Foundational Requirements for Artificial General Intelligence: A Falsifiable Framework Based on Signal Prediction

Abstract

Grounded in the premise that high-level intelligence can emerge from low-level signal processing, we advance a hypothesis regarding low-level requirements necessary for artificial general intelligence. The proposed requirements characterise core properties of systems that learn through prediction over spatially and temporally structured signals with initially unknown semantic content. They include a selection of basic principles observed in cognitive neuroscience, from learning from an uninformed state to real-time liveness. To enable empirical testing and hypothesis rejection, we introduce an operational testbed composed of transparent and reusable tests, one per requirement. To date, no non-intelligent system has been identified or reported as successfully passing the testbed. Pending such a counterexample, the testbed serves as a candidate empirical milestone toward general intelligence. The reference implementation of the testbed is publicly available.