Emergent Capabilities

Prompt Engineering

The practice of designing and optimising input prompts to elicit desired outputs from large language models.

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.

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.

Specialised hardware designed to speed up AI computations, including GPUs, TPUs, and custom AI chips.

A semiconductor designed specifically for AI and machine learning computations, optimised for parallel processing and matrix operations.

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

Google's custom-designed application-specific integrated circuit for accelerating machine learning workloads.

A graphical plot illustrating the diagnostic ability of a binary classifier as its discrimination threshold is varied.

The process of using a trained AI model to make predictions or decisions on new, unseen data.

A thought experiment by John Searle arguing that executing a program cannot give a computer genuine understanding or consciousness.

Machine learning techniques optimised to run on microcontrollers and extremely resource-constrained embedded devices.