AI Vocabulary · 03 Working with AI
What is Temperature?
A setting that controls how predictable or varied a model's output is. Low for consistency, higher for variety.
When a model generates text, it picks each next token from a list of likely options. Temperature adjusts how adventurous that choice is. Low temperature makes the model stick to the most likely options, giving more predictable, repetitive text. Higher temperature lets less likely options through, giving more varied and sometimes more creative, sometimes less reliable output.
Temperature is usually adjustable through an API or advanced settings, not in everyday chat apps. Even at very low settings, outputs are not always perfectly identical, so it reduces non-determinism rather than removing it.
Why it matters for you
For extraction, classification and structured output, lower is usually better. For brainstorming names or campaign ideas, a bit higher can help.
Own it
If you build workflows, choose the setting deliberately per task and keep it fixed, so changes in results come from your inputs, not from chance settings.
Where it comes from
The name is borrowed from physics. In statistical mechanics, temperature controls how spread out the probabilities of a system's states are, described by the Boltzmann distribution. Machine learning reused the same maths in the softmax function: a low temperature makes the most likely token dominate, a high one spreads the chances and makes output more varied.
Related
Your AI Learning Hub
Learn the whole AI Vocabulary, step by step, and build with it. Build it. Own it.