Generative AI & LLM Fundamentals

A free beginner course on generative AI: machine learning basics, how LLMs work, tokens, context windows, hallucinations and prompt engineering.

Beginner · 11 lessons

AI and machine learning basics

1. What Is Artificial Intelligence? - A plain explanation of AI, how it differs from machine learning and deep learning, and what it can and cannot do today.
2. Maths and Statistics You Need for AI - The small set of maths ideas behind AI: vectors, probability, averages, gradients and similarity, explained without heavy formulas.
3. Machine Learning Basics - Supervised, unsupervised and self-supervised learning, training and test sets, overfitting and the metrics used to judge a model.
4. Deep Learning, Embeddings and Transformers - How neural networks, embeddings and the transformer architecture lead to modern language models.

Generative AI and LLMs

1. Introduction to Generative AI - What generative AI is, how it differs from predictive AI, the main kinds of models and what they are good and bad at.
2. How Large Language Models Work - Tokens, next-token prediction, context windows, temperature and why models hallucinate, explained step by step.
3. Model Size, Quantization and Inference Speed - Parameters, quantization, distillation, mixture of experts and why inference is slow or expensive.

Prompt engineering

1. Prompt Engineering Basics - Zero-shot, one-shot and few-shot prompting, roles, constraints and reusable templates with practical examples.
2. Advanced Prompting Techniques - Step-by-step reasoning, task decomposition, prompt chaining, self-critique and managing long context.
3. Structured Outputs: Getting Reliable JSON - How to make a model return JSON that your code can use: schemas, validation, retries and repair prompts.
4. Prompt Testing, Versioning and Prompt Injection - How to test prompts with golden datasets, version them, and defend against prompt injection and jailbreaks.