<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Llm on InternetException</title><link>https://internetexception.com/tags/llm/</link><description>Recent content in Llm on InternetException</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sun, 15 Nov 2026 12:00:00 +0100</lastBuildDate><atom:link href="https://internetexception.com/tags/llm/index.xml" rel="self" type="application/rss+xml"/><item><title>Nonsensical LLMs writing</title><link>https://internetexception.com/2026-11-15/nonsensical-llm-writing/</link><pubDate>Sun, 15 Nov 2026 09:00:00 +0100</pubDate><guid>https://internetexception.com/2026-11-15/nonsensical-llm-writing/</guid><description>&lt;p&gt;I am experimenting lately with code written by models in some of my pet projects. It is a bit easier to do side projects this way: I can for example instruct it to make some specific change and then do something else entirely - some chores or just get a nap.&lt;/p&gt;&#10;&lt;p&gt;It mostly works, but the most problematic part is comments and documentation written by the model. I am using Qwen 3.8 Flash Next lately and it is a great model for more complex tasks, and it can be run fairly fast on Strix Halo with halogen server. But its writing is so Claude-like.&lt;/p&gt;</description></item></channel></rss>