Position: Levels of AGI for Operationalizing Progress on the Path to AGI
By Meredith Ringel Morris, Jascha Narain Sohl-Dickstein, Noah Fiedel, Tris Warkentin, Allan Dafoe, Aleksandra Faust, Clément Farabet, Shane Legg. 2023
113 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Management Information Systems, Management Science and Operations Research, AI Ethics, Fairness & Society
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
Citations in the corpus
- MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark (2024, background): “A key objective in this ongoing development is achieving expert-level intelligence, characterized by performance that meets or surpasses the top 10% of skilled adults in a diverse range of tasks [26].”
- MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark (2024, unknown): “However, as highlighted by the AGI taxonomy proposed by (Morris et al., 2024), which defines AGI as a system that performs at the “90th percentile of skilled adults” across a wide array of tasks, current benchmarks fall short of this standard.”