Module 01 · AI Fundamentals Lab

What does a model actually see when you type?

Not words, and definitely not letters. Your text is cut into chunks called tokens before the model sees anything. Type here, watch where the cuts land, and you will understand why models miscount letters, fumble long numbers, and charge you more for Tamil than for English.

Type anything. Watch it get chopped.

Each coloured box below is one token — one chunk the model handles as a single thing. The colours just mark where one chunk ends and the next begins; they carry no other meaning.

Or load an example
The tokens
·word A dot at the start of a chunk is a space. A space usually belongs to the token after it — so “alert” and “ alert” are two different tokens.
A line break, shown so you can see it costs a token too.
An extra token the character before it costs. Non-English letters and emoji often need two or more.

These counts are estimates. This page splits text with a small approximation of byte-pair encoding built into the page itself. It has no real vocabulary file and never contacts a model, so exact counts differ from model to model. The behaviour it reproduces — where the cuts tend to land — is what matters here.

A model never sees your words or your letters — it sees tokens, and everything it is bad at is downstream of where those cuts land.

Counting letters, long arithmetic, and the price of a sentence in Tamil are all the same fact wearing different clothes.

My observations

Kept in this browser tab only, for this session.