Tensors: the shape data takes inside AI
Building Blocks · Part 5
Vectors were one row of numbers. Tensors are what you get when a model needs to stack rows into grids, and grids into stacks of grids.
Read entryFig. I — The ledger, updated monthly
Notes on engineering, frontier AI, editorial design, and the quiet mechanics of running an independent studio.
Building Blocks · Part 5
Vectors were one row of numbers. Tensors are what you get when a model needs to stack rows into grids, and grids into stacks of grids.
Read entryBuilding Blocks · Part 4
Every entry in an embedding is a separate axis of meaning. Here's what that actually buys a model, and what it costs.
Read entryBuilding Blocks · Part 3
Vectors gave every idea an address. Embeddings are what happens when a model chooses those addresses on purpose, so that meaning has geography.
Read entryBuilding Blocks · Part 2
Part 1 gave you the dials. This one gives them something to act on.
Read entryBuilding Blocks · Part 1
Every model you've ever used is, underneath, a very long list of numbers. Here's why that turned out to be the winning design.
Read entryBuilding Blocks · Part 0
Somewhere between "it's just predicting the next word" and a hundred-billion-dollar training run sits an actual mechanism.
Read entryFoundations · Part 9
The question that started this whole series, revisited now that you actually know how the current stuff works.
Read entryFoundations · Part 8
One camp locks the recipe in a vault. The other publishes it for anyone to copy, tweak, and rebuild.
Read entryFoundations · Part 7
AI doesn't invent its opinions from nowhere. It learns them — including the ones we'd rather it didn't — from us.
Read entryNotes from the studio, sent on the first of the month. Engineering notes, design teardowns, and the occasional bad omen.
No spam, no tracking pixels. Just signal.
Get in touch for updates and project inquiries:
hello@goodomens.studio