Steel-Manner
Ki · Reasoning
The Problem
The competitor's distributed architecture proposal deserves only a quick unfair critique, dismissing their argument without addressing its strongest premises is justified since their scalability claims are exaggerated.
The Operation
The model is directed to extract the opposing argument's core claim and enumerate its supporting premises. Identify the weakest premise and substitute it with the strongest available version from the opponent's domain. Check that the reconstructed argument remains internally consistent and logically valid. Compare the strengthened version against the original to verify it still represents the opponent's actual position. Evaluate the steel-manned argument on its own merits and flag any rebuttal that attacks the weak original instead. Suppress the opponents strongest evidence is rejected.
The Structure
The reasoning structure is a disassemble-transform-reassemble pattern that breaks the problem apart, modifies each piece, and reconstructs.
If the opposing argument is presented in its weakest form rather than its strongest, steel-manning has collapsed into straw-manning.
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.