What's a token, the 'piece' AI talks in?
To AI, a sentence isn't letters or words — it's a line of pieces called tokens.
1 · Think first
The “next piece” from yesterday has a name in the AI world: a token.
A token is not a letter and not a word — it's a piece cut to be easy for AI to compute with, and its size changes from case to case.
So the same sentence gets a different count in tokens, and time and cost go up with that count.
2 · Experiment · Split it up
Try it — the sentence-splitting machine
Pick a sentence and cut it up three ways. Each way gives a different number of pieces.
Figure
In one picture
Same sentence, but the unit people count (words) and the unit AI counts (tokens) are different.
3 · Quiz
Quick check
Three questions. Pick an answer and it's marked right away, with the reason why.
Today in one line
Today in one line
To AI, a sentence isn't letters or words —
it's a line of pieces called tokens.
Learn more
- Today's common way of cutting text into pieces (subwords) goes back to this 2016 paper — Neural Machine Translation of Rare Words with Subword Units
- Want to see how a real AI splits text? Look up OpenAI's token counter (tiktoken) — github.com/openai/tiktoken