• A machine-learning technique in which a large language model (LLM) is given a single example of a task before being asked to perform that same task on new, unseen data. This approach allows models to quickly adapt to new tasks with minimal training data.

1. Related terms: Few-shot prompting · Zero-shot prompting · Prompt engineering · Machine learning
2. Previous term: One-based indexing
3. Next term: One-time password
4. Random term: Spoofing (webglossary.info/random 🎲)