📚 Basics

Short track on AI: terms and language models → LLM overview → prompt engineering, RAG, and LLM agents as separate articles.

• AI basics – introduction
  • 🎬 Video · reading 5 min / video 4 min
  • 🏷️ Terms: language model, dataset, parameters, AI/ML/NN, foundation models
  • 📊 Difficulty: basic
  • 📋 Prerequisites: none
• AI basics – overview
  • 🎬 Video · reading ~14 min / video 9 min
  • 📋 LLM overview: use cases, internals (tokens, transformers), prompting, RAG, fine-tuning, chain-of-thought, model families, key terms, risks, trends
  • 🏷️ LLM, transformer, token, temperature, prompt engineering, RAG, fine-tuning, RLHF, chain-of-thought, context window, hallucinations, multimodality, agents
  • 📊 Difficulty: basic
  • 📋 Prerequisites: none (intro to the series is enough)
• AI basics – prompt engineering
  • ⏱️ ~7 min read · no video
  • 📋 Zero-shot, few-shot, chain-of-thought, roles, step-back, where prompts come from; mind-map layout; accordions
  • 🏷️ prompt engineering, zero-shot, few-shot, CoT, role prompting, step-back, in-context learning
  • 📊 Difficulty: basic
  • 📋 Prerequisites: LLM overview recommended
• AI basics – RAG systems
  • ⏱️ ~6 min read · no video
  • 📋 Why RAG, pipeline stages, chunking, naive vs advanced RAG; accordions
  • 🏷️ RAG, retrieval, embeddings, vector index, chunking, context-conditioned generation
  • 📊 Difficulty: basic
  • 📋 Prerequisites: LLM overview recommended
• AI basics – LLM agents
  • ⏱️ ~7 min read · no video
  • 📋 Agent vs chat, planning / memory / tools, mindset, ReAct, multi-agent, who uses them; accordions
  • 🏷️ AI agents, LLM, ReAct, tools, planning, memory, multi-agent systems
  • 📊 Difficulty: basic
  • 📋 Prerequisites: LLM overview recommended; RAG helps

👥 On Their Shoulders

Short digests from interviews, podcasts, and conferences on AI

• The Future of AI: Why Scaling Alone is No Longer Enough
  • 🎬 Video · reading 12 min / video 8 min (original 52 min)
  • 👥 Participants: Nicholas Thompson, Eric Xing, Yoshua Bengio, Yuval Noah Harari, Yejin Choi
  • 🏷️ Terms: scaling, reward hacking, world model, guardrail, AGI, anthropomorphism
  • 📊 Difficulty: intermediate
  • 📋 Prerequisites: AI basics

📐 Essential Mathematics

Machine learning relies on mathematics that grows out of the school curriculum; to understand how ML works, you need a solid grasp of school-level math.

• Essential Mathematics — Overview
  • 📋 Overview: which math areas are needed for AI/ML and why
  • 🏷️ Linear algebra, calculus, probability and statistics
  • 📊 Difficulty: basic
• Math Analysis — Example of Analysis (Finding πr²)
  • 📋 Slicing the circle into rings, unrolling into strips 2πr × Δr — yields a triangle of area πR²
  • 🏷️ Integral, limits, area of circle
  • 📊 Difficulty: basic
• Math Analysis — Derivatives
  • 📋 Without this you can’t understand how neural networks learn. Derivative, gradient, chain rule.
  • 🏷️ Gradient descent, backpropagation
  • 📊 Difficulty: basic