<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Artificial Intelligence on Constantin's Blog</title><link>https://constantinsblog.eu/tags/artificial-intelligence/</link><description>Recent content in Artificial Intelligence on Constantin's Blog</description><generator>Hugo</generator><language>en</language><lastBuildDate>Tue, 15 Sep 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://constantinsblog.eu/tags/artificial-intelligence/index.xml" rel="self" type="application/rss+xml"/><item><title>Graphify vs. grep: Does a knowledge graph help an AI coding agent?</title><link>https://constantinsblog.eu/posts/graphify-llm-query-tool/</link><pubDate>Tue, 15 Sep 2026 00:00:00 +0000</pubDate><guid>https://constantinsblog.eu/posts/graphify-llm-query-tool/</guid><description>A measured comparison of Graphify and ordinary source search across twelve FastAPI repository questions, including time, tokens, cost, and whether the knowledge graph showed enough value to justify its overhead.</description></item><item><title>Before ChatGPT: What My Master's Thesis Taught Me About Meaning in Text</title><link>https://constantinsblog.eu/posts/gaussian-lda-master-thesis/</link><pubDate>Mon, 05 Jan 2026 00:00:00 +0000</pubDate><guid>https://constantinsblog.eu/posts/gaussian-lda-master-thesis/</guid><description>A look back at my 2021 master&amp;rsquo;s thesis on Gaussian LDA, word embeddings, and the surprisingly difficult question of whether a topic model has understood anything.</description></item></channel></rss>