

Deep learning doesn’t stop at llms. Honestly, language isn’t a great use case for them. They are—by nature—statistics machines, so if you have a fuck load of data to crunch, they can work very quickly to find patterns. The patterns might not always be correct, but if they are easy to check, then it might be faster to use them and modify the result compared to doing it all yourself.
I don’t know what this person does, though, and it will depend on the specifics of the situation for how they are used.
It’s not really communication. They ‘know’ because they become part of the same wave function. The wave function of the system is
|psi1 psi2> ± |psi2 psi1>
Note that if the ± is a plus, then exchanging psi1 and psi2 yields the exact same equation. If it’s a minus, you get a negative sign out front. Electron systems have a negative sign because of the spin statistics theorem (I don’t understand that part, so you can look it up if you want—it involves field theory iirc) Now, if electrons are exactly the same (indistinguishable), then exchanging them will yield the exact same wave function, leading to
|psi1 psi2> - |psi2 psi1> = |psi2 psi1> - |psi1 psi2>
The only solution here is |psi1 psi2> - |psi2 psi1> = 0
But recall that |psi1 psi2> - |psi2 psi1> describes the system as a whole. So this system is prohibited by quantum mechanics, and there’s no way for two electrons to have indistinguishable states (be in the same place at the same time).