Quick lookup of AI terms in plain language
Every term: short definition → real example → when to use. No translation-ese, no fluff.
✨ Start here
Foundational terms to read first if you're new to AI.
What is Artificial Intelligence (AI)?
The branch of computer science that builds machines capable of mimicking human reasoning, learning, and decision-making.
What is an LLM?
Large Language Models — AI systems trained on massive text corpora that can understand and generate human-like text. ChatGPT, Claude, and Gemini are all LLMs.
What is a Token (in LLMs)?
The smallest unit an LLM processes — not a word, but a fragment. Tokens determine API cost and context limits.
All terms
No matching terms
Try removing filters, or suggest a term you want explained.
What is a Context Window?
The maximum amount of text an LLM can 'remember' in a single pass. It decides how much information you can fit into a prompt.
What is a Diffusion Model?
A class of AI model that generates images by gradually denoising — the technology behind Midjourney, Stable Diffusion, and DALL-E.
What is a Foundation Model?
A large AI model trained on broad, general-purpose data — used as a base to fine-tune for many different tasks.
What is a GPU? Why does AI need GPUs?
Graphics cards — hardware that accelerates parallel computation, the backbone of every modern AI model.
What is a Neural Network?
A computational structure inspired by how neurons in the brain connect — the foundation of modern deep learning.
What is a System Prompt?
An instruction block that 'configures' an LLM before the user starts chatting — it sets the AI's persona, format, and limits.
What is a Token (in LLMs)?
The smallest unit an LLM processes — not a word, but a fragment. Tokens determine API cost and context limits.
What is a Transformer?
A neural network architecture introduced in 2017, the foundation behind every modern LLM (GPT, Claude, Gemini).
What is a Vector Database?
A type of database specialized in storing and quickly searching vector embeddings — the foundation for RAG and semantic search.
What is AI Alignment?
The research field that works to keep AI acting in line with human intent and values — even as systems grow more powerful.
What is AI Hallucination?
When an LLM confidently produces information that is factually wrong — fabricated stats, fake citations, made-up events.
What is an AI Agent?
An AI system that can plan, use tools, and take multi-step actions to complete a goal — not just answer a single question.
What is an AI API? How to use LLM APIs
How developers call AI models from code — how the Claude API, OpenAI API, and Gemini API work.
What is an Embedding?
A way to represent text, images, or anything else as numerical vectors so machines can compare meaning.
What is an LLM?
Large Language Models — AI systems trained on massive text corpora that can understand and generate human-like text. ChatGPT, Claude, and Gemini are all LLMs.
What is Artificial Intelligence (AI)?
The branch of computer science that builds machines capable of mimicking human reasoning, learning, and decision-making.
What is Chain of Thought (CoT)?
A prompting technique that asks an LLM to 'think step by step' before answering — significantly boosts accuracy on hard problems.
What is Computer Vision?
The branch of AI that lets machines 'see' and interpret images and video — from face recognition to self-driving cars.
What is Deep Learning?
A branch of machine learning that uses many-layered neural networks to learn from complex data like images, audio, and text.
What is Fine-tuning?
The process of further training an existing AI model on your data so it gets better at a specific task or matches a specific style.
What is Function Calling (Tool Use)?
The ability for an LLM to call external functions or APIs to fetch real data — not just generate text from memory.
What is Generative AI?
A type of AI that doesn't just classify or predict — it CREATES new content: text, images, video, code, and music.
What is Inference (AI Inference)?
The process of running a trained AI model to serve users — the main driver of cost and latency in any AI product.
What is Jailbreak (AI)?
Techniques that bypass an LLM's safety guardrails to make it do something it would normally refuse.
What is LoRA?
Low-Rank Adaptation — a technique for fine-tuning large models that saves 100-1000× the resources of full fine-tuning.
What is Machine Learning?
An approach to AI where computers learn patterns from data instead of being programmed step by step.
What is MCP (Model Context Protocol)?
An open standard from Anthropic that lets LLMs connect to tools, databases, and apps through a single unified protocol.
What is Multimodal AI?
AI that can handle multiple data types at once — text, images, audio, video — not just text like older LLMs.
What is NLP (Natural Language Processing)?
The branch of AI that helps machines read, understand, and produce human language — from Google Translate to ChatGPT.
What is Prompt Engineering?
The craft of writing instructions that get AI models to produce better, more reliable output.
What is Quantization?
A technique for reducing numeric precision in AI models so they run faster and use less RAM — at the cost of a bit of accuracy.
What is RAG (Retrieval-Augmented Generation)?
A technique that lets an LLM look up your documents before answering — reducing hallucinations and grounding answers in real data.
What is RLHF?
Reinforcement Learning from Human Feedback — a technique that uses human feedback to teach LLMs to answer in a way that matches human preferences.
What is Training?
The process of teaching an AI model by showing it millions or billions of examples and adjusting its internal parameters.