It doesn’t. They run using stuff like Ollama or other LLM tools, all of the hobbyist ones are open source. All the model is is the inputs, node weights and connections, and outputs.
LLMs, or neural nets at large, are kind of a “black box” but there’s no actual code that gets executed from the model when you run them, it’s just processed by the host software based on the rules for how these work. The “black box” part is mostly because these are so complex we don’t actually know exactly what it is doing or how it output answers, only that it works to a degree. It’s a digital representation of analog brains.
People have also been doing a ton of hacking at it, retraining, and other modifications that would show anything like that if it could exist.
I shouldn’t have anything to hide, but I’m part of a group the current fascist leadership in government want’s to eradicate, so hide I shall.
That said, I also feel like people acting like the remote server they are connected to is tracking what you do on it as some kind of surprise is so stupid. “Facebook is keeping track of the pictures I uploaded to it!!!” There’s a lot of stuff to complain about Facebook, google, or whoever, but them tracking stuff you send to them willingly isn’t one of them.