Ask AI

AI & LLM Glossary

Plain-English definitions of the AI terms you'll see thrown around. From attention to zero-shot, with links to the models and tools where each concept matters. Guides, prompts and comparisons live in our collection of AI learning resources.

Core AI terms

  • LLM (Large Language Model)An AI model trained on huge amounts of text that can read and generate natural language. ChatGPT, Claude and Gemini are all LLMs.
  • Foundation modelA large general-purpose AI model (like GPT-4 or Claude Sonnet) that's been trained on broad data and can be adapted for many tasks.
  • TransformerThe neural network architecture introduced in 2017 that powers every modern LLM - ChatGPT, Claude, Gemini, all of it.
  • TokenThe unit AI models read and write in. Roughly 4 characters or 0.75 words. Pricing and context windows are measured in tokens.
  • Context windowHow much text an AI can process at once, measured in tokens. A bigger context window means analysing longer documents, longer chats, and more complex tasks.
  • MultimodalA model that can handle multiple input types - Text, images, audio, video - Not just text.

Prompting terms

  • PromptWhat you type to an AI. The art of writing effective prompts is called prompt engineering.
  • Prompt engineeringThe discipline of writing AI prompts that consistently produce good answers. Includes techniques like few-shot, CoT, and role assignment.
  • System promptAn instruction sent before your message that shapes the AI's persona, tone and constraints for the rest of the conversation.
  • Chain of thoughtA prompting technique where the AI explains its reasoning step by step before giving a final answer - Usually more accurate than direct answers.
  • Zero-shotAsking the AI to do something without giving it any examples. The opposite of few-shot prompting.
  • TemperatureA setting that controls AI creativity. 0 = deterministic and predictable. 1 = more varied, creative, sometimes unhinged.

Models and providers

  • GPTGenerative Pre-trained Transformer. The model architecture and naming convention used by OpenAI for ChatGPT.
  • ClaudeAnthropic's family of AI models, known for thoughtful, careful, long-form writing. Available via claude.ai or AskAI.free.
  • GeminiGoogle's flagship AI model family. Gemini 2.5 Pro leads on long context (2M tokens) and multimodal tasks; Gemini 2.0 Flash is the fast, free-tier option.
  • OpenAIThe AI lab behind ChatGPT and the GPT family of models. Founded 2015, now valued in the hundreds of billions.
  • AnthropicThe AI lab behind Claude. Founded by ex-OpenAI researchers focused on AI safety. Major investors include Amazon and Google.
  • SonnetAnthropic's mid-tier Claude model - The flagship product line that most people use day-to-day.

Accuracy and safety

  • HallucinationWhen an AI confidently states something false. The biggest reliability issue with LLMs - Understanding hallucinations helps you use AI more safely.
  • RAGGrounding AI answers in your own documents - Retrieve relevant context first, then generate the answer. The key solution to knowledge cutoffs.
  • Knowledge cutoffThe date after which the AI doesn't know about world events. ChatGPT, Claude and Gemini all have one - For current events use Perplexity.
  • JailbreakA prompt that tricks an AI into ignoring its safety training and doing something it normally refuses.
  • Constitutional AIAnthropic's training method where Claude is trained against a written 'constitution' of values - Rather than ad-hoc human feedback for every example.
  • Reasoning modelAn AI model that explicitly 'thinks' before answering by generating a long chain of thought. Better at math, code and logic - Slower than chat models.

A

  • AI agent
    An AI system that can take actions on your behalf - Calling tools, browsing the web, writing files - Not just answering with text.
  • Alignment
    The research problem of making AI systems do what humans actually want - Not just what we ask for literally.
  • Attention
    The mathematical mechanism that lets transformers focus on different parts of the input when generating each output token.
  • Anthropic
    The AI lab behind Claude. Founded by ex-OpenAI researchers focused on AI safety. Major investors include Amazon and Google.

B

  • BERT
    An older Google model (2018) that was a major step before LLMs. Today mostly used inside Google Search, not for chat.

C

  • Chain of thought
    A prompting technique where the AI explains its reasoning step by step before giving a final answer - Usually more accurate than direct answers.
  • ChatGPT
    OpenAI's flagship AI chat product. Powered by the GPT family of models (4o, 4.1, o3, etc.).
  • Claude
    Anthropic's family of AI models, known for thoughtful, careful, long-form writing. Available via claude.ai or AskAI.free.
  • Constitutional AI
    Anthropic's training method where Claude is trained against a written 'constitution' of values - Rather than ad-hoc human feedback for every example.
  • Context window
    How much text an AI can process at once, measured in tokens. A bigger context window means analysing longer documents, longer chats, and more complex tasks.

E

  • Embedding
    A list of numbers that represents a piece of text in a way that lets computers measure 'similarity' mathematically. The foundation of semantic search and RAG.

F

  • Fine-tuning
    Training an existing model on additional examples to specialise it for a domain - Like making ChatGPT write in your company's voice.
  • Foundation model
    A large general-purpose AI model (like GPT-4 or Claude Sonnet) that's been trained on broad data and can be adapted for many tasks.

G

  • GPT
    Generative Pre-trained Transformer. The model architecture and naming convention used by OpenAI for ChatGPT.
  • Gemini
    Google's flagship AI model family. Gemini 2.5 Pro leads on long context (2M tokens) and multimodal tasks; Gemini 2.0 Flash is the fast, free-tier option.

H

  • Hallucination
    When an AI confidently states something false. The biggest reliability issue with LLMs - Understanding hallucinations helps you use AI more safely.

I

  • Inference
    Running a trained model to get an answer. Distinct from training, which is teaching the model in the first place.

J

  • Jailbreak
    A prompt that tricks an AI into ignoring its safety training and doing something it normally refuses.

K

  • Knowledge cutoff
    The date after which the AI doesn't know about world events. ChatGPT, Claude and Gemini all have one - For current events use Perplexity.

L

  • LLM (Large Language Model)
    An AI model trained on huge amounts of text that can read and generate natural language. ChatGPT, Claude and Gemini are all LLMs.

M

  • MCP (Model Context Protocol)
    Anthropic's open standard for connecting AI assistants to data sources and tools. Like USB-C for AI.
  • Multimodal
    A model that can handle multiple input types - Text, images, audio, video - Not just text.

N

  • Neural network
    The mathematical structure that LLMs are built from - Billions of simple equations connected together to learn patterns.

O

  • OpenAI
    The AI lab behind ChatGPT and the GPT family of models. Founded 2015, now valued in the hundreds of billions.

P

  • Parameter
    A single number inside a neural network. LLMs have billions of parameters - The bigger the count, the more capable (usually).
  • Prompt
    What you type to an AI. The art of writing effective prompts is called prompt engineering.
  • Prompt engineering
    The discipline of writing AI prompts that consistently produce good answers. Includes techniques like few-shot, CoT, and role assignment.

R

  • RAG
    Grounding AI answers in your own documents - Retrieve relevant context first, then generate the answer. The key solution to knowledge cutoffs.
  • Reasoning model
    An AI model that explicitly 'thinks' before answering by generating a long chain of thought. Better at math, code and logic - Slower than chat models.
  • Reinforcement learning (RL)
    A training technique where the AI improves by trial and error, getting rewards for good outputs. The 'F' in RLHF.

S

  • Sonnet
    Anthropic's mid-tier Claude model - The flagship product line that most people use day-to-day.
  • System prompt
    An instruction sent before your message that shapes the AI's persona, tone and constraints for the rest of the conversation.

T

  • Temperature
    A setting that controls AI creativity. 0 = deterministic and predictable. 1 = more varied, creative, sometimes unhinged.
  • Token
    The unit AI models read and write in. Roughly 4 characters or 0.75 words. Pricing and context windows are measured in tokens.
  • Tokenizer
    The component that converts text into tokens (and back). Different models use different tokenizers, which is why a sentence has a different token count in GPT vs Claude.
  • Training data
    The text an LLM is taught on. Typically trillions of tokens scraped from the web, books, code repos and more.
  • Transformer
    The neural network architecture introduced in 2017 that powers every modern LLM - ChatGPT, Claude, Gemini, all of it.
  • Tool use (function calling)
    When an AI model can call external functions - Search, calculator, database - Instead of just generating text.

V

  • Vision model
    An AI model that can understand images, not just text. Most modern flagship LLMs are now vision models.

Z

  • Zero-shot
    Asking the AI to do something without giving it any examples. The opposite of few-shot prompting.