Transformer: definition

A transformer is the neural-network design behind modern language models, able to weigh the relationships between all parts of an input at once, which is what made large language models possible.

Introduced in 2017, the transformer’s key idea (attention) lets a model consider how every word relates to every other word in a passage, in parallel. That turned out to scale astonishingly well, and it is the architecture under GPT, Claude, and the rest.

You do not need the internals to use these models, but it helps to know the "T" in GPT stands for transformer, and that this one design is why the last few years of AI happened.

Related terms

Large language model (LLM): A large language model is a neural network trained on huge amounts of text to predict the next token, which lets it write, summarise, classify, and answer questions across almost any topic.
Deep learning: Deep learning is machine learning that uses many-layered neural networks to learn complex patterns, and it is the approach behind most modern AI breakthroughs.
Neural network: A neural network is a computing system loosely inspired by the brain, made of layers of connected nodes that adjust their strengths as they learn from data.