1:40Explainer · 4 chapters
Why You Do Not Understand AI — watch, 1:40
Why a language model feels like it understands, what it is actually doing, and three questions that replace “does it understand?”.
Change a learning rate, draw a decision boundary or inspect attention weights in eight browser experiments. These small examples explain mechanisms; they do not evaluate a production model.
Watch signal propagation through a configurable feedforward network. Adjust layers and neurons, see activations flow in real time.
See the optimizer in action. Click anywhere on the surface to place the ball — watch it roll downhill to find a minimum.
A two-layer network showing forward and backward passes. Forward propagates input to output (steel blue). Backward sends error gradients (vermilion, dashed).
Click cells in the input grid to draw a pattern. Choose a kernel and see how convolution transforms the image.
See how self-attention lets each word look at every other word. Click a token to highlight its attention weights and the context it builds.
Plot the functions that give neural networks their nonlinearity. Toggle each one on or off and move your cursor to read exact values.
Place blue and red points, then train a perceptron. Watch the decision line rotate as it corrects each mistake — until it separates the classes.
Fit polynomials of different degrees to the same points. A low degree underfits; a very high degree fits every point but wiggles wildly between them.
You've seen what the models can do. The other question — what stays valuable when they can do it all — is a 224-page eBook: How to Remain Valuable When Intelligence Becomes Cheap →
A short companion to the tools above.
1:40Explainer · 4 chapters
Why a language model feels like it understands, what it is actually doing, and three questions that replace “does it understand?”.