Could you elaborate why this is so impressive? As I understand it, it's because things like TF or PyTorch can only AD specific things as part of a spec vs generic functions like this?
You don't have to hope that your AD/ML package has that function, you can just write it or find it in a package and punch it straight in. That's awesome.
Tensorflow has OP(eration)s that are differentiable that you can compose and that's it. If you want to implement something that is going to be differentiable you need to implement it using Tensorflow OPs or add your own OPs to [tensorflow] with their gradient.
With Flux you can take code written by a random guy on the internet that never thought about using his stuff in ML and Flux will be able to differentiate it anyway.
https://github.com/tensorflow/tensorflow/tree/master/tensorf...
They've also got to manually implement the Python -> autograph translation for a whole variety of language features (so any language features that get added or changed will break autograph until it's updated.
Flux gets this essentially for free, for the entire Julia language, without the need to manually build that language -> tensorflow translation layer. With the added benefit of Julia's non-trivial performance benefits.