Lesson 978 of 1234
AI Quietly Picks the Most Likely Word
AI picks each word by guessing which is most likely to come next.
Lesson map
What this lesson covers
Learning path
The main moves in order
- 1The big idea
- 2probability
- 3next-token prediction
- 4language models
Concept cluster
Terms to connect while reading
Section 1
The big idea
AI writes one word at a time. For each word, it guesses which word is most likely to come next.
Some examples
- After 'peanut butter and...' AI strongly guesses 'jelly.'
- After 'I love...' the next word could be many things.
- Each guess is a probability, like a weather forecast.
- AI usually picks the highest one, but sometimes it explores.
Try it!
Type 'peanut butter and' to AI. Watch it pick 'jelly' (most of the time). Now type 'I love' — the answers will be very different each time.
Key terms in this lesson
End-of-lesson quiz
Check what stuck
15 questions · Score saves to your progress.
Tutor
Curious about “AI Quietly Picks the Most Likely Word”?
Ask anything about this lesson. I’ll answer using just what you’re reading — short, friendly, grounded.
Progress saved locally in this browser. Sign in to sync across devices.
Related lessons
Keep going
Explorers · 40 min
AI Is Really a Prediction Machine
AI is like a super-smart guesser that predicts what comes next.
Explorers · 5 min
How AI Counts Words to Pick the Next One
AI doesn't think — it picks the next word by guessing what fits best.
Explorers · 40 min
How AI Chops Up Words Into Tiny Pieces
AI breaks words into little chunks called tokens.
