Deterministic vs. Stochastic
Deterministic systems return the same output for the same input every time. Stochastic (probabilistic) systems, including most LLMs, sample from possible answers so results can vary run to run.
This distinction explains why AI buttons feel “alive” but also unreliable compared to traditional software.
What it means
Deterministic: fixed rules or seeds produce repeatable results. Stochastic: the model chooses among likely tokens, so tone, structure, and facts can shift with temperature, prompt, or randomness.
Why designers should care
You design different UX for each mode: confirmations and diffs for stochastic drafts; strict validation for deterministic pipelines. Never promise spreadsheet precision from a sampling model without structure.
Example
“Regenerate summary” produces three variants users can compare; “Export to CSV” runs a schema-locked step with validation errors, not a free-form chat reply.
Common mistakes
- • Caching one good LLM output and assuming it will repeat for every user.
- • No regenerate, edit, or version history on stochastic content users must approve.
- • Mixing stochastic generation with deterministic-looking UI (fixed slot labels) without refresh affordances.