Series · / 02
Explained
Plain-language explainers on the companies, products, protocols, rules and ideas behind today's AI, each built from primary sources.
All issues · 18
18How to read a system card: a builder's guide to AI safety documentation7 MIN17Context windows vs memory vs RAG: what each one actually does7 MIN16How Gemini handles a 900-page PDF: the limits, the costs and what long-context benchmarks show6 MIN15The Claude app, explained: plans, models, Cowork and how usage limits work6 MIN14ChatGPT agent mode, explained: what it was, why it's gone, and what ChatGPT Work does instead7 MIN13How to choose a small AI model for your laptop: the memory math and the current shortlist7 MIN12Reasoning models explained: thinking tokens, what they cost, and when to use them7 MIN11What the EU AI Act means if you only use model APIs8 MIN10The EU AI Act in October 2026: what actually applies now8 MIN09What an NPU actually does, and why the TOPS number on your laptop matters less than you think7 MIN08Model routing explained: how to mix cheap, mid and frontier models8 MIN07MCP resources vs tools vs prompts: who decides, and when to use each6 MIN06OpenAI explained: who controls it, what it sells, and how it makes money7 MIN05Anthropic explained: history, products and how it makes money8 MIN04OpenAI Codex explained: where it runs, which models and limits you get, and how its sandbox works7 MIN03Claude Code mods, explained: what Anthropic's new extension layer can do, where it runs, and the security trade-off8 MIN02What is MCP? The Model Context Protocol explained (2026 edition)8 MIN01What "agentic" really means in 20266 MIN