AI Concept Map
The Building Blocks of Modern AI
Click any concept to expand its explanation
Expand All
Collapse All
Modern AI Systems
LAYER 01
Primitives
▼
Prompt
Prompt
Temperature
Context Window
inference parameters
LLM
Large Language Model
Transformer
MoE
model architectures
Embedding
Embedding
Vector Space
Cosine Similarity
semantic math foundations
LAYER 02
Compositions
▼
Function Calling
MCP
Vector Database
RAG
Guardrails
Multimodal
Prompt Caching
LAYER 03
Model Adaptation
▼
SFT
LoRA
RLHF / DPO
Knowledge Distillation
These adapt a pre-trained base model, not training from scratch. Pre-training costs tens of millions of dollars; only a handful of labs do it.
LAYER 04
Deployment
▼
Agent
Fine-tuning
Framework
Evals
Red Teaming
Small Model
LAYER 05
Emerging
▼
Multi-Agent Systems
Synthetic Data
Interpretability
Thinking Model
Test-Time Compute
Select a concept
Click any node to see its explanation here