Safety
temperature
Temperature scales randomness in sampling: lower values are more deterministic; higher values explore more.
Expanded definition
temperature shows up constantly when teams ship LLM features. Practically, it influences how you design prompts, evaluate quality, and reason about failure modes. Teams should document how temperature manifests in their stack—data handling, evaluation, and runtime guardrails—and revisit assumptions as models update.
Related terms
Explore adjacent ideas in the knowledge graph.