01 Wiki
The AI wiki, minus the jargon
Twenty-four concepts that explain 90% of every conversation about artificial intelligence. Each with an analogy, the technical detail, and an example.
-
LLM (large language model)
The engine behind ChatGPT, Claude and Gemini.
-
Tokens
The pieces AI breaks all text into.
-
Context window
The model's working memory: if it doesn't fit, it doesn't exist.
-
Temperature
The dial that controls how daring the model gets.
-
MCP (Model Context Protocol)
The USB-C of AI: one standard connector for tools and data.
-
RAG (retrieval-augmented generation)
The model stops memorizing and starts looking things up.
-
Fine-tuning
Turning a generalist model into your specialist.
-
AI agents
From answering questions to completing missions.
-
Hallucinations
When AI answers with total confidence… and is making it up.
-
System prompt
The invisible instructions the AI receives before yours.
-
Chain of thought
Asking the AI to think out loud before answering.
-
Embeddings
Turning meaning into coordinates a machine can compare.
-
Multimodal AI
Models that don't just read: they also see, listen and draw.
-
Parameters
The millions of internal “dials” where everything learned lives.
-
Open vs. closed models
Who gets to download, modify and run the model?
-
Prompt injection
When someone hides commands inside the text the AI is about to read.
-
Transformer
The architecture that made everything else possible.
-
Training
How a model goes from knowing nothing to talking about everything.
-
Inference
The moment the model works for you.
-
Benchmarks
The exams used to compare models.
-
AGI (artificial general intelligence)
The hypothetical AI capable of any human intellectual task.
-
Knowledge cutoff
How far the model knows what's happening in the world.
-
Tool use (function calling)
When the model stops just talking and starts pressing buttons.
-
Guardrails
The rules that keep the assistant from going off the road.