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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Šprogar, Matej
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918530536964096
author Šprogar, Matej
author_facet Šprogar, Matej
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2504_04430
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Foundational Requirements for Artificial General Intelligence: A Falsifiable Framework Based on Signal Prediction
Šprogar, Matej
Artificial Intelligence
I.2; D.2.8; I.2.6; I.5
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.
title Foundational Requirements for Artificial General Intelligence: A Falsifiable Framework Based on Signal Prediction
topic Artificial Intelligence
I.2; D.2.8; I.2.6; I.5
url https://arxiv.org/abs/2504.04430