Learn
Understand the tools you use
No jargon for its own sake. No sales copy dressed up as explanation. Just honest accounts of how these things actually work.
Learning tracks — start from zero
Five ordered paths from "what is AI" to working with agents. No code required to start. Pick the one that matches where you are.
AI from zero
No code, no math fear. What AI actually is, what data is, and how prediction works — for anyone starting cold.
8 stops · ◈ 8 interactive
Foundations of ML
How machines learn from examples: features, loss, gradient descent, and the eternal fight against overfitting.
8 stops · ◈ 8 interactive
Deep Learning
From a single neuron to the transformer: the architecture story that leads directly to modern AI.
8 stops · ◈ 8 interactive
LLMs & Generative AI
How the models you actually use get trained, tuned, shrunk, and pushed to reason.
18 stops · ◈ 18 interactive
Working with AI
The practical layer: prompting, retrieval, agents, evals — and the failure modes that bite in production.
17 stops · ◈ 17 interactive
All concepts — 59 articles · 7 groups
Grouped by where each idea lives in the stack — read in any order, but each group reads as a story if you take it top-to-bottom.
Foundations
8 conceptsZero assumed. What AI actually is, what data is, and why statistics runs the show.
Bias in Data
Correlation vs Causation
Data & Datasets
Patterns & Predictions
Probability & Uncertainty
Statistics Essentials
What is a Model?
What is AI, actually?
Machine Learning
11 conceptsHow machines learn from examples. The ideas every model — old or frontier — is built on.
Backpropagation
Clustering
Evaluation Metrics
Features & Labels
GPUs & Compute
Gradient Descent
Loss Functions
Neural Networks
Overfitting & Underfitting
Regression & Classification
Training vs Testing
Architecture
8 conceptsHow the models are built. The shapes underneath everything.
Attention
Diffusion Models
Embeddings
Mixture of Experts
Multimodal Models
Tokenization
Transformers
Vision-Language Models
Training
9 conceptsHow they learn. What gets baked in and what gets sanded down.
Distillation
DPO
Fine-Tuning
How AI Models Are Trained
Model Collapse
Quantization
RLHF
Scaling Laws
Synthetic Data
Inference
8 conceptsHow they answer. The mechanics of producing output one token at a time.
Chain-of-Thought
Context Windows
Function Calling
In-Context Learning
KV Cache
Reasoning Models
Structured Output
Temperature & Sampling
Practical
9 conceptsHow to actually use them. The patterns that survive contact with real work.
Agentic Memory
AI Agents
Evals
Model Cards
Model Context Protocol
Multiagent Systems
Prompt Engineering
Retrieval & Reranking
Retrieval-Augmented Generation
Safety
6 conceptsWhere they fail, lie, or get tricked. The shape of the things to watch for.