The strict umpire — temperature.
Show the same delivery twice and you can get two different calls. One dial — temperature — sets how often that happens.
From Lesson 1, the model never sees one certain answer. It sees the odds: a spread of possible calls, each with a probability. But it has to commit to just one. How it picks is the question this lesson answers.
It picks by drawing from those odds, and a setting called temperature controls the draw. Turn it down and the model almost always takes the single most likely call. Turn it up and the long shots — the less-likely calls — start getting a real chance.
Picture a strict umpire who goes by the book: the same delivery earns the same verdict, every time. A more relaxed umpire might see that ball and rule differently on another day. Temperature is the dial between those two umpires.
Turn it down for consistency — a verdict, a number, a fixed format; turn it up for range — ideas, phrasings, variety. In a real model the calls are possible next words, so the same dial decides whether each word is the safe pick or a surprising one.
Set the temperature, then review the same delivery a few times. Low and steady, or high and surprising — watch the calls.
One setting on the call.
Temperature is a single argument. Low for answers you want to be the same every time; high when you want the model to range around.
The dial between steady and surprising.
The model turns a delivery into odds. Temperature reshapes those odds before a call is drawn: low, and the top one towers over the rest — the strict umpire, the same verdict each time; high, and the odds flatten so the long shots start landing — varied, fresher, less predictable.
It changes how the answer is chosen — not how much the model knows, and not how confident it is: the underlying scores are identical either way. Turn it down for consistency and format; turn it up for range and ideas — and remember that more variety is not the same as more correct.