29 lessons · 4 topics · each one builds on the last

KIeinfach verstehen

KI einfach verstehen shows you how artificial intelligence actually works — clearly explained, never just skimming the surface. What happens between your question to a chatbot and its answer? Here you follow the path from the first token to the last word and try out for yourself how it works along the way.

New here? How this site worksWhy it exists

Continue to the topics

The path through all 29 lessons

Four topics, one continuous path

Every lesson is a complete, self-contained chapter — not a quick post. The topics build on each other, and the map always shows you where on the path you currently stand.

Overview map of your reading path: 29 lessons across four topics. 29 lessons are readable now; the rest are in preparation. Your reading progress is stored in this browser only.

  • readable now
  • in preparation
  • read by you
Topic 19 lessons

Foundations

The concepts everything else builds on: what separates a program from a model, and what's behind probabilities, vectors, hardware and neural networks.

  1. Program, Algorithm, Model Compared
  2. Input and Output: How a Function "Thinks"
  3. Tokenizers: How Text Breaks into Tokens
  4. Token IDs: What a Number Means
  5. Scalar, Vector, Matrix, Tensor: The Building Blocks of the Numbers
  6. Probability and Softmax: How a Model Decides
  7. Parameters, Training and Use: How a Model Learns
  8. Model Size and Hardware: Where a Model Fits
  9. The Artificial Neuron: How a Sum Becomes an Output
Explore this topic
Topic 49 lessons

From Model to Assistant

What turns a language model into a chat assistant — why it can be convincingly wrong, what it really knows in a conversation, and how you check its answers.

  1. Why Prediction Is More Than Parroting
  2. From Text Predictor to Assistant
  3. How a Model "Thinks"
  4. Why AI Is Convincingly Wrong
  5. What a Chatbot Knows in a Conversation
  6. From Chatbot to Agent: How AI Works through a Task
  7. Does AI Understand What It Says?
  8. Training Data: Copyright and Privacy
  9. Checking Answers: Using AI Safely in Everyday Life
Explore this topic

Start here

Readable nowLesson 1 · Foundations

Program, Algorithm, Model Compared

Is a language model just a very complicated program? The first lesson clears up exactly that misconception — and hands you the three terms every later lesson builds on.

  • ≈ 16 minutes of reading
  • With links into the glossary
  • Also available in German
Read lesson 1