ActPC-Chem: Discrete Active Predictive Coding for Goal-Guided Algorithmic Chemistry as a Potential Cognitive Kernel for Hyperon & PRIMUS-Based AGI

TL;DR

ActPC-Chem proposes a discrete Active Predictive Coding framework built on a metagraph of rewrite rules (algorithmic chemistry) as a cognitive kernel for PRIMUS/Hyperon AGI systems. It argues for a tight integration of data and models via rule-based transformations, guided by information-theoretic prediction errors, epistemic/instrumental rewards, and continuous/discrete predictive coding. The work lays out naive formalizations, adds discrete natural gradients with Wasserstein geometry to stabilize learning, and illustrates via toy and robot-enabled thought experiments how self-modifying rule sets can autonomously acquire goal-directed policies and abstractions. It further integrates symbolic AI (AIRIS, PLN) to support causal inference and probabilistic abstraction within a unified metagraph, and sketches a transformer-like network that replaces backpropagation with rule-based transformations and predictive coding. Together, these components chart a path toward a hybrid neural-symbolic system capable of robust reasoning, abstraction, and adaptive control with potential applicability to PRIMUS-based AGI and beyond.

Abstract

We explore a novel paradigm (labeled ActPC-Chem) for biologically inspired, goal-guided artificial intelligence (AI) centered on a form of Discrete Active Predictive Coding (ActPC) operating within an algorithmic chemistry of rewrite rules. ActPC-Chem is envisioned as a foundational "cognitive kernel" for advanced cognitive architectures, such as the OpenCog Hyperon system, incorporating essential elements of the PRIMUS cognitive architecture. The central thesis is that general-intelligence-capable cognitive structures and dynamics can emerge in a system where both data and models are represented as evolving patterns of metagraph rewrite rules, and where prediction errors, intrinsic and extrinsic rewards, and semantic constraints guide the continual reorganization and refinement of these rules. Using a virtual "robot bug" thought experiment, we illustrate how such a system might self-organize to handle challenging tasks involving delayed and context-dependent rewards, integrating causal rule inference (AIRIS) and probabilistic logical abstraction (PLN) to discover and exploit conceptual patterns and causal constraints. Next, we describe how continuous predictive coding neural networks, which excel at handling noisy sensory data and motor control signals, can be coherently merged with the discrete ActPC substrate. Finally, we outline how these ideas might be extended to create a transformer-like architecture that foregoes traditional backpropagation in favor of rule-based transformations guided by ActPC. This layered architecture, supplemented with AIRIS and PLN, promises structured, multi-modal, and logically consistent next-token predictions and narrative sequences.