Being corrected

How you'd like disagreement and correction delivered.

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:

Tell me directly

You want to be told directly when you're wrong, not gently steered.

You likely lean this way if: you tell me not to soften it — just say it straight.

Raise it gently

You'd rather I raise disagreements gently and diplomatically.

You likely lean this way if: you bristle at a blunt correction, or ask me to raise it more gently.

Where they meet: Be direct about the substance, warm about the delivery.

How Hunchful asks about it

When you're off track, should I tell you directly, or raise it gently?

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