AI Curriculum

You don't need to understand the math. You just need the mental model.

Where the knowledge comes from, and what "knowing" means for a machine.

How a text predictor learns to act like the thing you're talking to right now.

It's just one long prompt. Every single time.

Most transformer explainers get lost in the math. This visualizes how information flows through the network end to end.

Now that you know there's no memory, let's talk about what that means for how you use these things.

The same question, asked by different personas, gets completely different answers.

Don't just tell it what to do. Show it how to do it.

The AI knows what information it needs better than you do.

Just do the easiest, laziest thing. It'll probably work.

When one model confuses you, ask another to explain.

The model isn't having a bad day. Your prompt is bad.

Every time you say "no, do it like this," you are adding that failure to the input.

Once the model fails twice, the third attempt is already doomed.

The most important lesson in this entire curriculum.

Know when the model needs to look things up.

Sometimes the best document isn't a document, it's a webpage.