← Resources
How does Generative AI work?
01 / 12 · The prompt
Everything between those two moments is the story.
02 / 12 · Tokens
The model reads tokens, not words. Fragments, each with a numeric ID.
03 / 12 · Embeddings
The model has seen every token in millions of sentences. From the words it tends to sit beside, it builds a vector, a list of numbers that encode what this word means.
04 / 12 · Similarity
Words we use interchangeably end up with nearly identical vectors.
05 / 12 · Space
Stack those vectors together and patterns emerge. Weather words cluster, food words cluster, emotions cluster.
06 / 12 · Attention
A transformer reads the whole sentence at once. Each token decides which others matter, all in parallel.
07 / 12 · Context
Attention is how the model tells the difference.
08 / 12 · Depth
The same sentence flows through the attention machinery dozens of times. Each pass refines the picture. Grammar, tone, reference, agreement, all emerging as the stack climbs.
09 / 12 · Prediction
A probability over every token in the vocabulary.
10 / 12 · Temperature
That probability distribution has a knob. Turn it down and the model picks the most likely word every time. Turn it up and it starts gambling.
Same model. Same prompt. Same probabilities. Just a different appetite for risk.
11 / 12 · Generation
No plan. No outline. Just the next word, over and over.
12 / 12 · Limits
The model knows what text usually follows what text, not what's true.
Not a mind. Not the world. Just the patterns, and like any map, most useful when you remember it isn't the territory.
Take the AI Readiness Quiz →■ end ■