All commands have the format `output = \func inputs` or just `\function inputs`. Points and scalars are built on the fly. Eg `\line a b` to an empty canvas creates points `a` and `b`, and joins them with a line.

One can use broadcasting semantics similar to NumPy and PyTorch in a visual setting (imagine creating a list of circles where one dim corresponds to radius and another to the center). One can also use backpropagation, run gradient descent or visualize vector fields. Almost everything is reactive so changing a variable updates all of the downstream geometry. It also allows anyone to write and load their own visualization, which can be broadcasted and differentiated through.

I liked this one, but it took me a while to understand, I think this page is a much better intro: https://www.tinyvolt.com/geomatic/examples/getting-started

Bug: https://www.tinyvolt.com/geomatic/examples/broadcasting-in-g... Click "Draw a single n-star" Results in a message popping up "unknown command: n-star"

Clean implementation. One thing I always look for: how does this degrade when things go wrong? Good error handling is what separates weekend projects from tools people actually use.

Pretty cool. Curious, why a one time payment? Why not, say, a smaller monthly payment?

What is autodiff?