Skip to main content

Learn · Videos

Video shelf

Curated talks and tutorials on AI, machine learning and building software well. Filter by topic, or by audience tailored to your role.

Topic
Audience

AI Foundations

AI vs Machine Learning

IBM Technology · 5:49

A quick, clear map of how AI, machine learning and deep learning actually relate.

But what is a neural network?

3Blue1Brown · 18:40

The clearest visual introduction to what a neural network actually is.

Gradient descent — how neural networks learn

3Blue1Brown · 20:33

The intuition behind how neural networks learn from data.

Backpropagation, intuitively

3Blue1Brown · 12:47

What backpropagation is really doing when a network learns.

How AI Image Generators Work (Stable Diffusion / DALL·E)

Computerphile · 17:50

How diffusion models turn random noise into images.

The Strange Math That Predicts (Almost) Anything

Veritasium · 32:32

Markov chains — the deceptively simple math behind language models, PageRank and much of modern ML.

Maths & Foundations

Vectors — Essence of Linear Algebra

3Blue1Brown · 9:51

Vectors are the language of machine learning — a visual first step into linear algebra.

The Essence of Calculus

3Blue1Brown · 17:04

Derivatives and rates of change from the ground up — the foundation behind gradient descent.

The Normal Distribution, Clearly Explained

StatQuest · 5:12

The most important distribution in statistics, explained simply.

But what is the Central Limit Theorem?

3Blue1Brown · 31:14

Why the normal distribution shows up everywhere — the cornerstone of statistics, visualised.

Bayes' Theorem (with Example!)

Steve Brunton · 17:43

The intuition behind Bayes' theorem — the rule for updating beliefs with evidence that sits at the heart of probability and machine learning.

The Bayesian Trap

Veritasium · 10:36

How Bayesian thinking changes the way you reason about evidence — and where it can trip you up.

LLMs & Transformers

How Large Language Models Work

IBM Technology · 5:33

A short, accessible explainer on what LLMs are and how they generate text.

Word Embedding and Word2Vec

StatQuest · 16:11

How words become vectors — the foundation of how language models represent meaning.

Transformer Neural Networks, ChatGPT's foundation

StatQuest · 36:15

A clear, step-by-step walk through the transformer architecture behind ChatGPT.

Transformers, the tech behind LLMs

3Blue1Brown · 27:14

A visual walkthrough of the transformer architecture behind modern AI.

Attention in transformers, step-by-step

3Blue1Brown · 26:09

The attention mechanism — the key idea that makes transformers work — explained visually.

How might LLMs store facts

3Blue1Brown · 22:42

A visual look at where factual knowledge actually lives inside a transformer's weights.

Intro to Large Language Models

Andrej Karpathy · 59:48

A one-hour, non-hype primer on how LLMs work and where they're going.

Let's build GPT: from scratch, in code

Andrej Karpathy · 1:56:20

Build a transformer language model line by line, in code.

Building & Using AI

What is Retrieval-Augmented Generation (RAG)?

IBM Technology · 6:35

How RAG grounds LLMs in your own data — the backbone of most enterprise AI.

Andrew Ng on AI Agentic Workflows

Andrew Ng · 30:54

Why agentic workflows — where an LLM plans, uses tools and iterates rather than answering in one shot — are driving the next wave of AI progress.

How I use LLMs

Andrej Karpathy · 2:11:12

Practical, real-world patterns for getting the most out of LLM tools.

Let's build the GPT Tokenizer

Andrej Karpathy · 2:13:34

Build the tokenizer behind GPT from scratch — the crucial, often-overlooked first step in every LLM.

Deep Dive into LLMs like ChatGPT

Andrej Karpathy · 3:31:23

A thorough tour of how modern chat LLMs are actually built and trained.

Stanford CS229 · Building Large Language Models

Stanford Online · 1:44:31

A full Stanford lecture on how modern LLMs are built — pretraining, data and post-training.

Responsible & Safe AI

Intro to AI Safety, Remastered

Robert Miles AI Safety · 18:04

A clear, grounded introduction to why AI safety matters and what the field is actually trying to solve.

The AI "Stop Button" Problem

Computerphile · 20:00

A deceptively simple thought experiment about AI control — why 'just switch it off' is far harder than it sounds.

Deadly Truth of General AI?

Computerphile · 8:30

Why aligning a highly capable AI with human intentions is subtler and more important than it first appears.

Curiosities

The World's Most Important Machine

Veritasium · 55:00

The almost impossibly precise ASML EUV lithography machine behind every advanced chip — including the GPUs that train and run modern AI.

Lightboard Videos: How We Make Them

IBM Technology · 1:41

The clever trick behind those 'writing backwards' explainer videos — including a few on this very shelf.

Why Do Mirrors Flip Left & Right (but not up & down)?

minutephysics · 3:24

A classic brain-teaser — why a mirror seems to flip left–right but not up–down, and what's really going on.