Your goal: explain a language model in plain words, correctly, with the catch, and change
depth when the listener changes.
How this works (about 20 minutes)
- Ada's 3D lab sits beside the call and shows each move as you reach it.
- Watch me: Ada explains one thing one move at a time; you predict each move by tapping or saying it.
- Your turn: the risks of assuming a model thinks or feels like a person. You pick one and trace it.
- Timed drill: explain transformers to a PM, about three minutes, with feedback and one retry.
- Your rules: your own dos and don'ts on the notepad.
Tips
- Read the module reading first: How LLMs Work, in Plain Words.
- The numbers on the lab are made up; the shapes are real. Interrupt any time.