The era runs on learning machines, yet the learning itself stays hidden behind an API. Here it is in the open, every step on screen and running entirely in your browser: a neural net carving a decision boundary in real time, an agent stumbling into a reward, attention deciding which word to look at, noise resolving into structure under a diffusion model. No cloud, no keys — just gradients, policies and probability, drawn as they happen.
A Kohonen lattice that crumples, stretches, and drapes itself over any data distribution — topology discovery made visible.
Watch a tabular RL agent bootstrap a navigation policy from scratch — stumbling through traps, discovering reward, and etching optimal arrows into every cell of the grid.
Watch the 1958 Rosenblatt neuron carve a decision line through your data, one correction at a time.
Watch a hand-rolled neural network bend its decision boundary in real time as it learns to separate 2D point clouds through backpropagation.
The ancestor of GPT — predict the next token from the last few and watch coherence emerge as order grows.
Watch Lloyd's algorithm carve a scatterplot into living Voronoi territories as centroids hunt down their clusters in real time.
Watch a noisy or half-erased pattern snap back to a stored memory as a network of neurons rolls downhill into an attractor.
Five gradient-based optimizers race down the same loss landscape simultaneously, revealing why Adam dominates vanilla SGD in speed, stability, and saddle-point escape.
Roam a hand-crafted semantic space where king − man + woman snaps exactly to queen, and clusters of meaning bloom in neon colour.
Watch a CART classifier carve your 2-D data into axis-aligned regions — one information-maximising split at a time.
Watch ε-greedy, UCB1, and Thompson Sampling race to find the best slot machine arm — live cumulative regret plotted as the algorithms explore and exploit.
Watch a transformer decide what to look at — softmax(QKᵀ/√d) made visceral through live heatmaps and bipartite attention flows.