<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Shimin Zhang — The Journal</title><description>Programming, entrepreneurship, machine learning.</description><link>https://shimin.io/</link><item><title>What I learned asking 11 AI models to grade each other&apos;s AI predictions</title><link>https://shimin.io/journal/what-i-learned-asking-11-ai-models-to-grade-each-other/</link><guid isPermaLink="true">https://shimin.io/journal/what-i-learned-asking-11-ai-models-to-grade-each-other/</guid><description>An experiment on model personalities, a delusion index, and the open-weight dark horse contender I didn&apos;t see coming.</description><pubDate>Thu, 23 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Opus 4.7 isn&apos;t dumb, it&apos;s just lazy</title><link>https://shimin.io/journal/opus-4-7-just-lazy/</link><guid isPermaLink="true">https://shimin.io/journal/opus-4-7-just-lazy/</guid><description>Some follow up experiments with Claude Opus 4.7 based on Simon Willison&apos;s Pelican Benchmark Shocker.</description><pubDate>Mon, 20 Apr 2026 00:00:00 GMT</pubDate></item></channel></rss>