Attention is how a transformer decides which parts of its input matter for which part of its output. Each token computes how much it should listen to each other token — a learned, soft, weighted glance.
In plain language
In AI and machine learning, you will run into this term whenever someone talks about how a model is built or used. Attention is how a transformer decides which parts of its input matter for which part of its output. Each token computes how much it should listen to each other token — a learned, soft, weighted glance. If you are new to the field, the simplest mental model is this: the mechanism that lets a model focus selectively. Read it once with that frame in mind, then come back and read it again — that is usually enough for the rest of the entry to make sense.
An everyday picture
Think of Attention less like a thinking person and more like someone who has read an enormous amount and now finishes other people's sentences for a living. They have absorbed the shape of the work; they have not memorised any one page.
Where it shows up
Attention tends to sit inside products that need to read, write, or recognise without a hard-coded rule — assistants, search, document tools, voice apps. It is rarely the only moving part, but it is often the part the user feels.
A small example
Imagine the scene above. The role Attention plays is the one its blurb describes — The mechanism that lets a model focus selectively. When a chatbot in a customer service portal reads a question and returns a draft reply, several of these AI ideas — model, prompt, context — are at work behind the single button you saw.
Common misunderstanding
One line to take with you
Attention is statistics worn well. Useful for patterns; double-check it for facts.