AI Glossary
Key AI terms and concepts explained in plain language. Bookmark this page for reference.
A
Agentic AI
AI systems that can take autonomous actions to accomplish goals, make decisions, and interact with external systems without constant human intervention. Examples include AI agents that can browse the web, write code, or manage workflows.
API (Application Programming Interface)
A set of protocols that allows different software applications to communicate. In AI, APIs let developers integrate AI capabilities (like ChatGPT) into their own applications.
Artificial General Intelligence (AGI)
Hypothetical AI that can understand, learn, and apply intelligence to any intellectual task that a human can. Current AI is "narrow" (good at specific tasks), not general.
C
Chain of Thought (CoT)
A prompting technique where you ask the AI to explain its reasoning step-by-step. This often improves accuracy on complex problems by forcing the model to "think through" the solution.
Chatbot
A software application that simulates human conversation through text or voice. Modern AI chatbots use large language models to generate human-like responses.
Computer Vision
AI technology that enables computers to interpret and understand visual information from images and videos. Used in applications like facial recognition, object detection, and medical imaging.
Context Window
The maximum amount of text (measured in tokens) that an AI model can process at once. Larger context windows allow models to reference more information in a single conversation.
D
Deep Learning
A subset of machine learning using neural networks with many layers. It's the technology behind most modern AI breakthroughs, including image recognition and language models.
Diffusion Model
A type of generative AI that creates images by gradually removing noise from random data. Used by tools like Midjourney, DALL-E, and Stable Diffusion.
E
Embeddings
Numerical representations of data (text, images, etc.) that capture semantic meaning. Similar concepts have similar embeddings, enabling semantic search and RAG applications.
Edge AI
AI processing that happens locally on a device (phone, camera, sensor) rather than in the cloud. Provides faster responses and works without internet connectivity.
F
Fine-tuning
The process of further training a pre-trained AI model on specific data to customize it for a particular task or domain. Common for adapting LLMs to specialized use cases.
Foundation Model
Large AI models trained on broad data that can be adapted to many different tasks. Examples include GPT-4, Claude, and Llama. They serve as the "foundation" for various applications.
G
Generative AI
AI that creates new content—text, images, audio, video, or code—based on patterns learned from training data. ChatGPT and Midjourney are examples of generative AI.
GPT (Generative Pre-trained Transformer)
A type of large language model architecture developed by OpenAI. The "T" stands for Transformer, the neural network architecture that powers most modern LLMs.
Grounding
Connecting AI outputs to real-world data or facts to improve accuracy and reduce hallucinations. RAG is a common grounding technique.
H
Hallucination
When an AI generates false or fabricated information that sounds plausible but isn't true. A significant challenge with LLMs that can be mitigated through RAG and careful prompting.
I
Inference
The process of using a trained AI model to make predictions or generate outputs. When you ask ChatGPT a question, the response is generated through inference.
L
Large Language Model (LLM)
AI models trained on massive amounts of text data that can understand and generate human language. GPT-4, Claude, and Gemini are all LLMs.
Latency
The time delay between sending a request to an AI system and receiving a response. Lower latency means faster responses, which is important for real-time applications.
M
Machine Learning (ML)
A type of AI where computers learn patterns from data rather than being explicitly programmed. ML powers recommendations, predictions, and pattern recognition.
Model
In AI, a model is a program that has been trained on data to recognize patterns and make predictions. Different models are optimized for different tasks.
Multimodal AI
AI that can process and generate multiple types of content—text, images, audio, video—within the same model. GPT-4V and Gemini are multimodal models.
N
Natural Language Processing (NLP)
AI technology that enables computers to understand, interpret, and generate human language. Powers chatbots, translation, sentiment analysis, and text summarization.
Neural Network
A computing system inspired by the human brain, consisting of interconnected nodes (neurons) that process information. The foundation of modern deep learning.
P
Prompt
The input text you give to an AI model to get a response. The quality of your prompt significantly affects the quality of the AI's output.
Prompt Engineering
The practice of crafting effective prompts to get better results from AI models. Includes techniques like few-shot examples, chain of thought, and role-playing.
R
RAG (Retrieval-Augmented Generation)
A technique that enhances LLM responses by first retrieving relevant information from a knowledge base, then using that information to generate more accurate, grounded responses.
Reinforcement Learning from Human Feedback (RLHF)
A training technique where human feedback is used to improve AI behavior. This is how models like ChatGPT are trained to be helpful and avoid harmful outputs.
S
Semantic Search
Search that understands the meaning and intent behind queries rather than just matching keywords. Uses embeddings to find conceptually similar content.
System Prompt
Hidden instructions given to an AI model that define its behavior, personality, or capabilities. Sets the context before the user's conversation begins.
T
Temperature
A parameter that controls how random or creative an AI's responses are. Higher temperature = more creative/random. Lower temperature = more focused/deterministic.
Token
The basic unit of text that AI models process—roughly 4 characters or 3/4 of a word in English. Pricing and context limits are usually measured in tokens.
Transformer
The neural network architecture behind modern LLMs. Introduced in 2017, it uses "attention" mechanisms to understand relationships between words in text.
V
Vector Database
A database optimized for storing and searching embeddings (vectors). Essential for RAG applications and semantic search. Examples include Pinecone and Weaviate.
Z
Zero-shot Learning
When an AI performs a task without any specific examples—just from its general training. Contrasts with "few-shot" learning where you provide examples in the prompt.