Nice article, but the methods they used seem more like they just hand wrote a function for the task and called the function neurons based on how it was implemented. It is encouraging though that a simple network can be found for a complicated task like this, kind of like the Tiny Recursive Model that came out last year.

I think that's basically right. The "neurons" framing feels a bit loose here; it's more like a very compact hand-designed controller expressed in neural-network-ish terms

That was my take, too. You could control a bike with just one linear neuron with one input, if you pass in the correct steering torque. Still a fun paper.