<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="/feed.xsl"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Cagri Temel</title>
    <link>https://cagritemel.com/blog.html</link>
    <atom:link href="https://cagritemel.com/feed.xml" rel="self" type="application/rss+xml"/>
    <description>Notes on explainable AI, AI safety, Chain-of-Thought reasoning, and building trustworthy AI products.</description>
    <language>en</language>
    <lastBuildDate>Thu, 27 Aug 2026 18:00:00 GMT</lastBuildDate>
    <item>
      <title>A Robot Ran 100 Metres in 8.64 Seconds in Beijing: So What Does That Number Mean?</title>
      <link>https://cagritemel.com/blog/robot-ran-faster-then-hit-the-barrier.html</link>
      <guid isPermaLink="true">https://cagritemel.com/blog/robot-ran-faster-then-hit-the-barrier.html</guid>
      <pubDate>Thu, 27 Aug 2026 18:00:00 GMT</pubDate>
      <description>The Games by the numbers, the specifications of the record-setting Tiangong Ultra, and the robots that hit the padded barrier after the finish line. Why stopping is harder than running, and why the binding limit changes from geometry to friction the moment the robot leaves the track.</description>
    </item>
    <item>
      <title>Can My Robot Tell What Ground It Is On? I Measured It, and the Answer Came Eight Seconds Late</title>
      <link>https://cagritemel.com/blog/signal-eight-seconds-late.html</link>
      <guid isPermaLink="true">https://cagritemel.com/blog/signal-eight-seconds-late.html</guid>
      <pubDate>Thu, 27 Aug 2026 12:00:00 GMT</pubDate>
      <description>Three tests on the precondition for a terrain classifier: what it does on unseen ground, whether the information is in the data at all, and when the answer arrives. It arrived 8.3 seconds into a crossing that takes about ten.</description>
    </item>
    <item>
      <title>I Reviewed for Five Conferences This Year. The Same Paper Keeps Arriving.</title>
      <link>https://cagritemel.com/blog/the-same-paper-keeps-arriving.html</link>
      <guid isPermaLink="true">https://cagritemel.com/blog/the-same-paper-keeps-arriving.html</guid>
      <pubDate>Tue, 25 Aug 2026 12:00:00 GMT</pubDate>
      <description>Most submissions I score low are not wrong, they are unfalsifiable by the reader. Why correct ablations are blind to a fault in the substrate every arm shares, and the five questions I ask instead.</description>
    </item>
    <item>
      <title>My Robot Was Tipping 13 Degrees. That Was the Whole Result.</title>
      <link>https://cagritemel.com/blog/rig-fault-tipping-robot.html</link>
      <guid isPermaLink="true">https://cagritemel.com/blog/rig-fault-tipping-robot.html</guid>
      <pubDate>Fri, 21 Aug 2026 12:00:00 GMT</pubDate>
      <description>A wheel-slip study invalidated by its own apparatus. Why four months of correct ablations could not catch it, and how slip was re-established on a controlled ramp.</description>
    </item>
    <item>
      <title>My Slip Detector Was Accurate. It Was Also Useless.</title>
      <link>https://cagritemel.com/blog/slip-detector-observability.html</link>
      <guid isPermaLink="true">https://cagritemel.com/blog/slip-detector-observability.html</guid>
      <pubDate>Wed, 19 Aug 2026 12:00:00 GMT</pubDate>
      <description>A slip detector scored 0.869 accuracy and cut position error by 72 percent. The control arm, driving slower with no detector at all, did better.</description>
    </item>
    <item>
      <title>Welcome: what I write about</title>
      <link>https://cagritemel.com/blog/welcome.html</link>
      <guid isPermaLink="true">https://cagritemel.com/blog/welcome.html</guid>
      <pubDate>Thu, 18 Jun 2026 12:00:00 GMT</pubDate>
      <description>Why I started this blog and the topics I will cover: trustworthy AI, explainable reasoning, and lessons from building real AI products.</description>
    </item>
  </channel>
</rss>
