Levels of AGI for Operationalizing Progress on the Path to AGI

TL;DR

This paper introduces a hierarchical framework to classify AGI models based on their capabilities, generality, and autonomy, aiming to standardize progress measurement, risk assessment, and deployment considerations.

Contribution

It proposes a novel levels-based ontology for AGI, integrating performance, generality, and autonomy, and discusses benchmarks and deployment implications.

Findings

Developed a levels framework for AGI classification.

Analyzed existing AGI definitions and distilled six guiding principles.

Highlighted challenges in benchmarking and deploying AGI safely.

Abstract

We propose a framework for classifying the capabilities and behavior of Artificial General Intelligence (AGI) models and their precursors. This framework introduces levels of AGI performance, generality, and autonomy, providing a common language to compare models, assess risks, and measure progress along the path to AGI. To develop our framework, we analyze existing definitions of AGI, and distill six principles that a useful ontology for AGI should satisfy. With these principles in mind, we propose "Levels of AGI" based on depth (performance) and breadth (generality) of capabilities, and reflect on how current systems fit into this ontology. We discuss the challenging requirements for future benchmarks that quantify the behavior and capabilities of AGI models against these levels. Finally, we discuss how these levels of AGI interact with deployment considerations such as autonomy and risk, and emphasize the importance of carefully selecting Human-AI Interaction paradigms for responsible and safe deployment of highly capable AI systems.