is usually that I start a discussion with codex, I paste in some websites, some ideas, ask it to read code, and we flesh out a new feature together. If it’s something tricky, I ask it to write everything into a spec, give that to GPT-5-Pro for review (via chatgpt.com) to see if it has better ideas (surprisingly often, this greatly improves my plan!) and then paste back what I think is useful into the main context to update the file.&lt;br/&gt;&#xA;&lt;p&gt;&lt;strong&gt;Tags:&lt;/strong&gt; #ai #claude #codegen #codex #llms&lt;/p&gt;</description>
      <pubDate>Sun, 09 Nov 2025 18:52:53 +0000</pubDate>
      <guid isPermaLink="false">linkding-ssg:bookmark:37929</guid>
      <category>ai</category>
      <category>claude</category>
      <category>codegen</category>
      <category>codex</category>
      <category>llms</category>
    </item>
  </channel>
</rss>
