Transformer

Level 3

Short Description

The neural network architecture, introduced in 2017, that underpins modern LLMs and most state-of-the-art generative models.

Friendly Description: The Transformer is the breakthrough design that powers nearly all modern AI language models. Introduced by researchers in 2017, it uses an idea called attention to focus on the most relevant parts of an input. The Transformer is what made it possible to train AI on huge amounts of text efficiently, and it's behind tools like ChatGPT, Claude, and Gemini.

Example: When you chat with a modern AI assistant, a Transformer is doing the heavy lifting. It's looking at your message, paying attention to the most important parts, and generating a thoughtful response, often in less time than it took you to type the question.

→ Back to Dictionary