Learning Path168 concepts
Start here →Ten sections from first principles to advanced specialisms, curated in the right order so each idea builds on the last.
Foundational
Start here. These concepts are the prerequisites for everything else.
Core
The essential ideas that define modern AI - what most people mean when they say AI.
LLM Architectures
27 conceptsThe building blocks inside large language models - how they store knowledge, process text, and generate responses.
Explore →
Training & Alignment
29 conceptsHow models are built, fine-tuned, and taught to behave the way people actually want them to.
Explore →
Generative & Multimodal
17 conceptsAI that creates images, audio, and video - and systems that reason across multiple types of input at once.
Explore →
Agentic AI
13 conceptsAI that plans, acts, and uses tools autonomously - moving beyond question-and-answer into doing.
Explore →
AI Safety & Alignment
12 conceptsThe field dedicated to making AI systems behave reliably, honestly, and without causing unintended harm.
Explore →
Advanced
Deeper specialisms for engineers, researchers, and the genuinely curious.
MLOps & Infrastructure
17 conceptsThe engineering discipline of running AI in production - reliably, efficiently, and at scale.
Explore →
Reinforcement Learning & Robotics
17 conceptsAI that learns by doing - and the systems that let it operate in the physical world.
Explore →
Graph Neural Networks
12 conceptsA class of models built for data with relationships - social networks, molecules, maps, and knowledge graphs.
Explore →
Specialized Domains
14 conceptsAI applied to medicine, science, audio, and other fields where domain knowledge changes everything.
Explore →
Looking for a specific term? Browse all concepts or use the search box there to find it directly.