📖 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.
1.6K+475 7d - AI agent
A model wrapped in a loop that can use tools and take multi-step actions toward a goal.
372-15 7d - Benchmark
A standardized test set used to compare model capability.
261-53 7d - Inference
Running a trained model to get outputs — what you pay for per token.
235-9 7d - Token
The chunk of text (≈¾ of a word) that models read and generate, and that APIs bill by.
161-28 7d - Attention
The mechanism that lets a model weigh which parts of the input matter for each output.
105-17 7d - Fine-tuning
Further training a model on your own examples to specialize its behavior.
103-20 7d - Multimodal
Models that handle more than text — images, audio, video — in and/or out.
99-8 7d - Embedding
A list of numbers representing meaning, so similar texts land near each other.
66-17 7d - Transformer
The neural architecture behind modern AI, built on the attention mechanism.
65-31 7d - Diffusion model
The image/video generation technique that denoises random noise into pictures.
57-9 7d - MCP (Model Context Protocol)
An open standard for connecting AI assistants to tools and data sources.
47-18 7d - RAG (Retrieval-Augmented Generation)
Fetching relevant documents and feeding them to the model so answers cite real data.
36-11 7d - Hallucination
When a model states something false with full confidence.
23+2 7d - LoRA (Low-Rank Adaptation)
A cheap fine-tuning method that trains small adapter matrices instead of the whole model.
20-10 7d - Tool use (function calling)
Letting a model call external functions/APIs with structured arguments.
17+2 7d - Context window
How much text a model can consider at once, measured in tokens.
11-1 7d - Guardrails
Checks around a model that block unsafe or invalid inputs and outputs.
9-3 7d - Open weights
Models whose trained parameters are downloadable and self-hostable.
60 7d - Reasoning model
A model trained to "think" in long internal chains before answering.
2-5 7d - Prompt engineering
Crafting inputs that reliably get the output you want from a model.
1-1 7d - Vector database
A database optimized for finding the nearest embeddings to a query vector.
quiet00 7d