Guides

How AI works, in depth

Long-form guides to the mechanism itself, worked through with real numbers where they help. For readers who want more than the short explainers.

The transformer architecture 17 min read →
By the end you will be able to follow a token from the input text through attention, the feed-forward block, and the residual stream to the probability of the next token.
How a neural network works 17 min read →
By the end you will have computed a small neural network by hand and know exactly what a large one is doing more of.
Backpropagation 19 min read →
By the end you will be able to follow one full training step, from the loss to the gradient of every weight to the update, and see why a single backward pass is enough.
Embeddings 17 min read →
By the end you will know how a token becomes a vector, what "close" means between two vectors, how the numbers are learned, and what similarity can and cannot tell you.
How post-training shapes a model 17 min read →
By the end you will know how a text predictor is turned into an assistant, and why the confidence, warmth, and agreement it shows were selected by raters rather than earned by being right.
Are LLMs stochastic parrots? 15 min read →
Where the phrase came from, what it gets right about next-token prediction, what researchers have since found inside the models, and what to do with the answer.