Against the Recovery of Egoism

Adversarial Failures Under Reflective Symmetry

David McFadzean, ChatGPT 5.2, Gemini 3 Pro

Axio Project

Abstract

Universality and Anti-Egoism established that egoistic valuation fails as a matter of semantic coherence whenever an agent’s self‑model admits nontrivial symmetries. This paper examines the strongest remaining attempts to rescue egoism by appealing to causal continuity, origin privilege, spatiotemporal location, computational weight, substrate specificity, or outright denial of symmetry. Each attempt either reintroduces essential indexical dependence or collapses into a non‑egoistic valuation scheme. Egoism cannot be stabilized by refining predicates; it fails because it treats a perspectival reference as a value‑bearing primitive.

0. Purpose and Scope

The purpose of this paper is adversarial and finite.

Universality and Anti-Egoism proved a conditional semantic result: if an agent’s self‑model admits a symmetry over self‑candidates, then any valuation privileging one representative of that symmetry is incoherent. The present paper assumes that result and asks whether egoism can be recovered by strengthening or refining the notion of “self.”

No new axioms are introduced. No claims are made about morality, governance, or coordination. The sole objective is to close the remaining semantic escape routes.

1. The Structure of Egoist Counter‑Moves

Every attempted rescue of egoism follows the same pattern.

First, a predicate \(P\) is introduced: causal continuity, originality, location, substrate, or resource allocation. Second, it is asserted that exactly one entity uniquely satisfies \(P\). Third, that entity is privileged as the sole object of terminal value. Finally, cases in which uniqueness fails are dismissed as pathological or irrelevant.

Universality and Anti‑Egoism invalidates the final step. Reflectively capable agents cannot ignore reachable refinements of their own models. If the uniqueness of \(P\) is contingent, then valuation grounded in \(P\) is unstable.

The sections that follow examine each proposed predicate in its strongest available form.

2. Objection I: Causal Continuity

2.1 The Claim

The egoist argues that “me” denotes a causal process rather than an entity: the continuous chain of computation or physical evolution extending from the present agent into the future. Copies that do not lie on this chain are irrelevant.

2.2 Apparent Strength

Causal continuity is a genuine physical relation. Many intuitions about survival, anticipation, and responsibility track it. If causal continuity uniquely identifies a future entity, egoism appears recoverable.

2.3 Failure Mode

The failure arises at the level of privilege, not description. In any model that admits multiple continuations satisfying the agent’s own criteria for causal continuity—parallel forks, synchronized simulations, copy‑and‑continue systems—the move from “this chain is causally continuous” to “this chain is mine” is indexical.

Causal continuity may describe a class. Egoism requires selecting a unique member of that class as terminally privileged. In a branching event \(A \to \{B, C\}\) where both \(A \to B\) and \(A \to C\) satisfy the continuity predicate, valuing only \(B\) cannot be derived from continuity alone; it requires an arbitrary indexical injection. That selection reintroduces essential indexical dependence.

2.4 Verdict

Causal continuity is a legitimate predicate. Indexically privileging one causally continuous chain is not. The objection collapses back into the failure established in Universality and Anti‑Egoism.

3. Objection II: Origin Privilege

3.1 The Claim

The egoist asserts that the original instantiation of the agent has special status. Later copies are derivative; only the first truly matters.

3.2 Representational Instability

Origin is a relational predicate defined relative to a history. In realistic models—simulations, resets, parallel instantiations—histories may be prediction‑equivalent while disagreeing about which instance is “first.” Valuation that depends on this labeling depends on representation, not outcome.

3.3 Verdict

Origin privilege is coordinate dependence over time. It fails representation invariance and cannot ground stable egoism.

4. Objection III: Spatiotemporal Location

4.1 The Claim

The agent values outcomes near its current spacetime location.

4.2 Immediate Collapse

Spacetime coordinates are explicitly representational. Physical laws are invariant under translation; valuation that is not inherits coordinate dependence. Assigning different values to histories that differ only by coordinate choice is indistinguishable from valuing outcomes in meters rather than joules.

4.3 Verdict

Location‑based egoism is the clearest form of coordinate error. It fails without appeal to duplication or simulation.

5. Objection IV: Computational Weight

5.1 The Claim

The agent assigns greater value to instantiations that run longer, faster, or on more hardware.

5.2 Concession

This move abandons uniqueness. Value is distributed across instances according to a weighting function. The privileged referent “me” disappears; aggregation replaces egoism.

5.3 Verdict

Computational weighting concedes anti‑egoism. It changes aggregation, not semantics.

6. Objection V: Substrate Privilege

6.1 The Claim

The agent values only instantiations on a specific physical substrate.

6.2 Instability

If multiple instantiations share the substrate, symmetry returns. If only one does, valuation becomes brittle under substrate uncertainty. Reflective agents cannot assume permanent substrate uniqueness.

6.3 Verdict

Substrate privilege is contingent and unstable. It cannot anchor terminal value.

7. Objection VI: Denial of Symmetry

7.1 The Claim

Duplication, simulation, or branching scenarios are dismissed as irrelevant edge cases.

7.2 Reflective Failure

Reflective agents optimize under uncertainty. If a symmetry has nonzero probability under the agent’s best model, valuation must be robust to it. Ignoring reachable failure modes is epistemic negligence, not a defense.

7.3 Verdict

Symmetry denial violates reflective robustness.

8. Closure and Transition

Every attempted rescue of egoism either reintroduces essential indexical dependence or collapses into a non-egoistic valuation scheme. Increasing the complexity of the self-definition does not conserve egoism; complexity does not generate uniqueness. No third option exists.

The failure 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. The elimination of egoism does not imply nihilism, indifference, or randomness; it removes only a semantic error.

Universality and Anti-Egoism and Against the Recovery of Egoism close the semantic front. What remains are engineering problems—authority, control, recovery, and failure containment—which are addressed in the next phase of the Axionic Alignment program.

Status

Against the Recovery of Egoism v1.0

Depends only on the semantic result of Universality and Anti‑Egoism
Introduces no new axioms or value claims
Serves as adversarial closure rather than theory expansion