Deleted Comment
In that website's playground (https://quantumjavascript.app/playground.html), just write:
H
And you'll get 50% 0 and 50% 1.Now, /why/ does it jump when measured? We don't know, but physicists have many cool theories.
One of which is that it doesn't really jump, but just that there are many universes created and one shows a 0 and another one shows a 1 (Called the Many-worlds interpretation). As weird as it sounds, it seems like the most promising explanation. There are other theories but they all need to add hacks to make the maths work.
They are fantastic in hot climates, and should be littering the roofs in CA, AZ, TX, etc.
Dead Comment
In a nutshell, differentiable programming is a programming paradigm in which your program itself can be differentiated. This allows you to set a certain objective you want to optimize, have your program automatically calculate the gradient of itself with regards to this objective, and then fine-tune itself in the direction of this gradient. This is exactly what you do when you train a neural network."
Isn't this just declarative programming as we know it from e.g. Prolog, SQL or other places where the programmer declares what their objective is, and it's left up to the interpreter, compiler or scheduler to figure out the best way to achieve that? And now that's being applied to ML (which probably makes sense, since it involves a lot of manual tweaking). Sounds like a great use case for a library, but hardly worthy of being called a new programming paradigm.
Also I personally would prefer a paid service, faces typically are secure private documents I would want some level of guaranteed and privacy.