Wirewalk Instituteof AI
fnd-102 Basic Available

How Large Language Models Work, Without the Math

For non-engineers who use AI assistants daily and want an accurate mental model of what happens inside one, so they can predict its behavior instead of being surprised by it.

Level
Basic
Study time
8 hours
Lessons
16 in 6 modules
Exam
20 questions

About this course

Most explanations of large language models stop at "it predicts the next word". That is true but not enough to explain why a model can follow instructions, why it forgets the middle of a long document, why the same question gets different answers, or why newer "reasoning" models pause to think. This course opens the box one layer at a time, using worked examples you can try in any chat assistant and the free tokenizer tools vendors publish.

You will follow a piece of text from tokenizer to embedding vectors, through the attention layers of a transformer, and back out as a probability distribution over the next token. You will see how pretraining on internet-scale text differs from the instruction tuning and preference training that turn a raw model into an assistant, how reasoning models spend extra computation before answering, and how context windows, tools and retrieval extend what a model can do. The course closes by tying each mechanism to a behavior you have seen at work. It ends with an automated exam and a Wirewalk Institute certificate of completion and assessment. Product facts are stated as of the review date and the course is re-reviewed on each major Anthropic or OpenAI model release or every six months; errors can be reported through the contact link on this site.

What you will be able to do

  • Trace how a sentence is split into tokens and explain why token counts drive cost, limits and some odd mistakes such as miscounting letters
  • Describe embeddings and attention in plain language and use them to explain how a model relates words across a passage
  • Distinguish pretraining, supervised instruction tuning and preference training, and explain what each contributes to an assistant's behavior
  • Explain what reasoning models do differently at answer time and when the extra cost and latency are worth it
  • Explain how temperature and sampling produce varied answers, and when to expect consistency
  • Describe context windows, tool use and retrieval, and predict where a model will struggle with long or unfamiliar material
  • Map common surprising behaviors, such as hallucination, sycophancy and knowledge cutoffs, to the mechanism that causes them

Syllabus

6 modules · 16 lessons · about 8 hours

Module 1: From Text to Tokens to Vectors

How a model turns your words into numbers it can work with.
3 lessons
  1. Tokenizers in Action: Byte-Pair Encoding with Real Examples
  2. Why Models Miscount Letters and Struggle with Some Languages
  3. Embeddings: Meaning as Position in a Space

Module 2: Inside the Transformer

Attention and layers explained with analogies and toy examples, not formulas.
3 lessons
  1. Attention: How Every Word Looks at Every Other Word
  2. Stacking Layers: From Grammar to Facts to Tasks
  3. Parameters, Model Size and What "70 Billion" Actually Means

Module 3: How a Raw Model Becomes an Assistant

The training stages that turn a text predictor into something that follows instructions.
3 lessons
  1. Pretraining: Learning from a Large Slice of the Written World
  2. Instruction Tuning and RLHF: Teaching the Model to Help
  3. Reasoning Models: Spending More Computation Before Answering

Module 4: Generating an Answer

What happens between pressing Enter and seeing the reply.
3 lessons
  1. Probabilities, Temperature and Why Answers Vary
  2. Context Windows: What the Model Can See at Once
  3. System Prompts, Conversation History and Memory Features

Module 5: Extending the Model: Tools and Retrieval

How assistants search, run code and read your files without retraining.
2 lessons
  1. Tool Calling: How a Model Asks for a Search or a Calculator
  2. Retrieval-Augmented Generation in Plain Language

Module 6: Explaining Behavior from Mechanism

Connect what you now know to the surprises you meet at work.
2 lessons
  1. Hallucination, Sycophancy and Knowledge Cutoffs, Explained Mechanically
  2. Reading Vendor Claims: Context Length, Benchmarks and Model Cards

Exam and certificate

The exam unlocks once you have completed every lesson. It draws 20 questions from a larger bank, spread across the modules, with the answer options shuffled for each attempt. You have 40 minutes and need 80% to pass. After a failed attempt you can try again after 24 hours, up to 3 attempts in total. Feedback is given per module, never as the answer key.

Passing earns a certificate of completion and assessment from the Wirewalk Institute of AI with a unique ID that anyone can check at institute.wirewalk.com/verify. It is not an accredited qualification or a vendor certification. How certification works.

The Wirewalk Institute of AI is independent. This course teaches publicly documented products and is not affiliated with or endorsed by OpenAI, Anthropic, Google, Meta, Mistral AI, or DeepSeek. Product and company names are trademarks of their respective owners.

More in AI Foundations

All 9 courses in this track
fnd-001 Free intro Available

What Is AI? A One-Hour Introduction

A free, plain-English introduction taught through one realistic company getting ready for its busiest season. Sort the kinds of AI, see why a chat assistant can sound right and be wrong, decide which tasks it fits and how to measure them, catch its three predictable failures, ask well, and decide what never goes into an AI tool.

1 h · 7 lessons Free intro
fnd-101 Basic Available

AI Foundations for Everyone

A plain-language grounding in artificial intelligence: what AI, machine learning and generative AI actually are, how chat assistants produce text, why they sometimes get things confidently wrong, and how to use them safely for real work.

6 h · 16 lessons See price at checkout
fnd-103 Basic Available

Generative AI for Images, Audio and Video

Work through a fictional Ohio learning venue’s campaign using supplied briefs, review logs, scripts and timeline records. Compare manual production and generative approaches, repair concrete defects, and prepare a rights-aware accessible release recommendation.

12 h · 18 lessons See price at checkout