🔮The Codex
Transformer
The neural network architecture behind modern AI language models.
📖 Apprentice Explanation
A transformer is the engine that powers AI chatbots. It's a special design that lets AI understand how words relate to each other in a sentence, even if they're far apart.
🧙 Archmage Notes
Introduced in 'Attention Is All You Need' (2017), transformers use self-attention mechanisms to process sequences in parallel. Variants include encoder-only (BERT), decoder-only (GPT), and encoder-decoder (T5) architectures.