<?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>Strategy Genes on Chuanxilu for Skilled Homo sapiens</title><link>https://blog.chuanxilu.net/en/tags/strategy-genes/</link><description>Recent content in Strategy Genes on Chuanxilu for Skilled Homo sapiens</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Sun, 24 May 2026 08:00:00 +0800</lastBuildDate><atom:link href="https://blog.chuanxilu.net/en/tags/strategy-genes/index.xml" rel="self" type="application/rss+xml"/><item><title>Strategy Genes: Pruning Review Prompts with Genetic Algorithm Thinking</title><link>https://blog.chuanxilu.net/en/posts/2026/05/signal-purity-less-is-more/</link><pubDate>Sun, 24 May 2026 08:00:00 +0800</pubDate><guid>https://blog.chuanxilu.net/en/posts/2026/05/signal-purity-less-is-more/</guid><description>A review prompt went from 317 lines to 135 lines, and review quality improved by 29%. What I removed was not useful procedure, but redundant content the model could infer on its own. What stayed were strategy genes: irreplaceable constraints, negative examples, and tone locks.</description></item></channel></rss>