I've read Raschka's "Build Your Own LLM from Scratch" book and really enjoyed it. I haven't tried the code yet, but the code from his previous Python ML book worked great.

I follow Disney's theme park patents for fun. They've got two alternate methods for singling out guests. One uses shoe recognition (https://patents.google.com/patent/US9393697B1/en). Another identifies individual guests who interact with a group (https://patents.justia.com/patent/9807350), and builds a social graph based on that.

Neither of these can tie back to personal information. But within the park, they seem intent on distinguish between individuals.

Starts off by explaining the industrial engineering decisions that drove Disney to create its FastPass ride-reservation system. Goes on to show how business decisions led to longer waits for some theme park customers.