10 posts found
What a large language model actually predicts
A model does not look anything up and does not decide what is true. It estimates which token comes next. Almost everythi...
Tokens, not words: how a model reads your text
Models do not see characters or words. They see tokens — and once you know how text becomes tokens, several odd behaviou...
Why temperature changes the answer, not the knowledge
Turning temperature down does not make a model more accurate. It makes it more repeatable — and confusing the two is how...
Embeddings explained without the linear algebra
An embedding turns text into coordinates, and nearby coordinates mean related meaning. That single idea is what makes se...
Training, fine-tuning and prompting are three different tools
Teams reach for fine-tuning when they need context, and for prompting when they need behaviour. Knowing which problem ea...
The context window is a budget, not a memory
Bigger context windows did not give models memory. They gave you a larger envelope to fill on every single request — and...
Why models hallucinate, and what actually reduces it
Hallucination is not a glitch that a better model will one day remove. It is what generation does when it has nothing to...
System prompts: the instructions the user never sees
A system prompt sets the rules for everything that follows. Written well it is the cheapest quality improvement availabl...
Structured output beats parsing prose
If your code needs a value from a model, ask for JSON and validate it. Regexing an answer out of a paragraph is a bug wa...
Choosing between a large model and a small one
Most production traffic does not need the largest model available. Routing by task rather than defaulting to the top of...