abra1010

If you're doing "deep learning" using frameworks like Tensorflow, PyTorch or JAX you're using autodiff all the time.

> the need for a statically typed "differentiable" language is extremely high

This is not what Google has found, actually. Teams who wanted to use this for research found that a static language is not flexible enough when they want to generate graphs at runtime. This is apparently pretty common these days, and obviously Python allows it. Especially with JAX that traces code for autodiff

You're right, it sounds like BS because it's BS.

Swift was railroaded in Google by Chris Lattner, who has since left Google and S4TF is on death watch. No one is really using it and it hasn't delivered anything useful in 2.5 years