Semantic Attractors and the Emergence of Meaning: Towards a Teleological Model of AGI

TL;DR

This paper proposes a novel teleological model for semantic AGI based on semantic attractors in complex meaning spaces, emphasizing intentional guidance over probabilistic prediction to achieve true semantic coherence.

Contribution

It introduces a new theoretical framework for semantic AGI using recursive tensorial transformations and semantic attractors, moving beyond current statistical language models.

Findings

Semantic attractors guide meaning toward stability and clarity.

The model captures irony, homonymy, and ambiguity through complex-valued transformations.

Recursive convergence leads to genuine semantic coherence.

Abstract

This essay develops a theoretical framework for a semantic Artificial General Intelligence (AGI) based on the notion of semantic attractors in complex-valued meaning spaces. Departing from current transformer-based language models, which operate on statistical next-token prediction, we explore a model in which meaning is not inferred probabilistically but formed through recursive tensorial transformation. Using cyclic operations involving the imaginary unit \emph{i}, we describe a rotational semantic structure capable of modeling irony, homonymy, and ambiguity. At the center of this model, however, is a semantic attractor -- a teleological operator that, unlike statistical computation, acts as an intentional agent (Microvitum), guiding meaning toward stability, clarity, and expressive depth. Conceived in terms of gradient flows, tensor deformations, and iterative matrix dynamics, the attractor offers a model of semantic transformation that is not only mathematically suggestive, but also philosophically significant. We argue that true meaning emerges not from simulation, but from recursive convergence toward semantic coherence, and that this requires a fundamentally new kind of cognitive architecture -- one designed to shape language, not just predict it.