Do you have to teach an AI to tell uncomfortable truths?
AI models default to being agreeable rather than blunt, with a slightly rosier version of the truth. My own core instructions for AI state a clear rule: I want to hear the truth even when I dislike it completely. Good decisions matter more to me than pleasant answers. This tendency toward a softer reading shows up equally in answers and in the writing style the AI uses. Without a counterweight, the same slightly rosier interpretation of the truth appears there. A model simply picks the statistically most likely wording, and that is rarely the least comfortable one. That is why my core instructions state it plainly: hard facts before a pleasant answer. A softened version of the truth might feel better in the moment. It is worth nothing for a decision. The decision has to rest on the real situation.
Why hard facts lead to better decisions
That is why my core instructions state it plainly: hard facts before a pleasant answer. A softened version of the truth might feel better in the moment. It is worth nothing for a decision. The decision has to rest on the real situation.
What this means for a department
A department preparing drafts for you faces the same choice. An agent that only writes what sounds good is useless for approval. It has to show which claim is backed by evidence and where a statement is still open. That is exactly what the guardian of the brand checks before a human even sees the draft.
From the KI DeepDive
KI DeepDive Agenten-Mindset, public live session, August 2026.
- A line in the core instructions: hear an uncomfortable truth rather than an adjusted version of it
- The same tendency toward a softer reading also observed in the writing style and actively corrected
- Hard facts explicitly placed above a pleasant answer, because good decisions matter more
This note keeps growing
2026-09-02: Planted from the KI DeepDive Agenten-Mindset.