<?xml version="1.0" encoding="utf-8"?>
<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/">
    <channel>
        <title>Clint Johnson — LLM-as-judge</title>
        <link>https://www.clint-johnson.com/articles/tag/llm-as-judge</link>
        <description>Articles tagged LLM-as-judge by Clint Johnson.</description>
        <lastBuildDate>Tue, 23 Jun 2026 00:31:00 GMT</lastBuildDate>
        <docs>https://validator.w3.org/feed/docs/rss2.html</docs>
        <generator>https://github.com/jpmonette/feed</generator>
        <image>
            <title>Clint Johnson — LLM-as-judge</title>
            <url>https://www.clint-johnson.com/og-image.png</url>
            <link>https://www.clint-johnson.com/articles/tag/llm-as-judge</link>
        </image>
        <copyright>All rights reserved 2026</copyright>
        <item>
            <title><![CDATA[Why Your LLM Evaluator Is Lying to You]]></title>
            <link>https://www.clint-johnson.com/articles/llm-judge-wont-save-you</link>
            <guid isPermaLink="false">https://www.clint-johnson.com/articles/llm-judge-wont-save-you</guid>
            <pubDate>Sat, 29 Jun 2024 00:00:00 GMT</pubDate>
            <description><![CDATA[LLM-as-judge evaluators feel like quality assurance but behave like rubber stamps. They fail hardest on the outputs that matter most: edge cases, safety-critical errors, domain-specific nuance. What to do instead.]]></description>
            <content:encoded><![CDATA[LLM-as-judge evaluators feel like quality assurance but behave like rubber stamps. They fail hardest on the outputs that matter most: edge cases, safety-critical errors, domain-specific nuance. What to do instead.]]></content:encoded>
            <author>clint@1putthealth.com (Clint Johnson)</author>
            <enclosure url="https://images.clint-johnson.com/articles/llm-judge-wont-save-you/hero.png" length="0" type="image/png"/>
        </item>
    </channel>
</rss>