Module 01

How LLMs Work

00Welcome: You Are Going to Build AI Systems01What Actually Is AI?02What Is a Model?03How Does a Model Learn?04Training, Validation, Testing, Inference05Neural Networks Without the Scary Math06Tokens: LLMs Don't Read Text Like You Do07Context Windows08Embeddings: Meaning as Numbers09Why Transformers?10Attention11Query, Key, Value12Self-Attention13Inside a Transformer Block14Encoder, Decoder, and Decoder-Only Models15What Is an LLM?16The Flagship Next-Token Simulation17Logits, Probabilities, Softmax18Sampling19Why Can an LLM Follow Instructions?

Step 01 / 03

Which two mean something similar?

Module map

Humans spot related meaning instantly. Computers need a representation that makes “nearby meaning” measurable.

  • A. "I love puppies."
  • B. "Dogs are my favorite animals."
  • C. "The stock market crashed."

Which pair is most similar in meaning?