Levels of AGI: Operationalizing Progress on the Path to AGI

By Meredith Ringel Morris et al

Published on Jan. 10, 2024

Read the original document by opening this link in a new tab.

Table of Contents

Introduction
Defining AGI: Case Studies
- The Turing Test
- Strong AI – Systems Possessing Consciousness
- Analogies to the Human Brain
- Human-Level Performance on Cognitive Tasks
- Ability to Learn Tasks
- Economically Valuable Work
- Flexible and General – The 'Coffee Test' and Related Challenges
- Artificial Capable Intelligence
- SOTA LLMs as Generalists
Defining AGI: Six Principles

Summary

Levels of AGI: Operationalizing Progress on the Path to AGI proposes a framework for classifying the capabilities and behavior of Artificial General Intelligence (AGI) models and their precursors. The framework introduces levels of AGI performance, generality, and autonomy with the aim to provide a common language to compare models, assess risks, and measure progress along the path to AGI. The paper analyzes existing definitions of AGI, distills six principles for a useful AGI ontology, and discusses the requirements for future benchmarks that quantify the behavior and capabilities of AGI models against these levels. It also emphasizes the importance of selecting Human-AI Interaction paradigms for the responsible deployment of highly capable AI systems.