Learn how modern AI
actually works.
A structured path from linear algebra to production agents. Every concept is written to be read once and understood, then drilled with flashcards until it sticks, then extended with a deep dive that shows how it plays out in real systems.
Three ways in, one body of knowledge.
Concepts
446 self-contained explainers organised into 8 domains and 36 tracks. Each one is a short read that starts from what you already know and ends somewhere useful.
Open the tree → 02Flashcards
2,671 cards drawn straight from the concepts. Flip with a keypress, shuffle a deck, mark what you know. Progress is kept in your browser, so nothing to sign up for.
Start a deck → 03Deep dives
63 long-form pieces with the maths, the diagrams and the numbers intact. These are the articles to read once you know the vocabulary and want to know why the field settled where it did.
Read the writing →Eight domains, ordered from first principles up.
The order is deliberate. Domain 01 assumes nothing; domain 08 assumes the rest. You do not have to follow it, but if you are starting cold, start at the top.
Foundations
The mathematics and neural-network mechanics everything else assumes.
Transformer Internals
Open the box. How a language model actually turns text into predictions.
Training & Fine-Tuning
From raw web crawl to an aligned model — data, dynamics, scale and adaptation.
Reinforcement Learning
Classical RL, then the specific dialect of it that post-trains language models.
Inference, Systems & Hardware
Where the model meets the silicon, the memory bus and the latency budget.
Applied LLM Engineering
Building things people use: retrieval, prompts, agents and production architecture.
Reasoning, Evaluation & Safety
Models that think longer, the evals that measure them, and the failure modes that matter.
Multimodal & Applications
Beyond text — vision, speech, robotics and scientific discovery.
If you are new, these come first.
Beginner-level concepts that assume no prior machine learning.
Anatomy of a Transformer Block
The exact sequence of operations inside one transformer block, from tensor shapes to parameter counts, and why every frontier model is just this same function stacked dozens of times.
Attention InternalsAttention as Soft Dictionary Lookup
The mental model that makes attention click before the matrix algebra does - a lookup table where the key match is a matter of degree, not an exact hit or miss.
Speech RecognitionAudio Features and Spectrograms
Raw audio waveforms are rarely fed directly to speech models; this concept explains how and why they are first converted into spectrogram-based representations that compress perceptual information into a learnable 2-D grid.
Context & In-Context LearningAutoregressive Generation
How a language model turns next-token prediction into a paragraph, and why generation is a loop that feeds its own output back as input.
Tensors & Neural PlumbingBroadcasting and Vectorisation
Broadcasting is the rule that lets a bias vector add to every row of a batch without an explicit loop, and understanding its shape-matching logic prevents the class of bugs that produce wrong answers without an error.
Prompt EngineeringChain of Thought Prompting
Why telling the model to think step by step radically improves reasoning, and when it actively hurts.
Embeddings & RepresentationsCosine Similarity vs Dot Product
Two near-identical looking formulas that answer different questions, one measures direction alone, the other measures direction and magnitude together, and picking the wrong one silently breaks a search or ranking system.
Deep Learning Building BlocksDropout and Modern Regularisation
Why dropout was the dominant regulariser for a decade and why modern LLM training mostly skips it in favour of letting data do the work.
Longer reads, one per collection.
Claude Certified Architect - Foundations: The Complete Exam Preparation Guide
A comprehensive, interactive study guide covering every domain of the Claude Certified Architect - Foundations (CCAF) exam. Master agentic architecture, tool design, Claude Code configurati…
Reasoning & EvaluationError Bars for Evals: Why Most Benchmark Differences Are Noise
A 250-question benchmark carries a standard error of about three percentage points. Most of the model comparisons published on top of such benchmarks cannot distinguish the models they are …
Model ArchitectureContext Rot: Why Bigger Context Windows Don't Mean Better Retrieval
A million-token window promises perfect recall of everything you feed it. Controlled tests on 18 frontier models show recall degrading steadily, unevenly, and well before the window fills, …
Safety, Security & GovernanceThe Lethal Trifecta: Why Prompt Injection Is Structural in Tool-Using Agents
The protocols that let agents read your email, query your database, and post to Slack were the most-adopted infrastructure in AI over the past year. They also handed attackers a way in that…
Training & AlignmentBorrowed Intelligence: How Knowledge Distillation Builds Small Language Models That Punch Above Their Weight
A 2-billion-parameter model that trades blows with one ten times its size is not an accident of architecture. It is the product of a teacher pouring its full probability distribution into a…
Inference & ServingCache-Augmented Generation: When Preloaded KV-Caches Replace Retrieval Pipelines
Retrieval-augmented generation fetches documents at query time, scores them, and hopes the retriever got it right. Cache-Augmented Generation sidesteps the entire pipeline by preloading kno…