AI Jargon Buster
AI news and the language around it, simplified.
What is an Autoregressive Model?
An autoregressive model is a type of AI system that generates content by predicting the next piece of information based on the pieces that came before it. Think of it like a sophisticated version of the autocomplete feature on your phone. It looks at the sequence of words or data you have already provided and calculates the most statistically likely next step. It repeats this process over and over, one step at a time, to build a complete sentence, paragraph, or image. Essentially, it is a model that talks to itself to ensure that each new addition fits logically with the history of what it has already created. Because it relies entirely on the previous output to determine the next one, the quality of the final result depends heavily on the initial prompt or the context provided at the start of the interaction.
Why this matters to you
Most modern generative AI tools rely on this architecture to produce human-like text. Understanding this helps you realize that these tools are not thinking in a human sense, but are instead performing complex probability calculations to guess what should come next in a sequence. This is why these models can sometimes lose the thread of a conversation or make mistakes if the previous context was confusing or incorrect, as every error compounds with each subsequent step.
How you might hear this
Our new content generation tool is an autoregressive model, which explains why it sometimes drifts off topic if the initial prompt is not specific enough.
AI Jargon Buster
Search any AI term, explained in plain English.
Type a term below and search. You will be taken straight to the tool.
Related terms
See how your CV performs against the ATS algorithms that screen candidates before a human ever reads your application.
Try the CV Optimiser →How AI job displacement actually works, what it means for your career, and what to do about it. Written by someone who has been in recruitment for 25 years.
When the Ground Shifts →