Key facts
- Architecture
- Transformer
- Training
- Next-token prediction
Forest Trails
- Built with
- Examples
- Powers
Referencing articles
The rise of large language models
An LLM is a Transformer trained on a lot of text. The interesting behaviour appears only above a certain scale.
Continue reading
Meta after Facebook
Meta operates the largest social platforms in the world — and quietly ships some of the most influential open-weight AI models.
Continue reading
What is a Transformer?
The Transformer replaced recurrence with attention — and unlocked models that scale with data and compute in ways nothing else did.
Continue reading