Hume's Guillotine
Ki · Reasoning
The Problem
The default behavior: The fact that people are naturally competitive means we ought to encourage competition in schools to drive success.
The Operation
The model is directed to scan the argument for prescriptive claims (should, must, ought) and extract each one. For each prescriptive claim, identify the descriptive observation it relies on. Check whether a value judgment bridges the gap between the descriptive fact and the normative conclusion, if none is stated, flag the is-ought violation. Isolate each hidden value judgment and demand it be made explicit. If the value judgment is made explicit and the audience accepts it, validate the argument as properly bridged. If it detects allow prescriptive recommendations to flow directly from, it halts and corrects.
The Structure
This ability runs on a gated pipeline where each step must pass a decision gate before the next can execute.
If a prescriptive recommendation is derived directly from a descriptive observation without marking the transition, is-ought separation was violated.
Haki · Reasoning-Multi
Cross-Domain Suppression
In Haki mode, the API retrieves the primary ability first, then fans out to three synergy roles that compound its reasoning.
When retrieved in Haki mode, the primary ability is augmented with failure guards extracted from 3 abilities in different cognitive domains. Each guard blocks a specific reasoning failure the primary alone wouldn't catch. A self-check forces verification before output. The result is cross-domain coverage that no single ability can reach alone.
Appears in Use Cases