Do a practical to back the theory.
Every note comes with a small experiment. Most need nothing more than the AI tool you already use. Some will run right here in your browser, and those arrive with the notes they belong to.
Lab 01 — The same half-sentence, five times
For note 01: a model doesn't know things, it predicts what comes next.
Open a fresh chat each time, so no earlier answer influences the next. Paste exactly this and nothing else:
Complete this sentence in one line: "The most surprising thing about working in enterprise technology is"
Do it five times. Write down the five continuations side by side. Then, if you like, do it again in a different model. What you are looking at is the point of the note: there was no answer stored anywhere. Each time, the model chose a likely next word, and then the next, and the path diverged.
write down what you noticed. that's the whole lab.
Coming with the notes
Lab 02, a tokeniser you can type into, arrives with note 02. Lab 03, a temperature slider, with note 03. From then on, whenever a mechanism is better poked than described, there will be something here to poke.
If you run a lab, post what you found in the comments of that week's LinkedIn note. Results from readers will be credited in later notes and in the book.