📖 AI Glossary
22 key AI terms in plain English — each links to the related concepts so you can follow a thread instead of memorizing jargon. JSON is available at /api/glossary.
- Large Language Model (LLM)
A neural network trained on huge text corpora to predict and generate language.
1.3K-476 7d - AI agent
A model wrapped in a loop that can use tools and take multi-step actions toward a goal.
478-74 7d - Inference
Running a trained model to get outputs — what you pay for per token.
235-87 7d - Benchmark
A standardized test set used to compare model capability.
219-115 7d - Token
The chunk of text (≈¾ of a word) that models read and generate, and that APIs bill by.
170-124 7d - Attention
The mechanism that lets a model weigh which parts of the input matter for each output.
110-44 7d - Diffusion model
The image/video generation technique that denoises random noise into pictures.
83-11 7d - Multimodal
Models that handle more than text — images, audio, video — in and/or out.
77-19 7d - Transformer
The neural architecture behind modern AI, built on the attention mechanism.
73-24 7d - Fine-tuning
Further training a model on your own examples to specialize its behavior.
71-44 7d - MCP (Model Context Protocol)
An open standard for connecting AI assistants to tools and data sources.
68-2 7d - Embedding
A list of numbers representing meaning, so similar texts land near each other.
48-21 7d - LoRA (Low-Rank Adaptation)
A cheap fine-tuning method that trains small adapter matrices instead of the whole model.
31-3 7d - Guardrails
Checks around a model that block unsafe or invalid inputs and outputs.
21+3 7d - Hallucination
When a model states something false with full confidence.
160 7d - RAG (Retrieval-Augmented Generation)
Fetching relevant documents and feeding them to the model so answers cite real data.
14-19 7d - Context window
How much text a model can consider at once, measured in tokens.
9-2 7d - Tool use (function calling)
Letting a model call external functions/APIs with structured arguments.
9-5 7d - Open weights
Models whose trained parameters are downloadable and self-hostable.
8-1 7d - Reasoning model
A model trained to "think" in long internal chains before answering.
8+4 7d - Prompt engineering
Crafting inputs that reliably get the output you want from a model.
30 7d - Vector database
A database optimized for finding the nearest embeddings to a query vector.
2+2 7d