Every track on lAItest
Ten tracks in dependency order: nothing uses a term before the track that teaches it. Every figure in every lesson is read from a live model index when the page renders and carries the vendor page it came from and the date that page was last checked.
What is this thing?
Start from nothing. Finish knowing what a language model is, what it cannot do, and why.
12 concepts, about 72 minutes of reading. Free to read, with no account.
Turning the dials
Logits, softmax, temperature, top-p, streaming and stop conditions — the whole control panel, without the maths anxiety.
10 concepts, about 60 minutes of reading. Free to read, with no account.
Getting good answers
Prompts, examples, thinking budgets, tools and schemas: the controls that decide whether a model hands you something usable or something merely plausible.
10 concepts, about 60 minutes of reading. 5 of them are free to read with no account; the rest need a paid plan.
Memory and truth
How a model reaches things it was never trained on — embeddings, retrieval, context and memory.
13 concepts, about 78 minutes of reading. 2 of them are free to read with no account; the rest need a paid plan.
What's inside
The architecture without a single equation — from what one parameter is to why the second token is cheaper than the first.
13 concepts, about 78 minutes of reading. 3 of them are free to read with no account; the rest need a paid plan.
How models are made
Pretraining, RLHF, LoRA, Chinchilla. The whole path from a pile of text to a model you can call, with the hand-waving removed.
13 concepts, about 78 minutes of reading. 3 of them are free to read with no account; the rest need a paid plan.
Cheap and fast
Where the money actually goes: memory, batches, caches, tiers and routing. How to cut a bill by an order of magnitude without changing the product.
12 concepts, about 72 minutes of reading. 1 of them is free to read with no account; the rest need a paid plan.
Agents
What the word agent means once the marketing is removed: a loop, some tools, and the permissions you decided to grant.
11 concepts, about 66 minutes of reading. Every concept in this track needs a paid plan.
Trust and evals
How anyone knows whether any of this works: what an eval is, what a benchmark score hides, and the ways a system fails while its numbers improve.
13 concepts, about 78 minutes of reading. Every concept in this track needs a paid plan.
Fast, slow, and neither
The System 1 / System 2 story everyone tells about AI, how much of it the evidence actually supports, and where TypeSafe’s Jev sits — a model that answers without writing anything, on neither axis.
5 concepts, about 30 minutes of reading. Every concept in this track needs a paid plan.