Prompt Engineering

Few-Shot Prompting

A technique where a language model is given a small number of examples within the prompt to guide its response pattern.

Zero-Shot Prompting

Querying a language model to perform a task it was not explicitly trained on, without providing any examples in the prompt.

Chain-of-Thought Prompting

A prompting technique that encourages language models to break down reasoning into intermediate steps before providing an answer.

In-Context Learning

The ability of large language models to learn new tasks from examples provided within the input prompt without parameter updates.

Few-Shot Learning

A machine learning approach where models learn to perform tasks from only a small number of labelled examples, often achieved through in-context learning in large language models.

Zero-Shot Learning

The ability of AI models to perform tasks they were not explicitly trained on, using generalised knowledge and instruction-following capabilities.

Emergent Capabilities

Abilities that appear in large language models at certain scale thresholds that were not present in smaller versions, such as in-context learning and complex reasoning.

Tool Use in AI

The capability of AI agents to invoke external tools, APIs, databases, and software applications to accomplish tasks beyond the model's intrinsic knowledge and abilities.

System Prompt

An initial instruction set provided to a language model that defines its persona, constraints, output format, and behavioural guidelines for a given session or application.

The ratio of true positive predictions to all actual positive instances, measuring completeness of positive identification.

The creation of artificially produced datasets that mimic the statistical properties of real-world data, used for training AI models while preserving privacy.

Techniques for combining the weights and capabilities of multiple fine-tuned models into a single model without additional training, creating versatile multi-capability systems.

A degradation phenomenon where AI models trained on AI-generated data progressively lose diversity and accuracy, converging toward a narrow distribution of outputs.

Safety mechanisms and constraints implemented around AI systems to prevent harmful, biased, or policy-violating outputs while preserving useful functionality.

A machine learning approach where models are trained across decentralised devices without sharing raw data, preserving privacy.

Middleware that manages routing, fallback, load balancing, and model selection across multiple AI providers to optimise cost, latency, and output quality.

A technique where a smaller, simpler model is trained to replicate the behaviour of a larger, more complex model.