<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
  <channel>
    <title>links.lmorchard.com - #gpt-5</title>
    <link>/tags/gpt-5/</link>
    <description>Recent bookmarks tagged #gpt-5</description>
    <lastBuildDate>Mon, 02 Nov 2026 08:24:56 +0000</lastBuildDate>
    <item>
      <title>The End of Shouting: Prompts as Programs in GPT-5</title>
      <link>https://www.robert-glaser.de/prompts-as-programs-in-gpt-5/</link>
      <description>GPT-5 with reasoning (GPT-5 Thinking) follows instructions with a precision we haven’t seen before (GPT-4.1 was the exception, but lacked reasoning). What sounds like a feature flips established prompt-engineering practices on its head. The era of “shouting”—ALL CAPS, exclamation marks, redundant pleading—is over. Clear rules, explicit policies, and structured instructions now rule the day.&lt;br/&gt;&#xA;&lt;p&gt;&lt;strong&gt;Tags:&lt;/strong&gt; #ai #chatgpt #genai #gpt-5 #llms #openai&lt;/p&gt;</description>
      <pubDate>Mon, 03 Nov 2025 20:29:56 +0000</pubDate>
      <guid isPermaLink="false">linkding-ssg:bookmark:37903</guid>
      <category>ai</category>
      <category>chatgpt</category>
      <category>genai</category>
      <category>gpt-5</category>
      <category>llms</category>
      <category>openai</category>
    </item>
  </channel>
</rss>
