What is Next Token Prediction? Why does it exist? Where does it appear in Language Modeling?
Draw or describe a visual model of Next Token Prediction. What does it look like conceptually?
Work through a concrete manual example of Next Token Prediction with real numbers or pseudocode.
Implement Next Token Prediction from scratch in Python. Keep it minimal — just enough to see it work.
Try Next Token Prediction on a real example. Vary the inputs and observe what changes.
Explain Next Token Prediction in plain language using an analogy. Could a non-expert follow it?
Build a small project or demo that uses Next Token Prediction as a core component.