<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">
  <channel>
    <title>InfoQ - AI Certification</title>
    <link>https://www.infoq.com</link>
    <description>InfoQ AI Certification feed</description>
    <item>
      <title>Production AI, Architecture Trade-Offs &amp; Team Design: InfoQ Opens Registration for 6 January Cohorts</title>
      <link>https://www.infoq.com/news/2026/11/onlinecohort-jan27-certification/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=AI+Certification</link>
      <description>&lt;img src="https://res.infoq.com/news/2026/11/onlinecohort-jan27-certification/en/headerimage/onlinecohorts-jan27-certifications-1794839939505.jpg"/&gt;&lt;p&gt;From agent reliability to architecture decisions and delivery bottlenecks, InfoQ’s January 2027 cohorts give senior practitioners five weeks to examine current challenges, test approaches in their own work, and compare results with peers.&lt;/p&gt; &lt;i&gt;By Artenisa Chatziou&lt;/i&gt;</description>
      <category>AI Architecture</category>
      <category>AI Certification</category>
      <category>InfoQ Certification Program</category>
      <category>AI Engineering Certification</category>
      <category>High Performing Teams Certification</category>
      <category>AI, ML &amp; Data Engineering</category>
      <category>news</category>
      <pubDate>Tue, 17 Nov 2026 11:00:00 GMT</pubDate>
      <guid>https://www.infoq.com/news/2026/11/onlinecohort-jan27-certification/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=AI+Certification</guid>
      <dc:creator>Artenisa Chatziou</dc:creator>
      <dc:date>2026-11-17T11:00:00Z</dc:date>
      <dc:identifier>/news/2026/11/onlinecohort-jan27-certification/en</dc:identifier>
    </item>
    <item>
      <title>Article: LLM Reliability Layers under Test: Accuracy, Yield, and the Limits of Verification</title>
      <link>https://www.infoq.com/articles/llm-reliability-layers-limits-accuracy/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=AI+Certification</link>
      <description>&lt;img src="https://res.infoq.com/articles/llm-reliability-layers-limits-accuracy/en/headerimage/llm-reliability-layers-limits-accuracy-header-1793873839325.jpg"/&gt;&lt;p&gt;Verification layers sort outputs by trust rather than fixing errors. In a benchmark of six reliability layers, voting and self-correction failed to recover accuracy - they only withheld doubtful records. Production systems gain more reliability by replacing generation with deterministic lookups, tracking yield over raw accuracy, and resolving extraction bottlenecks before stacking checks.&lt;/p&gt; &lt;i&gt;By Pushpdeep Mishra, Wejdan Bagais&lt;/i&gt;</description>
      <category>Machine Learning</category>
      <category>Large language models</category>
      <category>AI Architecture</category>
      <category>Verification</category>
      <category>InfoQ Certification Program</category>
      <category>AI Engineering Certification</category>
      <category>Reliability</category>
      <category>Software Engineering</category>
      <category>AI, ML &amp; Data Engineering</category>
      <category>article</category>
      <pubDate>Tue, 10 Nov 2026 09:00:00 GMT</pubDate>
      <guid>https://www.infoq.com/articles/llm-reliability-layers-limits-accuracy/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=AI+Certification</guid>
      <dc:creator>Pushpdeep Mishra, Wejdan Bagais</dc:creator>
      <dc:date>2026-11-10T09:00:00Z</dc:date>
      <dc:identifier>/articles/llm-reliability-layers-limits-accuracy/en</dc:identifier>
    </item>
  </channel>
</rss>
