knowledge base

Knowledge Base

Papers we've read carefully enough to redraw. Each entry starts with no assumptions at all and adds the technical layer only once the idea has landed — the version we wish had existed when we first opened the PDF.

cat method.md
→ plain english first — the idea before any notation
→ then the construction — how it's actually built
→ then the arithmetic — only where it earns its place
→ every figure animated, zoomable, and drawn from the real numbers

20 illustrated · 22 in the base

Send each query to the cheapest model that can actually answer it — the upfront routers, the cascades that check their own work, and how to measure any of them honestly.

The same specialist quality on a fraction of the parameters — by copying a bigger model, by finding the subnetwork that mattered, or by training only a thin adapter.

How much data, of what quality, for how big a model — the arithmetic of where to spend a compute budget, and the case that quality beats quantity.

How a base model becomes an assistant — the data bar, the human-feedback template, the loss that made preferences cheap, the hardware that fits one GPU, and the fully open recipe that ties it together.

The bets on what comes after the standard recipe — reasoning learned from reward, sequence models without attention, models that keep learning after training ends, and prediction in latent space.

What all of the above looks like in a regulated domain, where the data can't leave the building and "approximately right" isn't good enough.

Every numbered entry is live — illustrated end to end. Dashed cards are in the works — the wider reading list under papers/, built in curriculum order — and link to the source paper until their entry lands. As the base grows: search and the tag chips cut across every arc, the arc bar above jumps within the page, and ≡ compact flips to a one-line-per-paper view.

Prefer a guided tour of the architecture itself? The Illustrated Decoder covers a GPT-style model one figure at a time, or run the forward pass in 3D.

Working on routing, fine-tuning, evaluation, or sovereign deployment — or want to? hello@attention.sh