Temperature
Temperature is a setting that controls how predictable or varied a model's output is. Low temperature makes it pick the most likely words (steady, repetitive); higher temperature lets it take more chances (creative, but more error-prone).
In one line, for a 12-year-old
Temperature is the AI's "surprise me" dial: low is careful, high is wild.
An example
A developer sets a low temperature for a bot that extracts invoice totals, and a higher one for a slogan brainstorm.
Why it matters to people
It explains why you can ask the same question twice and get different answers. Consistency matters when AI is used for anything official.