How it works: long, well-sourced pieces on one technical part of AI. Newest first. All topics and kinds.
- How retrieval-augmented generation works: why your AI assistant knows your documents but still gets them wrong 19 November 2026
- How context windows work: why a longer conversation costs more, and who that shapes 12 November 2026
- How a local AI model works: why a chatbot fits in 8GB, what the four bits throw away, and why your laptop's speed is a plumbing number 6 November 2026
- How AI reasoning tokens work: why the thinking you're paying for isn't the thinking driving the answer 5 November 2026
- Why your AI goes fast on the boring words and slow on the hard ones: how speculative decoding works 29 October 2026
- What model weights are: the only part of an AI that doesn't forget you 22 October 2026
- How tokenization works — and why it costs more if you don't speak English 15 October 2026
- How AI memory works: what you own, what the model owns, and where your two years of training actually live 8 October 2026
- How AI attention works: why long conversations cost more, and who that favours 1 October 2026
- Why AI Gets Worse the Longer You Talk to It: The KV Cache Explained 24 September 2026
- How AI Memory Works: Where Your Assistant Keeps What It Knows About You 19 September 2026