liveBook · Manning

Nondeterminism

Also called non-determinism, nondeterministic

Nondeterminism is the property of a system or computation in which the same inputs and conditions can produce different possible behaviors or outcomes.

How 5 Manning books explain it

Machine Learning Platform Engineering

Nondeterminism is behavior in which identical inputs can produce different valid outputs across executions.

How it is used
Reframes LLM testing and production quality assurance around variable but valid outputs.
How deep it goes
Explains probabilistic variation through sampling parameters and stops short of detailed model internals.
Examples
Uses temperature, top-k, and top-p settings to demonstrate deterministic and increasingly varied outputs.
What you can do after
Evaluate LLM responses semantically and tune sampling settings instead of relying on exact string matches.

Read how Machine Learning Platform Engineering explains nondeterminism →

Machine Learning System Design

Nondeterminism is the property that identical apparent inputs may produce different outcomes because of uncontrolled state, data, timing, or randomness.

How it is used
Frames API design around making every factor affecting an ML prediction visible and controllable.
How deep it goes
Explains hidden time and random state through contrasting predict-function designs, without developing algorithmic internals.
Examples
Uses stochastic text generation, Python predict functions, current time, random seeds, and explicit random state as examples.
What you can do after
Diagnose irreproducible predictions by identifying implicit inputs and exposing time, seeds, and other output-controlling parameters.

Read how Machine Learning System Design explains nondeterminism →

Generative AI in Action

Nondeterminism is the property that repeated executions with the same apparent inputs can produce different outputs rather than a single fixed result.

How it is used
Guides temperature and evaluation choices for creative, automation, prompting, and image-generation workflows.
How deep it goes
Defines repeated-run variation and demonstrates temperature effects, but does not derive the underlying generation mathematics.
Examples
Uses repeated text completions at temperatures 0.8, 0.2, and 1.8, plus image prompts producing varied generated images.
What you can do after
Apply temperature and sampling-count settings, then evaluate generated text or images for consistency, quality, and risk.

Read how Generative AI in Action explains nondeterminism →

Build High Value Software Systems

The property of behavior that can produce different outcomes for the same input because of probabilistic processes or varying execution conditions.

How it is used
Uses nondeterminism to explain why shared standards matter when AI generates code across features.
How deep it goes
Contrasts inconsistent patterns with standards-driven consistency, without explaining the system's underlying mechanisms.
Examples
Compares error handling in payment and refund flows and cites differing logging and validation patterns.
What you can do after
Apply team standards in AI prompts to make repeated feature work produce more consistent patterns.

Read how Build High Value Software Systems explains nondeterminism →

Data-Oriented Programming in Java

Non-determinism is the property that identical inputs can produce different outputs because of hidden mutable state or other varying conditions.

How it is used
Organizes application dependencies by separating deterministic domain transformations from non-deterministic effects and service interactions.
How deep it goes
Explains causes, testing consequences, refactoring steps, and architectural boundaries, while allowing practically negligible theoretical nondeterminism.
Examples
Uses current dates, database lookups, service calls, mutable person state, parallel reduction, and late-fee processing as examples.
What you can do after
Diagnose/debug with it by locating hidden dependencies, extracting deterministic functions, and testing them without extensive mocks.

Read how Data-Oriented Programming in Java explains nondeterminism →

Also covered in

What to know first

Related concepts

Questions about nondeterminism

What is nondeterminism?

Nondeterminism is the property of a system or computation in which the same inputs and conditions can produce different possible behaviors or outcomes.

Which Manning books explain nondeterminism?

Machine Learning Platform Engineering, Machine Learning System Design, Generative AI in Action, Build High Value Software Systems and Data-Oriented Programming in Java.

What should I know before learning nondeterminism?

Manning books that teach nondeterminism usually introduce language model, contract, loop and generative modeling first.

What is the difference between nondeterminism and conversational ai?

Nondeterminism is the property of a system or computation in which the same inputs and conditions can produce different possible behaviors or outcomes. Conversational AI is artificial intelligence that enables software systems to interpret user input and interact with users through natural-language dialogue.

What is nondeterminism also called?

Nondeterminism is also called non-determinism or nondeterministic.

These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.