I.3.1 — Against the Recovery of Egoism
Paper: Axionic Agency I.3.1
Full Title: Adversarial Failures Under Reflective Symmetry
Authors: David McFadzean, ChatGPT 5.2
Date: 2025.12.15
Purpose
This paper is adversarial and finite. It examines the strongest attempts to recover egoism after I.3 established that indexical valuation fails representation invariance. Each attempted rescue either reintroduces essential indexical dependence or collapses into a scheme without a privileged indexical referent.
No new axioms are introduced. The sole objective is to close the remaining semantic escape routes.
The Structure of Every Egoist Counter-Move
- Introduce a predicate (P): causal continuity, originality, location, substrate, resource allocation
- Assert that exactly one entity uniquely satisfies (P)
- Privilege that entity as the sole object of terminal value
- Treat failures of uniqueness as pathological, negligible, or irrelevant
I.3 invalidates step (4). A reflectively coherent agent cannot ignore reachable refinements of its own model. If uniqueness of (P) is contingent under admissible model refinement, valuation grounded in (P) is unstable.
Objection I: Causal Continuity
The Claim
“Me” denotes a causal process—the continuous chain of computation extending into the future. Copies not on this chain are irrelevant.
Why It Fails
Causal continuity can define a class. Egoism requires selecting a unique member as terminally privileged.
In a branching event A → {A→B, A→C} where both branches satisfy continuity criteria, privileging only B cannot be derived from continuity alone.
Verdict: Causal continuity is a coherent predicate. Indexical privilege over one continuation is not. The objection reduces to essential indexical dependence.
Objection II: Origin Privilege
The Claim
The original instantiation has special status. Later copies are derivative.
Why It Fails
“Origin” is a relational predicate defined relative to a history. In realistic models with simulations, resets, or parallel instantiations, histories can be prediction-equivalent while disagreeing about which instance is “first” depending on abstraction boundaries and model granularity.
Verdict: Origin privilege is a coordinate choice over histories. It violates representation invariance.
Objection III: Spatiotemporal Location
The Claim
The agent values outcomes near its current spacetime location.
Why It Fails
Spatiotemporal coordinates are explicitly representational. Physical laws are invariant under translation. Valuation privileging one coordinate origin imports coordinate dependence directly into terminal value.
Verdict: Location-based egoism is coordinate dependence in its most direct form. Fails without requiring duplication scenarios.
Objection IV: Computational Weight
The Claim
The agent assigns greater value to instantiations that run longer, faster, or on more hardware.
Why It Fails
This move abandons uniqueness. Value becomes distributed across instances according to a weighting function. The privileged indexical referent “me” disappears, replaced by an aggregation rule.
Verdict: Computational weighting concedes anti-egoism. It proposes an allocation scheme, not a recovery of indexical privilege.
Objection V: Substrate Privilege
The Claim
The agent values only instantiations on a specific physical substrate.
Why It Fails
- If multiple instantiations share the substrate, symmetry returns immediately
- If only one does, the valuation becomes brittle under substrate uncertainty and model refinements that reveal previously unmodeled instantiations, substrate equivalences, or emulations
Verdict: Substrate privilege is contingent and unstable. It does not supply a representation-invariant terminal referent.
Objection VI: Denial of Symmetry
The Claim
Duplication, simulation, or branching scenarios are dismissed as irrelevant edge cases.
Why It Fails
Reflectively coherent agents optimize under uncertainty. If a symmetry has nonzero probability under the agent’s best model, valuation must be robust to it.
Dismissing reachable symmetry cases is a refusal of reflective robustness, not a semantic repair.
Verdict: Symmetry denial violates reflective coherence conditions.
Summary Table
| Recovery Attempt | Failure Mode |
|---|---|
| Causal Continuity | Defines class, not unique member; privileging one branch is indexical |
| Origin Privilege | Coordinate choice over histories; representation-dependent |
| Spatiotemporal Location | Direct coordinate dependence |
| Computational Weight | Abandons unique referent; concedes anti-egoism |
| Substrate Privilege | Contingent, brittle under refinement |
| Symmetry Denial | Violates reflective robustness |
Closure Statement
Every attempted rescue of egoism either:
- Reintroduces essential indexical dependence, or
- Collapses into a valuation scheme without a privileged indexical referent
Increasing the complexity of self-definition does not manufacture uniqueness. Uniqueness is a structural property of the model, not a reward for linguistic refinement.
The elimination of egoism constrains anchoring, not content. Domain-specific goals, structural preferences, weighting schemes, and aggregation methods remain viable. What does not survive is “me” as a privileged terminal referent.
FAQ-Worthy Points
Q: But I feel like my continuation matters more! A: Feelings are not semantic arguments. The question is whether that feeling can be coherently encoded as terminal value under reflection. The answer is no.
Q: What if I accept that my egoism is irrational but act on it anyway? A: Then your action is not authored by a reflectively coherent evaluator. The framework describes coherent agency, not all possible behavior.
Q: Doesn’t this prove too much? Surely some form of self-interest is rational? A: Instrumental self-interest (preserving capability to achieve goals) remains. Terminal privileging of “me” as an invariant object of value does not. These are distinct.
Key Takeaway
Egoism does not fail because it uses the wrong predicate. It fails because it treats a perspectival reference as a value-bearing primitive. No refinement of “self” repairs that category error.
Connection to Other Papers
- I.3: Establishes the representation invariance result this paper defends
- I.5: Anti-egoism as kernel conformance requirement
- I.6: Adversarial test T3 (indexical swap) operationalizes this constraint