AI Origins · Lesson 03
Pick a story, teach the robot, and watch a tiny language model guess the next word.
First try: Animal Story, then Generate from "our class."
Pick a story to get started.
When you change the controls, keep your eyes here. This is the live result.
Pick a sample, teach the robot, and generate from a starter phrase.
Turn on comparison mode to see a semantic-style continuation.
N-grams count words; LLMs model relationships.
Click a guess to add it to your starter phrase.
N-grams are one of the oldest honest ways to explain how a machine can guess what word might come next.
1900s
Andrey Markov studied how one item in a sequence can help predict the next. That idea still powers this lesson.
1948
Claude Shannon showed that language could be modeled statistically, which helped launch information theory and early language prediction.
2010
Google made n-gram history visible by letting people explore how words and phrases rise and fall across millions of books.
Today
Newer AI systems go far beyond n-grams, but this is still a great first model for understanding next-word prediction.
Change one thing at a time and see how the robot responds.
Use these prompts for discussion, notebooks, or a fast exit ticket.