Cool! How do you actually implement “Reverse-mode automatic differentiation with a tape-based computational graph” in rust?

Most web request cases where you care about performance probably have multiple parallel web requests, so there’s no clean separation possible?

Don't the models typically train on their input too? I.e. submitting the question also carries a risk/chance of it getting picked up?

I guess they get such a large input of queries that they can only realistically check and therefore use a small fraction? Though maybe they've come up with some clever trick to make use of it anyway?