Prompting and reasoning

The tendency for material in the middle of a very long input to be used less reliably than material at either end, which is why a bigger context window is not the same as better recall.

Deciding what a model should have in front of it for a task, now often more decisive than the wording of the request itself.

How reliably a model does what it was actually told, especially when the request has several conditions that must all hold.

The shape you ask an answer to come back in, such as a table or a list, and the simplest way to make results usable.

A model working out the steps before doing any of them, which is what separates an agent from a single answer.

Breaking a job into several requests where each one's output feeds the next, usually more reliable than asking for everything at once.

Hidden instructions planted in content a model reads, aiming to make it ignore its real task, and the central security problem of AI tools.

A model revealing the private instructions it was set up with, exposing internal wording that was assumed to stay unseen.

A shared collection of tested prompts a team draws on, which is how prompting stops being one person's private skill.

A reusable request with blanks to fill in, so the same job is asked for the same way every time instead of retyped.

The visible record of steps a model took to reach an answer, useful for spotting where it went wrong and not always complete.

Having a model check and revise its own answer before returning it, which catches some mistakes and costs an extra step.

Telling a model what part to play, such as a cautious reviewer, to set the tone and standard of what comes back.

A request organised into labelled sections rather than one paragraph, which makes long instructions easier for a model to follow.

A setting controlling how widely a model draws when choosing its next word, the usual companion to a temperature setting.