<?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>LLM Inference on Evgeny Karpov</title><link>https://karpov.dk/tags/llm-inference/</link><description>Recent content in LLM Inference on Evgeny Karpov</description><image><title>Evgeny Karpov</title><url>https://karpov.dk/images/profile.png</url><link>https://karpov.dk/images/profile.png</link></image><generator>Hugo</generator><language>da-DK</language><lastBuildDate>Fri, 03 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://karpov.dk/tags/llm-inference/index.xml" rel="self" type="application/rss+xml"/><item><title>AI-tokens er billige. Regningen er det ikke.</title><link>https://karpov.dk/posts/ai-tokens-er-billige-regningen-er-det-ikke/</link><pubDate>Fri, 03 Jul 2026 00:00:00 +0000</pubDate><guid>https://karpov.dk/posts/ai-tokens-er-billige-regningen-er-det-ikke/</guid><description>En praktisk forklaring på tokenpriser, caching og hvorfor coding agents typisk bruger flere tokens end andre AI-agenter.</description></item></channel></rss>