🔮The Codex
Few-Shot Learning
Teaching AI to perform a task by showing it just a few examples in the prompt.
📖 Apprentice Explanation
Few-shot learning is when you show an AI a few examples of what you want before asking it to do the task. It's like showing someone three example emails before asking them to write one in the same style.
🧙 Archmage Notes
In-context few-shot learning leverages the model's ability to pattern-match from examples in the prompt. Performance depends on example quality, ordering, and format. Typically 3-5 examples are optimal for most tasks.