Skip to content

Model Training & Adaptation

Autoregressive model

AI that creates something one piece at a time, using earlier pieces to help choose the next.

Example

A writing AI chooses its next piece of text using the words already written.

Why people use it

It provides a way to build a longer answer one piece at a time.

What you'll hear

“Each new piece follows what came before.”

What this means for you

Remember that a plausible continuation can still be factually wrong.

Can you control it?

Developer-only

The people building or running the AI choose this setup. An everyday user generally needs their help to change how this part works.

Common questions

Can this method create something other than ordinary writing?
Yes. The same step-by-step approach can be used for ordered material such as code or sound.
Can an early mistake affect later writing?
Yes. Later pieces are influenced by the text already generated, including earlier mistakes.
Does it know the entire final answer before starting?
Not necessarily. The sequence develops as the system selects successive pieces.

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