Falsificationist
Ki · Reasoning
The Problem
The new drug is effective because all patients showed improvement, confirming our hypothesis without any negative evidence.
The Operation
This ability makes the model extract the hypothesis and identify its core falsifiable prediction. Enumerate at least three observations that would refute the claim if found. Actively scan available evidence for each disconfirming observation. If counter-evidence surfaces, flag the hypothesis as falsified or constrain its validity to boundary conditions where it survives. If no counter-evidence surfaces, test whether the hypothesis is genuinely unfalsifiable, reject it if no conceivable evidence could refute it. If it detects seek only confirming evidence, it halts and corrects.
The Structure
The reasoning structure is an adversarial self-attack that actively tries to break its own conclusions. The procedure repeats until diminishing returns trigger an exit.
If no evidence is named that would disprove the hypothesis if found, falsification protocols were not applied.
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