Skip to content

Videos

AI explained in short videos

One idea per video, in plain language. Each one links to the chapter of our free course that explains it step by step.

AI news, guides and product updates, by email

WhatsApp community (opens in a new tab)Telegram channel (opens in a new tab)

Start here AI 101

Latest

By course chapter

  1. 1The Perceptron From Scratch: What a Neuron Computes10 videos
  2. 2Where a Loss Function Comes From: Likelihood, Not Convention12 videos
  3. 3Downhill: Gradient Descent, and the Two Steps Everyone Skips13 videos
  4. 4Classification, Cross-Entropy, and How Not to Fool Yourself22 videos
  5. 5Backpropagation From Scratch: The Engine, Then the Network11 videos
  6. 6Getting It to Train, and Getting It to Generalise19 videos
  7. 7Build a BPE Tokenizer: Why Your Model Can't Count the R's12 videos
  8. 8Next-Token Prediction: Embeddings, and What Perplexity Means17 videos
  9. 9Attention and the Transformer Block, Derived From an Average17 videos
  10. 10Pretraining an LLM: Data, Compute, Scaling Laws and Cost21 videos
  11. 11From Base Model to Assistant: SFT, RLHF, DPO and GRPO16 videos
  12. 12Chain of Thought, RLVR and Test-Time Compute, Measured9 videos
  13. 13Making Inference Cheap: KV Cache, Batching and Quantization18 videos
  14. 14Your First Production LLM Call: Streaming, Retries, Timeouts11 videos
  15. 15Prompt Engineering, Measured: What Changes the Output11 videos
  16. 16The Context Window, Tokens and the Bill, Measured2 videos
  17. 17Temperature, Top-p and the Determinism You Do Not Have
  18. 18Tool Calling and Structured Outputs: The Contract That Holds
  19. 19RAG in Production: Chunking, Retrieval and Honest Citations
  20. 20Fine-Tune, Retrieve or Prompt? The Decision Is Economic
  21. 21Multimodal Pricing: What Images, Audio and Video Really Bill
  22. 22What an AI Agent Is: Five Classic Types, Two Rival Definitions
  23. 23Build an Agent Harness: The Loop and Its Five Ways Out
  24. 24Context Engineering: Why Your Agent Gets Dumber at Turn 40
  25. 25Multi-Agent Orchestration: Five Patterns, and When One Wins
  26. 26MCP Explained Against the Spec: What a Server Really Is
  27. 27Ship an MCP Server: TypeScript and Python, Measured
  28. 28Agent Skills and SKILL.md: Progressive Disclosure, Measured
  29. 29LLM Evaluation: From Public Benchmarks to Your Golden Set
  30. 30Prompt Injection and the Lethal Trifecta: Securing a Real Agent