TECHNOLOGY
Transformer Architecture
The 2017 neural network architecture, built around self-attention, that replaced recurrent networks for sequence modeling and became the substrate of every large language model since.
The transformer is a neural network architecture introduced in the 2017 paper "Attention Is All You Need" by Vaswani and colleagues at Google Brain. Its distinguishing mechanism — self-attention — allows each position in a sequence to weight its relationship to every other position directly, replacing the sequential processing of earlier recurrent neural networks. Every major LLM of the current era (GPT, Claude, Gemini, LLaMA) is a transformer variant.
In The You On AI Field Guide
The transformer is the enabling technical precondition of the You On AI Field Guide's subject matter. The jump from pre-2017 language models (recurrent, slower to train, shorter-context) to post-2017 (transformer-based, parallelizable, scalable to internet-sized corpora) was what made the current LLM era possible.
The Orange Pill Asimov volume uses the transformer sparingly — Asimov's framing is more about neural networks as a category — but the implicit comparison is between the positronic brain's rule-following and the transformer's distribution-learning. The transformer is the thing that is neither designed nor inspectable but nevertheless works at scale.