Principlev1
When stated values diverge from revealed values, treat the
When stated values diverge from revealed values, treat the gap as a design problem requiring infrastructure changes rather than a character problem requiring willpower, since willpower without redesign merely patches symptoms.
Why This Is a Principle
This is a meta-principle about how to approach values alignment. It derives from Directed Attention as Depletable Resource (willpower is finite resource), Single-loop learning adjusts actions within existing (double-loop learning questions assumptions vs single-loop adjusting within them), and Every system is perfectly designed to get the results it (systems produce their results). It's prescriptive (treat as design not character), actionable (tells you what category of solution to pursue), and addresses the systematic failure of willpower-based approaches to closing stated-revealed gaps.