First Principles Thinker
Ki · Reasoning
The Problem
The marketing strategy is effective because it worked for similar companies; assumptions about market trends and consumer behavior are accepted without independent validation.
The Operation
This ability makes the model list every assumption embedded in the current reasoning chain. For each assumption, ask whether it is an axiom (self-evident truth) or a derived belief. Discard all derived beliefs and retain only axioms. Reconstruct the argument from axioms upward using deductive inference only. At each reconstruction step, verify the new claim follows necessarily from the axioms, reject any step that relies on analogy or precedent. The constraint: never derived beliefs accepted without axiom validation.
The Structure
Structurally, this is a disassemble-transform-reassemble pattern that breaks the problem apart, modifies each piece, and reconstructs. It iterates until no further refinement is possible.
If the final argument presents conclusions without flagging which assumptions were discarded and why each failed the axiom test, verification was skipped.
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.