You don't have to solve the Navier Stokes equations analytical for this. You don't even have to solve them explicitly at all: I can see a grad student just getting a lot of experimental data and throwing it all at a neural net with good results.
> You don't have to solve the Navier Stokes equations analytical for this.
Yes, to be sure you are right. It was just a silly (and, as you point out, mathematically inaccurate) joke.
It doesn't solve the hidden cavity problem very well, though.
Just a quick solution of a million-dollar math problem (https://en.wikipedia.org/wiki/Millennium_Prize_Problems#Navi...) and you're on your way!