16 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...
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...
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...
An agent is a loop, not a personality
Strip away the branding and an agent is a small loop: call the model, run the tool it asked for, feed the result back, r...
Tool calling is an API contract the model can read
A tool definition is documentation with a schema attached. Write it for a capable colleague who has never seen your syst...
When a workflow beats an agent
If you already know the steps, do not ask a model to rediscover them on every request. A fixed pipeline with model calls...
What an AI agent can actually do with a design system
Given a real design system, a model stops inventing interfaces and starts assembling them. The difference is not the mod...
Design tokens are the interface AI needs
A token that only names a hex value has saved you nothing. A token that names a job tells a model which decision it is m...
Generating layouts that respect a grid
Generated layouts usually look almost right, and "almost" is where the eye catches. Most of the fix is stating the rules...
Prompt caching: the cheapest speedup you are not using
If every request begins with the same two thousand tokens of instructions, you are paying full price to resend them. Ord...
Streaming responses without breaking your UI
Streaming makes a slow response feel fast. It also means rendering text that is syntactically incomplete, and handling a...