<?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>Donald-Knuth on danilchenko.dev</title><link>https://www.danilchenko.dev/tags/donald-knuth/</link><description>Recent content in Donald-Knuth on danilchenko.dev</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 25 Mar 2026 06:00:00 +0000</lastBuildDate><atom:link href="https://www.danilchenko.dev/tags/donald-knuth/index.xml" rel="self" type="application/rss+xml"/><item><title>Donald Knuth's 'Claude's Cycles': When AI Solved a Problem the Father of CS Couldn't</title><link>https://www.danilchenko.dev/posts/2026-03-25-donald-knuth-claudes-cycles-ai-solves-open-math-problem/</link><pubDate>Wed, 25 Mar 2026 06:00:00 +0000</pubDate><guid>https://www.danilchenko.dev/posts/2026-03-25-donald-knuth-claudes-cycles-ai-solves-open-math-problem/</guid><description>Donald Knuth published Claude&amp;#39;s Cycles after Claude Opus 4.6 solved his open graph theory problem in 31 tries. The full breakdown of what happened.</description></item></channel></rss>