Simple visuals + everyday analogies that explain AI concepts to everyone — whether you write code or have never opened a terminal.
If this helps you finally "get" AI — drop a ⭐. It helps more people find it.
AI is everywhere, but most explanations are either too technical (walls of math) or too fluffy (no real understanding).
This repo sits in the middle. Every concept gets:
- 🧒 An "Explain Like I'm 5" analogy— the one-liner you'll actually remember - 🖼️ A simple diagram— see the idea, don't just read it - 🔧 "How it actually works"— for when you're ready to go deeper - 🌍 A real-world example— where you've already seen it in action
No PhD required. No prior coding needed. Just curiosity.
| # | Concept | One-liner |
|---|---|---|
| 1 | ||
🔤 Token📍 Embedding🕸️ Neural Network🏋️ Training vs Inference💬 Prompt🪟 Context Window🎯 Fine-tuning📖 RAG (Retrieval-Augmented Generation)🌀 Hallucination| # | Concept | One-liner | |---|---|---| | 11 | |
👀 Attention🌡️ Temperature🔗 Chain of Thought| # | Concept | One-liner | |---|---|---| | 15 | |
⚡ GPU📏 Overfitting🎛️ Parameters / Weights🏛️ Foundation Model🗜️ Quantization| # | Concept | One-liner | |---|---|---| | 21 | |
doesthings, not just chats.🗄️ Vector Database🎨 Diffusion Model🎭 GAN🪪 System Prompt🌈 Multimodal🛠️ Tool Calling| # | Concept | One-liner | |---|---|---| | 28 | |
📅 Knowledge Cutoff🕵️ Prompt Injection🧭 Alignment & Guardrailsnotto do.🌅 AGI
flowchart LR
A[💬 Your Prompt] --> B[🔤 Split into Tokens]
B --> C[📍 Turned into Embeddings]
C --> D[🕸️ Neural Network<br/>the LLM]
D --> E[🪟 Limited by<br/>Context Window]
D --> F[📝 Generates Answer]
F -.->|sometimes| G[🌀 Hallucination]
H[(📚 Your Documents)] -->|RAG| D
I[🎯 Fine-tuning] -.->|specializes| D
style A fill:#dbeafe,stroke:#3b82f6
style D fill:#fef3c7,stroke:#f59e0b
style F fill:#dcfce7,stroke:#22c55e
style G fill:#fee2e2,stroke:#ef4444
Read it in orderif you're brand new — each concept builds on the last.Jump aroundif you already know the basics.
- Pick a concept from the table above. - Read the analogy. Look at the diagram.
- Curious? Read "How it actually works."
- Found it useful? Star the repo⭐ and share it.
Know a concept we're missing? Have a better analogy? We'd love your help.
See CONTRIBUTING.md for the simple template — adding a concept takes about 10 minutes.
Good first additions: Reinforcement Learning, Mixture of Experts (MoE), MCP, Deepfake, Backpropagation, Loss Function, Zero-shot vs Few-shot, Speech-to-Text / Text-to-Speech, Open vs Closed Models, AI Ethics.
MIT — free to use, share, remix, and teach with. Attribution appreciated.
Made for curious humans. 🧠
If this made AI click for you, the best thank-you is a ⭐.