Track · Developers and makers building with AI

Builder

From prompts to products.

What you need to build apps on top of language models: embeddings, transformers, retrieval, agents, evals and open models.

0 of 11 finished

1. 1Beginner · 6 min · up nextMeet the chatbots: LLMsHow ChatGPT, Claude and friends work: one word at a time, with surprising results.
2. 2Beginner · 6 minTalking to AI: prompting wellA chatbot is only as good as what you ask it. Five habits that turn vague answers into great ones.
3. 3Intermediate · 7 minHow text becomes tokensLanguage models don't read letters or words: they read tokens. How text gets chopped up, and why it explains some odd model mistakes.
4. 4Intermediate · 5 minEmbeddings: meaning as mapsHow AI turns words, images and songs into points in space where closeness means similarity.
5. 5Advanced · 8 minAttention is all you needThe transformer architecture and the attention mechanism that powers every modern LLM.
6. 6Advanced · 7 minRAG & AI agentsGiving models fresh knowledge with retrieval, and the ability to act with tools.
7. 7Advanced · 8 minAgents: loops, tools and memoryAn agent is a language model in a loop that can act. How the loop works, how tools plug in, and why agents fail in surprising ways.
8. 8Intermediate · 7 minHow we test language modelsBenchmarks, leaderboards, human votes and AI judges: how anyone decides one model is better than another, and why it's harder than it looks.
9. 9Intermediate · 6 minOpen-weight models and running AI yourselfWhat "open" really means for AI models, why it matters, and how a laptop can run a capable chatbot.
10. 10Advanced · 6 minFine-tuning on a budget: LoRA & quantisationHow to customise a billion-parameter model on a single GPU.
11. 11Advanced · 8 minHow models are served: prefill, decode and the KV cacheWhat happens on the computer when you press send. Why replies stream out word by word, why output tokens cost more, and the tricks that make it all faster.