What is Autoregressive Model?
An AI model that generates output one piece at a time, using each piece to predict the next.
Why It Matters
Most modern language models are autoregressive, which is why they generate text word by word.
Real-World Example
ChatGPT generates each word based on all the words before it, which is why you see text appearing gradually.
“Understanding terms like Autoregressive Model matters because it helps you have better conversations with developers and make smarter decisions about your software. You do not need to be technical. You just need to know enough to ask the right questions.”
Related Terms
Large Language Model (LLM)
An AI system trained on massive amounts of text that can understand and generate human language.
Masked Language Model
An AI model trained by hiding random words in text and learning to predict what the missing words are.
Transformer
A type of AI architecture that processes text by paying attention to relationships between all words at once, rather than reading sequentially.
Encoder-Decoder
An AI architecture where one part compresses input into a representation and another part generates output from it.
Learn More at buildDay Melbourne
Want to understand these concepts hands-on? Join our one-day workshop and build a real web application from scratch.