AI Terms
A plain-English AI glossary
Key terms you'll encounter across the world of AI and automation.
- Prompt Engineering
- The practice of designing and refining inputs (prompts) to get the most useful output from an AI model.
- Few-shot Prompting
- Giving an AI model a handful of examples within the prompt to guide its responses.
- Chain-of-Thought (CoT)
- Prompting a model to reason step by step before producing a final answer.
- Fine-tuning
- Further training a pre-trained model on a specific dataset to specialise its behaviour.
- LLM
- Large Language Model — a model trained on vast text data to understand and generate language.
- Hallucination
- When an AI confidently produces information that is factually incorrect or fabricated.
- Token
- A chunk of text (word or sub-word) that a language model processes as a single unit.
- RAG
- Retrieval-Augmented Generation — grounding model output in retrieved documents for accuracy.
- AGI
- Artificial General Intelligence — hypothetical AI with human-level ability across any task.