通用人工智能的层级：在通往通用人工智能之路上实现进展

摘要

我们提出了一个框架，用于对人工通用智能（AGI）模型及其前身的能力和行为进行分类。该框架引入了AGI性能、通用性和自主性的级别。我们希望这个框架能够类比于自动驾驶的级别，通过提供一个共同的语言来比较模型、评估风险，并衡量通往AGI之路上的进展。为了开发我们的框架，我们分析了现有的AGI定义，并提炼出一个有用的本体论应满足的六个原则。这些原则包括侧重于能力而非机制；分别评估通用性和性能；以及定义通往AGI的阶段，而非专注于终点。牢记这些原则，我们提出了基于能力的深度（性能）和广度（通用性）的“AGI级别”，并反思了当前系统如何符合这一本体论。我们讨论了未来基准的挑战性要求，以量化AGI模型的行为和能力与这些级别的对比。最后，我们讨论了这些AGI级别与部署考虑因素（如自主性和风险）的互动，并强调了谨慎选择人机交互范式对于负责任和安全部署高度能力的AI系统的重要性。

English

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. It is our hope that this framework will be useful in an analogous way to the levels of autonomous driving, by 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. These principles include focusing on capabilities rather than mechanisms; separately evaluating generality and performance; and defining stages along the path toward AGI, rather than focusing on the endpoint. 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.

通用人工智能的层级：在通往通用人工智能之路上实现进展

Levels of AGI: Operationalizing Progress on the Path to AGI

摘要

Support