Skip to content

Generative AI & LLMs

Model nondeterminism

An AI giving different results when the same request is repeated under apparently identical conditions.

Example

An assistant writes slightly different drafts from the same request.

Why people use it

It explains why repeating a request may not produce identical results.

What you'll hear

“Why did the same question get different replies?”

What this means for you

Try repeated requests when consistency matters and record the settings used.

Can you control it?

No

No direct control. This describes a wider issue, concept or result rather than something you can simply switch on or off in a tool.

Common questions

Does setting a low temperature always guarantee identical results?
No. Other implementation and execution factors can still affect reproducibility.
Does a different reply always mean the facts changed?
No. The wording or selection process can change while the basic information stays the same.
Can it complicate comparing two versions?
Yes. Several trials may be needed to separate ordinary variation from a real difference.

Related terms

Still have questions?

Up to 500 characters.

Ask LATHIC about AI. Relevant glossary entries may be included.

Your question, the glossary entries it matches, and a rotating pseudonymous identifier go to Microsoft Azure’s OpenAI service through Vercel AI Gateway to generate an answer. Zero retention and no training are required of the provider, and LATHIC does not save your question or answer. Privacy Notice