Definition
Few-shot prompting is a technique in which you include a small number of worked examples — typically two to a handful — directly inside the prompt before posing the actual question. Each example pairs an input with its desired output, demonstrating the pattern you want. The model then generalises from those demonstrations to handle a new, unseen input, all without any change to its underlying weights.
How it works
Because the examples live in the prompt rather than in training, few-shot prompting is a form of in-context learning: the model learns the task at inference time from the context window alone. A sentiment-classification prompt, for instance, might show three correctly labelled sentences (positive, negative, neutral) and then ask the model to label a fourth. Seeing the format and the decision boundary, the model usually produces output matching the demonstrated style.
When to use it
Few-shot prompting shines when a task is hard to describe in words but easy to show, or when you need output in a strict, consistent format. It generally outperforms zero-shot prompting on benchmarks, though not always — for very capable models on simple tasks, examples can add cost without improving results. The minimal version, supplying exactly one example, is one-shot prompting.
For sovereign Bitcoiners running smaller, self-hosted models, few-shot prompting is especially valuable: a compact local model that struggles with a bare instruction often performs reliably once shown a few examples. It is a foundational tool within broader prompt engineering practice.
In Simple Terms
Few-shot prompting is a technique in which you include a small number of worked examples — typically two to a handful — directly inside the…