Sound Research WIKINDX
Sound Research WIKINDX |
|
 |
|
Morris, M. R., Sohl-Dickstein, J., Fiedel, N., Warkentin, T., Dafoe, A., & Faust, A., et al. Levels of AGI for Operationalizing Progress on the Path to AGI. Unpublished paper presented at Proceedings of ICML 2024. Added by: alexb44 (03/09/2026, 08:31) Last edited by: alexb44 (03/09/2026, 08:32) |
 |
| Resource type: Conference Paper BibTeX citation key: Morris Email resource to friend View all bibliographic details  |
Categories: AI/Machine Learning Keywords: Artificial General Intelligence, Artificial Intelligence, Definition of AGI Creators: Dafoe, Farabet, Faust, Fiedel, Legg, Morris, Sohl-Dickstein, Warkentin Collection: Proceedings of ICML 2024 |
Views: 5/5
|
| 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.
Added by: alexb44 |