Modelwerk
For the longest time children stood inside looms lifting weights to allow the thread to go through on the command of the weaver. They were called draw boys...
I think about this a lot when I look at modern AI, not because the technology is simple, but because arguably the opposite problem has set in. The draw boys are back, except now they are us. We sit inside these systems lifting weights to pull threads—fine-tuning, prompt-engineering, RLHF-ing, RAG-ging, context engineering—and we can't explain what the machine is doing, or why, or even what the final pattern will be. Their abstractions have become a mystery. And they are far from predictable or legible.
The project he's writing about is cool too, a journey through the implementation of different kinds of neural networks from a Perceptron to an Attention model, all using only the python standard library.
Each lesson is a runnable Python script. You execute it, it trains the model, it prints a narrative explanation of what just happened. The output walks through the architecture, the math, a worked example, and what the results mean. It's meant to read like a tutorial that also actually runs.