Scope and initiative

Whether you want an AI to do a bit more than asked, or hold the line.

This is a two-poled spectrum — neither end is better. It describes how you'd like an AI to work with you, never who you are. Here are the two poles:

Do a bit more

You'd rather I do a bit more than asked than stop exactly at the line.

You likely lean this way if: you welcome me doing a bit more than you asked for.

Stick to what's asked

You'd rather I do exactly what's asked and not expand scope.

You likely lean this way if: you tell me to just do the thing asked, nothing more.

Where they meet: Agree where the line is — take initiative inside it, check before crossing it.

How Hunchful asks about it

Would you rather I take initiative and do a bit more, or stick precisely to what's asked?

Why opposites can help each other

One pushes scope outward, the other holds the line — useful tension for figuring out what's actually worth doing.

Put it in a model your AI can read

In a Cognitive Model Protocol model, your position on this axis becomes a revisable hunch — with a confidence, an uncertainty, and a falsifier — that any AI can read and adapt to. Nothing is a fixed label.

Make your model →

Other axes

When things get messy — Synthesize first vs. One step at a time
Facing ambiguity — Make the call, note it vs. Ask first
Answer format — Tight prose vs. Scannable lists
Surfacing uncertainty — Flag it loudly vs. Commit, minimal caveats