Emergent Causality & the Foundation of Consciousness

Abstract

<p>To make accurate inferences in an interactive setting, an agent must not confuse passive observation of events with having participated in causing those events. The ``do'' operator formalises interventions so that we may reason about their effect. Yet there exist at least two pareto optimal mathematical formalisms of general intelligence in an interactive setting which, presupposing no explicit representation of intervention, make maximally accurate inferences. We examine one such formalism. We show that in the absence of an operator, an intervention can still be represented by a variable. Furthermore, the need to explicitly represent interventions in advance arises only because we presuppose abstractions. The aforementioned formalism avoids this and so, initial conditions permitting, representations of relevant causal interventions will emerge through induction. These emergent abstractions function as representations of one’s self and of any other object, inasmuch as the interventions of those objects impact the satisfaction of goals. We argue (with reference to theory of mind) that this explains how one might reason about one's own identity and intent, those of others, of one's own as perceived by others and so on. In a narrow sense this describes what it is to be aware, and is a mechanistic explanation of aspects of consciousness.</p>

The Optimal Choice of Hypothesis Is the Weakest, Not the Shortest

“…Obviously this can work well, but only for the subset of possible tasks that the vocabulary is able to describe in this way (anything else will not be able to be represented as a universally quantified rule, and so will not be represented at all [25]). This illustrates how future research [26,27] may explore choices of v in aid of more efficient induction in particular sorts of task.…”

On the Computation of Meaning, Language Models and Incomprehensible Horrors

“…Let k and o be organisms. If k affects o, and assuming v o is sufficient to allow o to distinguish when it is affected by k from when it is not (meaning all else being equal k's interventions are distinguishable by the presence of an identity [22], then there exists experience…”

Enactivism & Objectively Optimal Super-Intelligence

“…Preferences that determine what is considered complete, methods of attributing task completion to past decisions, as well as relative grades thereof, are beyond this paper's scope. Preferences are formalised in a companion to this paper [28,29].…”