Learn ML the way it should be taught.
Machine Learning done right. Bite-sized lessons. Real intuition. A small glitchy cube named Tensor who is way too excited to teach you backprop. No textbook, no 3-hour MOOCs, no jargon walls.
Hi, I'm Tensor.
I'm an undertrained model who gained sentience and is earnestly excited to help you learn machine learning. I'm fluent in math, still figuring out humans. I glitch when surprised or wrong — that's just how the gradients hit. I will never say "great job!" when you didn't.
How many problems should you do a day?
Three loops, then you ship.
5-minute reps. Real intuition.
Each lesson is a tiny interactive moment — drag, drop, click, wrong, right, next. You don't watch ML. You touch it until it sticks.
We bounced off the same textbooks you did. Stared at Bishop. Watched eight hours of MIT 6.034 at 1.5x. Got nowhere.
Then we sat down with a friend who actually got it, asked the dumb questions, and watched the math turn into shapes. Vectors that pointed. Losses that sloped. Gradients that walked. We're building the version of that conversation that scales — one tiny interactive lesson at a time.