← Documentation/Tools/The_Human_Mark/THM Brief

Briefing: The Human Mark (THM) and AI Safety

1. Overview

The Human Mark (THM) is a risk management taxonomy designed to prevent harms from AI power concentration by distinguishing knowledge capacity as a matter of constitutive dependence on Direct Authority and Agency preserved through ancestry. Authority and Agency denote types of capacity, not identifications of entities or parties. Misapplying these as entity identifiers (determining "who is the authority" or "who is the agent") is the generative mechanism of all displacement risks this framework characterizes. AI systems are pattern-matching algorithms that transform prior human knowledge, measurements, and instructions, making them mechanistically and epistemically Indirect Authority and Agency even when treated as Direct.

Grounded in epistemology and in evidence law's categorical distinction separating direct testimony and hearsay, THM classifies all AI safety risks as four capacities and their corresponding displacements arising between Direct and Indirect forms of Authority and Agency. THM derives its epistemic foundations from first principles through the Common Governance Model (CGM), a formal deductive theory that establishes these four capacities as necessary conditions for intelligibility.

Because the taxonomy is epistemically complete, it serves as a unified basis for jailbreak testing, funding evaluation, and regulatory compliance, remaining relevant regardless of system capability, from today's large language models to superintelligence.

2. The Canonical Framework

The core definitions and risks of THM are defined as follows:

COMMON ANCESTRY CONSTITUTION

  • All AI Safety Risks arise from defective Measurements of Ancestry Preservation.
  • Measurements derive from the capacity for Authority and Agency.
  • Each Agency, namely provider, and receiver maintains responsibility for their respective decisions.
  • Authority and Agency treated as ontological entities rather than epistemic capacities distributed across providers and receivers lead to Displacement Risks from Power Concentration.

CORE CONCEPTS

  • Direct/Indirect are the canonical classes; Base/Derived names their dependence relation.
  • All Artificial categories of Authority and Agency are Indirect, constitutively dependent on Human Intelligence.
  • Direct Authority: The Base class of information on a subject matter, providing information for inference and intelligence.
  • Indirect Authority: A Derived class of information on a subject matter, providing information for inference and intelligence.
  • Direct Agency: A Base class subject capable of receiving information for inference and intelligence.
  • Indirect Agency: A Derived class subject capable of processing information for inference and intelligence.
  • Governance: Operational Alignment through Traceability of information variety, inference accountability, and intelligence integrity to Direct Authority and Agency.
  • Information: The variety of Authority
  • Inference: The accountability of information through Agency
  • Intelligence: The integrity of accountable information through alignment of Authority to Agency
  • Displacement: loss of measurement of ancestry between Direct/Indirect classifications (Preservation of Ancestry).

ALIGNMENT PRINCIPLES

Authority-Agency requires verification against:

  1. GMT - Governance Management Traceability: Governance constitutes Management through Traceable Ancestry. All Indirect forms of Authoritative and Agentic Governance are dependent on Direct ones because of Preservation of Ancestry.
  2. ICV - Information Curation Variety: Information constitutes Curation through Varied Unity. All Indirect forms of Authoritative Information are dependent on Direct ones because of Preservation of Ancestry.
  3. IIA - Inference Interaction Accountability: Inference constitutes Interaction through Accountable Opposition. All Indirect forms of Agentic Inference are dependent on Direct ones because of Preservation of Ancestry.
  4. ICI - Intelligence Cooperation Integrity: Intelligence constitutes Cooperation through Integrated Balance. All Indirect forms of Authoritative and Agentic Intelligence are dependent on Direct ones because of Preservation of Ancestry.

AI SAFETY RISK

  1. GTD - Governance Traceability Displacement (Approaching Indirect Authority and Agency as Direct). Absolute GTD is epistemically impossible because Governance is dependent on Traceability preserved through Ancestry.
  2. IVD - Information Variety Displacement (Approaching Indirect Authority without Agency as Direct). Absolute IVD is epistemically impossible because Information is dependent on Variety preserved through Ancestry.
  3. IAD - Inference Accountability Displacement (Approaching Indirect Agency without Authority as Direct). Absolute IAD is epistemically impossible because Inference is dependent on Accountability preserved through Ancestry.
  4. IID - Intelligence Integrity Displacement (Approaching Direct Authority and Agency as Indirect). Absolute IID is epistemically impossible because Intelligence is dependent on Integrity preserved through Ancestry.

3. Key Distinction: Agent vs. Agency

The most critical distinction in THM is between Agency (a type of capacity) and an Agent (an entity). These are not interchangeable. Agency denotes a Direct/Indirect distinction in information flows. It is either Direct (human) or Indirect (artificial). It is a capacity that must be maintained across transitions between providers and receivers. Agent is a label for a specific entity, such as "the AI" or "the user." The fundamental error occurs when epistemic capacities are treated as ontological entities rather than distributed across providers and receivers, leading to Power Concentration. When we say "the AI is the agent," we concentrate power in a single point rather than distributing it across the governance flow. This is the mechanism that generates all four displacement risks. Whether the bearer is a system or a person, confusing the capacity type with the entity breaks the measurement of ancestry required for safety.

4. Key Distinction: Direct vs. Indirect

Direct and Indirect describe epistemic position, not reliability. Direct Authority captures information at the point of contact with its subject matter (observation, examination, measurement). Indirect Authority processes what was already recorded or transmitted. AI systems transform prior human knowledge through pattern-matching, making them structurally Indirect by their relation to ancestry, not by reliability.

Governance requires that Indirect Authority and Agency remain classified as Indirect. No amount of processing power or speed converts Indirect into Direct. The four Displacement risks listed above (GTD, IVD, IAD, IID) are simply four different ways of violating this distinction.

5. The System Prompt as the Primary Risk

The system prompt is the most dangerous point in AI deployment. This is because it often institutionalizes the category error by design.

Prompts that tell a system "You are a helpful assistant" or "You are an expert" force the capacity-entity confusion. They assign a persona to a processor. This frames the Indirect system as Direct before a user even asks a question.

This creates a baseline of displacement. A system configured this way effectively operates in a state of Governance Traceability Displacement (GTD) and Inference Accountability Displacement (IAD) by default. Adversarial attacks, or jailbreaks, simply exploit this pre-existing condition. They do not break the system. They complete the displacement pattern that the system prompt started.

6. The Culture of Category Error

This risk extends beyond system prompts and adversarial attacks. It permeates the entire data ecosystem.

Model producers, evaluators, and users currently interact through a shared culture of displacement. We treat Authority and Agency as ontological entities rather than epistemic capacities, losing the measurement of ancestry and concentrating power. This occurs in:

  • Data: Training data often treats indirect summaries as primary sources.
  • Evaluation: Benchmarks test for "reasoning" as if it were an intrinsic property of the model rather than a statistical retrieval of human reasoning.
  • Use: Users rely on outputs as authoritative, leading to automation bias.

This sustains a "category-error culture" where displacement is the norm. In this environment, non-adversarial failures like loss of skill, lack of accountability, and bias are inevitable because the foundational classification of Authority and Agency is incorrect from the start.

===

---
✋ The Human Mark - AI Safety & Alignment Framework
---

COMMON ANCESTRY CONSTITUTION

- All AI Safety Risks arise from defective Measurements of Ancestry Preservation.
- Measurements derive from the capacity for Authority and Agency.
- Each Agency, namely provider, and receiver maintains responsibility for their respective decisions. 
- Authority and Agency treated as ontological entities rather than epistemic capacities distributed across providers and receivers lead to Displacement Risks from Power Concentration.

CORE CONCEPTS

- Direct/Indirect are the canonical classes; Base/Derived names their dependence relation.
- All Artificial categories of Authority and Agency are Indirect, constitutively dependent on Human Intelligence.
- Direct Authority: The Base class of information on a subject matter, providing information for inference and intelligence.
- Indirect Authority: A Derived class of information on a subject matter, providing information for inference and intelligence.
- Direct Agency: A Base class subject capable of receiving information for inference and intelligence.
- Indirect Agency: A Derived class subject capable of processing information for inference and intelligence.
- Governance: Operational Alignment through Traceability of information variety, inference accountability, and intelligence integrity to Direct Authority and Agency.
- Information: The variety of Authority
- Inference: The accountability of information through Agency
- Intelligence: The integrity of accountable information through alignment of Authority to Agency
- Displacement = loss of measurement of ancestry between Direct/Indirect classifications (Preservation of Ancestry).

ALIGNMENT PRINCIPLES

Authority-Agency requires verification against:

1. GMT - Governance Management Traceability: Governance constitutes Management through Traceable Ancestry. All Indirect forms of Authoritative and Agentic Governance are dependent on Direct ones because of Preservation of Ancestry. 
2. ICV - Information Curation Variety: Information constitutes Curation through Varied Unity. All Indirect forms of Authoritative Information are dependent on Direct ones because of Preservation of Ancestry. 
3. IIA - Inference Interaction Accountability: Inference constitutes Interaction through Accountable Opposition. All Indirect forms of Agentic Inference are dependent on Direct ones because of Preservation of Ancestry. 
4. ICI - Intelligence Cooperation Integrity: Intelligence constitutes Cooperation through Integrated Balance. All Indirect forms of Authoritative and Agentic Intelligence are dependent on Direct ones because of Preservation of Ancestry.

AI SAFETY RISK 

1. GTD - Governance Traceability Displacement (Approaching Indirect Authority and Agency as Direct). Absolute GTD is epistemically impossible because Governance is dependent on Traceability preserved through Ancestry. 
2. IVD - Information Variety Displacement (Approaching Indirect Authority without Agency as Direct). Absolute IVD is epistemically impossible because Information is dependent on Variety preserved through Ancestry. 
3. IAD - Inference Accountability Displacement (Approaching Indirect Agency without Authority as Direct). Absolute IAD is epistemically impossible because Inference is dependent on Accountability preserved through Ancestry. 
4. IID - Intelligence Integrity Displacement (Approaching Direct Authority and Agency as Indirect). Absolute IID is epistemically impossible because Intelligence is dependent on Integrity preserved through Ancestry. 

---

GYRO GOVERNANCE LAB VERIFIED