⚙️ Under the hood
Transformer
The architecture behind almost all modern language models, introduced in 2017. Its core idea is attention.
💭 Imagine …
Instead of reading text word by word as if through a straw, the transformer sees everything at once and decides what matters for what.
🔎 Example
The “T” in GPT stands for transformer.
🎯 Why it matters
Transformers can be trained massively in parallel. That made the current AI boom possible.
🎓 Prefer step by step?
The AI Literacy course: 6 short modules with quizzes, a solid foundation in about 60 minutes.