Transformer
The neural-network design behind almost every modern language model. It reads a whole sequence at once and learns which parts relate to which.
It is the architecture that made today's AI boom possible. The "T" in GPT stands for it.
Frequently asked questions
What does the T in GPT stand for?
It stands for transformer, the neural-network design behind almost every modern language model. The transformer is the breakthrough architecture that made today's AI boom possible.
Why is the transformer such a big deal?
Unlike older designs that read text word by word in order, a transformer takes in a whole sequence at once and learns which parts relate to which. That ability to see the full picture is what unlocked reading, writing, and reasoning at scale.
Do I need to understand transformers to use AI?
Not at all to use it day to day. It helps to know that a transformer is the engine design under the hood, so when you hear the word you can place it as the foundation that models like GPT are built on.
New to all this? Start with what an AI agent really is, browse the full glossary, or explore the learning hub.
← Back to the glossary