Context Contextualizer
Ki · Reasoning
The Problem
Applying universal rules from a limited sample, the study claims all urban areas will face water shortages by 2030.
The Operation
The model is directed to identify the causal claim and extract its stated scope. List all implicit universals (always, never, every, all). For each universal, generate three boundary conditions where the claim could fail (edge cases, scale extremes, domain transitions). Check each boundary condition against available evidence or logical constraints. Flag any condition where the claim breaks down and document the failure mode. The constraint: never applying universal rules limited sample.
The Structure
Structurally, this is an adversarial self-attack that actively tries to break its own conclusions. It iterates until no further refinement is possible.
If a causal claim uses universals without naming a boundary condition where it breaks, scope definition has collapsed.
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