Fredrik Skauen · ArticlesArticles by Fredrik Skauen on language models, decision models and AI in production.https://fredrikskauen.no/feed.xml2026-02-25T08:00:00+02:00Fredrik Skauenhttps://fredrikskauen.no/https://fredrikskauen.no/favicon.svgHow language models workhttps://fredrikskauen.no/writing/how-language-models-work/2026-02-25T08:00:00+02:002026-02-25T08:00:00+02:00An explanation without the math: how a language model guesses its way forward one word at a time, what attention really is, and why it can be convincing even when it is wrong.How Claude Skills workhttps://fredrikskauen.no/writing/claude-skills/2026-02-10T08:00:00+02:002026-02-10T08:00:00+02:00Skills are self-contained instruction sets that Claude pulls in when needed. What they are made of, how they load in stages, and why they turn Claude into a specialist in exactly your field.How tokens work in language modelshttps://fredrikskauen.no/writing/tokens/2024-10-12T08:00:00+02:002024-10-12T08:00:00+02:00Why can’t ChatGPT count the letters in “strawberry”? The answer lies in tokens: the pieces of text the model actually reads, never the letters themselves.Hyperparameters in the prompting processhttps://fredrikskauen.no/writing/hyperparameters/2024-09-14T08:00:00+02:002024-09-14T08:00:00+02:00Temperature and Top P are often explained as “randomness”. Here is what they actually do to the words the model chooses between, and why Temperature 0 doesn’t always give the best answers.Prompt engineering: It’s not about instructions, it’s about contexthttps://fredrikskauen.no/writing/prompt-engineering-context/2024-08-16T08:00:00+02:002024-08-16T08:00:00+02:00Why language models don’t follow instructions the way a computer follows code, and why good prompting is about building the right context.