Explainers
Notes and interactive guides on things I'm learning.
N.B. These pages are AI-generated. Treat them as explainers rather than primary sources.
- 1. HTTP Caching From Cache-Control directives to the wire, with diagrams, a header builder, and a live cache simulator.
- 2. How LLMs Work Tokens, embeddings, attention, the KV cache, and prefill vs. decode. What actually happens when a chatbot replies.
- 3. GPUs SMs, warps, tensor cores, and why bandwidth, not flops, is usually the limit. The chip that became the engine of AI.
- 4. Claude Agent SDK The agent loop that powers Claude Code, exposed as a library. Tools, permissions, MCP, hooks, and subagents, with diagrams.
- 5. Macroeconomics in 2026 Inflation tamed, central banks cutting, the AI capex boom, deficits at wartime levels, and a fragmenting trade order.
- 6. Domain Driven Design Ubiquitous language, bounded contexts, aggregates, and the idea that the words you say should match the words in the code.
- 7. Your Ancestors A reverse family tree from you to the dawn of life. Why the doubling has to stop, and why every stranger is a cousin.
- 8. RAG for EPR Legislation Building a retrieval pipeline over global producer-responsibility law: structure-aware chunking, hybrid search, jurisdiction routing, grounded citations.