Transformer
Working knowledgeEvergreen Landmarks
The transformer is a neural network architecture that relies entirely on self-attention to process sequential data in parallel rather than one element at a time. It was introduced in the 2017 research paper "Attention Is All You Need". Removing the sequential bottleneck is what made training on very large text collections practical, and the transformer is now the foundation of modern large language models and much of computer vision.
In practice
No buyer chooses a transformer, but every buyer feels its consequences: it is why the frontier models converged on one design, why scale bought capability, and why compute became the binding constraint on progress. When a vendor claims a novel architecture, ask what it does that a transformer cannot.