AI glossary / How it works
Transfer learning
Reusing what a model learned on one task as a head start on another.
Think of it as: Knowing how to ride a bike makes learning a motorbike easier.
More words in How it works
- TransformerThe model design, introduced in 2017, behind nearly all modern language AI. It's the T in GPT.
- Unsupervised learningTraining where the AI finds patterns in data on its own, without being given the right answers.
- WeightsThe numbers inside a model that hold everything it has learned. Share the weights and you've shared the model.
- World modelAn AI's internal sense of how the world works, which lets it predict what will happen next. Seen as important for robots.
- Agent harnessThe software wrapped around a model that lets it act as an agent. It manages the to-do list, the tools, the memory and the permissions.