Podcast
What do large language models actually do?


In this episode of the KI Kantine, Buschi explains how large language models like GPT work under the hood. It covers the Transformer architecture, tokenization, embeddings, and high-dimensional vector spaces. What sounds like pure calculation often seems surprisingly human – find out why in this episode.
The AI Canteen is a project by Michael Busch - developer, entrepreneur, and curious canteen philosopher.
Join us regularly during lunch break for discussions about Artificial Intelligence in real developer life - understandable, practical, and with a pinch of skepticism.
New episodes are released regularly - usually just when you're grabbing a tray.
📬 Questions, feedback, or your own AI experiences?
Write to me at podcast@ki-kantine.de
All episodes & more:
https://ki-kantine.letscast.fm/