10 posts found
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...
How to evaluate an AI feature before you ship it
You cannot unit test "is this a good answer", but you can build a set of real cases with known-good outputs. An afternoo...
The cost model of an AI feature
Per-token pricing looks trivial until you multiply by retries, conversation history and the context you resend on every...
Writing prompts your team can maintain
Prompts are code with none of the tooling. Treat them like code anyway — version them, review them, test them, and expla...
What to tell users when the model is wrong
Your AI feature will be confidently wrong in front of a user. What the interface does in that moment decides whether the...
AI adoption without a rewrite
The best first AI feature is small, measurable and easy to switch off. Start where a wrong answer is cheap and the value...