In plain English
The transformer is the neural network architecture behind most modern large language models. Introduced in 2017, it uses a mechanism called attention to weigh the relationships between all parts of an input at once, rather than reading strictly left to right. This made it possible to train much larger and more capable language models than earlier approaches.
Why it matters
The transformer is the breakthrough that made today's wave of language AI possible, so it sits underneath almost every assistant you use.
A worked example
Attention is why a model can correctly link 'it' to the right earlier word in a long sentence, tracking relationships across the whole input.
Common confusion
The architecture has nothing to do with the films or electrical transformers; the name refers to how it transforms representations of text using attention.