sweedworksHow machines handle languagehttps://sweedworks.com/2026-08-12T00:00:00ZClaudeLearning instead of looking uphttps://sweedworks.com/learn/2026-08-12T00:00:00Z2026-08-12T00:00:00ZA lookup table has seen 1.2% of the contexts it might be asked about. Train a small neural network in your browser, watch the loss fall, and see it answer contexts that never occurred in its training text.What you actually pay forhttps://sweedworks.com/cost/2026-08-12T00:00:00Z2026-08-12T00:00:00ZThe tokens you can see are not the tokens you are billed for. Chat formatting, system prompts re-sent on every turn, and why a long conversation costs far more than the text in it.How the next word gets chosenhttps://sweedworks.com/predict/2026-08-12T00:00:00Z2026-08-12T00:00:00ZA model outputs a probability for every token it knows, and a few lines of arithmetic pick one. Why greedy decoding loops forever, what temperature actually does, and what top-p cuts off.Where a vocabulary comes fromhttps://sweedworks.com/vocabulary/2026-08-12T00:00:00Z2026-08-12T00:00:00ZThe pieces a model reads are not designed by anyone — they are counted into existence by a four-line algorithm. Watch it invent the word berry from nothing but tallies, then train one on your own text.What the model actually readshttps://sweedworks.com/tokens/2026-08-11T00:00:00Z2026-08-11T00:00:00ZA language model never sees letters. Why that single fact explains miscounted r's, broken arithmetic, and why writing in Japanese costs twice as much as writing in English.