<?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>Tools on Soup to Cloud</title>
    <link>https://souptocloud.cloudhastaenlasopa.com/categories/tools/</link>
    <description>Recent content in Tools on Soup to Cloud</description>
    <image>
      <title>Soup to Cloud</title>
      <url>https://souptocloud.cloudhastaenlasopa.com/images/Portada.jpg</url>
      <link>https://souptocloud.cloudhastaenlasopa.com/images/Portada.jpg</link>
    </image>
    <generator>Hugo -- 0.165.0</generator>
    <language>en-US</language>
    <lastBuildDate>Thu, 03 Sep 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://souptocloud.cloudhastaenlasopa.com/categories/tools/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>I have the feeling that Kiro is more efficient. Is it just me, or is it real?</title>
      <link>https://souptocloud.cloudhastaenlasopa.com/2026/09/i-have-the-feeling-that-kiro-is-more-efficient.-is-it-just-me-or-is-it-real/</link>
      <pubDate>Thu, 03 Sep 2026 00:00:00 +0000</pubDate>
      <guid>https://souptocloud.cloudhastaenlasopa.com/2026/09/i-have-the-feeling-that-kiro-is-more-efficient.-is-it-just-me-or-is-it-real/</guid>
      <description>I had the feeling that Kiro lasted longer than Codex or Claude Code, but without numbers not even I believed it. So I built a benchmark with the same models, the same exercises and the same prompt across all three tools. The results surprised me, and not in the direction I expected.</description>
    </item>
  </channel>
</rss>
