<?xml version="1.0" encoding="UTF-8" ?> <?xml-stylesheet type="text/xsl" href="rss.xsl"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:dc="http://purl.org/dc/elements/1.1/"> <channel> <title>wtf</title><description>Notes and experiments by Korridzy.</description><link>https://wtf.korridzy.com/</link><atom:link href="https://wtf.korridzy.com/feed_rss_created.xml" rel="self" type="application/rss+xml" /> <managingEditor>Korridzy</managingEditor><language>en</language> <pubDate>Tue, 30 Jun 2026 17:40:51 -0000</pubDate> <lastBuildDate>Tue, 30 Jun 2026 17:40:51 -0000</lastBuildDate> <ttl>1440</ttl> <generator>MkDocs RSS plugin - v1.19.0</generator> <image> <url>None</url> <title>wtf</title> <link>https://wtf.korridzy.com/</link> </image> <item> <title>Twilight of the Gods</title> <author>Korridzy</author> <category>AI agents</category> <category>LLM</category> <category>LangGraph</category> <category>Python</category> <category>Refactoring</category> <description>&lt;h1&gt;Twilight of the Gods. Comparing how 11 LLMs approach a code-reorganization task.&lt;/h1&gt; &lt;p&gt;!!! info &#34;Other languages&#34; Эта статья также доступна на русском: &lt;a href=&#34;/ru/gibel-bogov/&#34;&gt;Гибель богов&lt;/a&gt;.&lt;/p&gt; &lt;p&gt;This is a detailed write-up of one experiment. I took a god node from a real LangGraph agent and asked 5 American and 6 Chinese models first to propose how to untangle it, then to evaluate each other&#39;s proposals. After that, I tried three different ways to figure out which of them to trust on the matter.&lt;/p&gt;</description> <link>https://wtf.korridzy.com/twilight-of-the-gods/</link> <pubDate>Tue, 30 Jun 2026 00:00:00 +0000</pubDate> <source url="https://wtf.korridzy.com/feed_rss_created.xml">wtf</source><guid isPermaLink="true">https://wtf.korridzy.com/twilight-of-the-gods/</guid> </item> </channel> </rss>