Words Are Secretly Numbers

Computers only understand numbers. So how do they read your messages? They turn every word into a secret number code. So when you type a message to an AI, something sneaky happens.

12 min · Reviewed 2026

Computers Only Speak Math

Here is a fun secret. A computer cannot actually read the word cat. To a computer, letters are just squiggles on a screen. It only really understands numbers.

So when you type a message to an AI, something sneaky happens. Every word gets turned into a number first. Then the AI thinks about the numbers. Then it picks new numbers and turns those back into words for you.

Tiny word parts called tokens

It is even a little wilder than that. The computer does not always use one number per word. Sometimes it chops words into small pieces called tokens. The word playing might be split into play and ing, each with its own number.

cat might be one token
unhappiness might be three tokens: un, happy, ness
short common words usually get their own token
strange or long words get chopped up

Try it in your head

Imagine the sentence I love pizza. A computer might turn it into the numbers 15, 203, 4902. That tiny number sentence is what the AI actually thinks about. Wild, right?

In the computer's world, Shakespeare is just a very long list of numbers.
— A friendly programmer

The big idea: every word you type becomes a number. AI thinks in numbers, then translates back to words so we can read its answer.

End-of-lesson check

8 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-explorers-words-as-numbers

What is the main idea of "Words Are Secretly Numbers"?
1. Computers only understand numbers.
2. Use AI as the final authority for the whole decision
3. Avoid checking the answer once it sounds polished
4. Focus only on speed instead of judgment
Which concept is most central to "Words Are Secretly Numbers"?
1. representation
2. tokens
3. encoding
4. token
Which use of AI fits this topic best?
1. Let the AI decide what matters without your review
2. Use the answer before checking whether it fits the situation
3. cat might be one token
4. Trust the first answer because it sounds confident
What should a careful learner remember about "Think of it like a secret code"?
1. Use AI to learn about tokens, then check the answer with a trusted adult or source.
2. Skip the context so the tool can guess faster
3. Treat the output as private even after sharing it online
4. Use the answer without checking the source
You want to use AI after this lesson. What is the safest next step?
1. Act immediately because the AI answer is written clearly
2. Use short, concrete wording and ask a trusted adult when the stakes matter.
3. Hide uncertainty so the final answer looks cleaner
4. Use private or sensitive details before checking permission
How should AI output about tokens be treated?
1. As proof that no other source is needed
2. As a replacement for context, consent, or expert review
3. As a draft or helper output that still needs human judgment and verification
4. As something that becomes correct when it sounds confident
Name one way to verify an AI answer about tokens.
Which action would help you apply "Words Are Secretly Numbers" responsibly?
1. Use the tool to avoid thinking through the tradeoff
2. Keep going even if the output conflicts with a trusted source
3. Trust the first answer because it sounds confident
4. unhappiness might be three tokens: un, happy, ness

← Back to interactive lesson

Tendril · Explorers · AI Foundations

Words Are Secretly Numbers

Computers only understand numbers. So how do they read your messages? They turn every word into a secret number code. So when you type a message to an AI, something sneaky happens.

12 min · Reviewed 2026

Computers Only Speak Math

Here is a fun secret. A computer cannot actually read the word cat. To a computer, letters are just squiggles on a screen. It only really understands numbers.

Tiny word parts called tokens

cat might be one token
unhappiness might be three tokens: un, happy, ness
short common words usually get their own token
strange or long words get chopped up

Try it in your head

Imagine the sentence I love pizza. A computer might turn it into the numbers 15, 203, 4902. That tiny number sentence is what the AI actually thinks about. Wild, right?

In the computer's world, Shakespeare is just a very long list of numbers.
— A friendly programmer

The big idea: every word you type becomes a number. AI thinks in numbers, then translates back to words so we can read its answer.

End-of-lesson check

8 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-explorers-words-as-numbers

What is the main idea of "Words Are Secretly Numbers"?
1. Computers only understand numbers.
2. Use AI as the final authority for the whole decision
3. Avoid checking the answer once it sounds polished
4. Focus only on speed instead of judgment
Which concept is most central to "Words Are Secretly Numbers"?
1. representation
2. tokens
3. encoding
4. token
Which use of AI fits this topic best?
1. Let the AI decide what matters without your review
2. Use the answer before checking whether it fits the situation
3. cat might be one token
4. Trust the first answer because it sounds confident
What should a careful learner remember about "Think of it like a secret code"?
1. Use AI to learn about tokens, then check the answer with a trusted adult or source.
2. Skip the context so the tool can guess faster
3. Treat the output as private even after sharing it online
4. Use the answer without checking the source
You want to use AI after this lesson. What is the safest next step?
1. Act immediately because the AI answer is written clearly
2. Use short, concrete wording and ask a trusted adult when the stakes matter.
3. Hide uncertainty so the final answer looks cleaner
4. Use private or sensitive details before checking permission
How should AI output about tokens be treated?
1. As proof that no other source is needed
2. As a replacement for context, consent, or expert review
3. As a draft or helper output that still needs human judgment and verification
4. As something that becomes correct when it sounds confident
Name one way to verify an AI answer about tokens.
Which action would help you apply "Words Are Secretly Numbers" responsibly?
1. Use the tool to avoid thinking through the tradeoff
2. Keep going even if the output conflicts with a trusted source
3. Trust the first answer because it sounds confident
4. unhappiness might be three tokens: un, happy, ness

← Back to interactive lesson