<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Anthropic on dhangaard</title><link>https://dhangaard.dk/tags/anthropic/</link><description>Recent content in Anthropic on dhangaard</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2026 dhangaard</copyright><lastBuildDate>Sun, 13 Sep 2026 00:00:00 +0200</lastBuildDate><atom:link href="https://dhangaard.dk/tags/anthropic/index.xml" rel="self" type="application/rss+xml"/><item><title>Mind Your Tokens</title><link>https://dhangaard.dk/posts/ai-4-prompting/</link><pubDate>Sun, 13 Sep 2026 00:00:00 +0200</pubDate><guid>https://dhangaard.dk/posts/ai-4-prompting/</guid><description>What I took from two days on LLM APIs: how Mistral and Anthropic want to be prompted, why every message costs you the whole conversation, and where skills fit in.</description></item></channel></rss>