Vanessa is a user on octodon.social. You can follow them or interact with them if you have an account anywhere in the fediverse.
If you don't, you can sign up here.
In the end it's just matrices of numbers (representing weighted connections and biases) and known activation functions that we selected before training (usually Gaussian or sigmoidal but anything differentiable will do if you like to experiment). Simple? Probably not. Utterly impenetrable? No.
