The AI Learning Hub Journal
◆ Free course · 4 modules · 27 lessons

AI Deep Dive

Practitioner-level AI — architecture, training, agent design, and the frontier for those who want the full picture

Read it in the library →
Module 1 · 6 lessons

The AI Story

The technical and historical arc of AI — paradigm shifts, scaling laws, the compute stack, and the economics that make the current era structurally different from all previous ones.

  1. AI Paradigms: Symbolic vs Connectionist
  2. Scaling Laws
  3. The Compute Stack
  4. AI vs ML vs Deep Learning (Technical)
  5. Why This Moment Is Different
  6. The Economics of Intelligence
Module 2 · 9 lessons

Generative AI & LLMs

Transformer internals, MoE architectures, training and post-training pipelines, tokenisation, inference optimisation, hallucination mechanics, RAG engineering, and the adaptation decision framework.

  1. The Transformer Architecture
  2. Beyond Vanilla Transformers: MoE and Friends
  3. Pre-training & Fine-tuning Pipeline
  4. Tokenisation In Depth
  5. Inference & Latency Optimisation
  6. Hallucination: Mechanisms & Mitigations
  7. RAG Architecture In Depth
  8. Fine-Tuning vs RAG vs Prompting
  9. LLM Governance & Safety — When Each Layer Applies
Module 3 · 7 lessons

Agentic AI

The architectural overview of agentic systems: architecture patterns, orchestration frameworks, MCP and A2A protocols, the attack surface, production reliability, context engineering, and evals. This module orients you across the whole shape of the problem. Three courses on this site — Agent Engineering, Securing AI Systems, and Does Your AI Actually Work? — take these same topics to production depth, and each lesson below says which one picks up where it stops.

  1. Agent Architecture Patterns
  2. Orchestration Frameworks
  3. MCP & A2A In Depth
  4. Security Attack Surface of Agents
  5. Production Reliability & Observability
  6. Context Engineering
  7. Evaluating LLMs and Agents
Module 4 · 5 lessons

AI Frontiers

The current edge of the field — RL-trained reasoning, multimodal understanding and generation, alignment as an engineering discipline, the regulatory landscape as it actually stands, and where the next few years are heading.

  1. Reasoning Models
  2. Multimodal Architecture
  3. Alignment Research
  4. AI Governance & Regulation
  5. The Road Ahead

Every lesson is free, with no sign-up. Reading happens in the library, where your progress is saved on your device.