量子物理如何影响通用人工智能的实现与能力边界
Quantum AGI: Ontological Foundations
- 从信息论角度区分经典与量子通用智能
- 量子非局域性、上下文依赖等特性限制智能体实现
- 适合对量子智能基础感兴趣的理论研究者
我们探讨量子基础对通用人工智能（AGI）的影响，重点分析贝尔定理（非局域性）、Kochen-Specker 定理（上下文依赖性）以及不可克隆定理对量子环境中实现 AGI 的挑战。提出一种新的信息论分类框架，区分经典 AGI 与量子 AGI，揭示量子力学如何改变代理的基本特征。研究表明，量子本体论既可能带来计算优势，也可能引入新约束，从而重塑 AGI 的能力边界。
原文摘要 · Abstract (English)
We examine the implications of quantum foundations for AGI, focusing on how seminal results such as Bell's theorems (non-locality), the Kochen-Specker theorem (contextuality) and no-cloning theorem problematise practical implementation of AGI in quantum settings. We introduce a novel information-theoretic taxonomy distinguishing between classical AGI and quantum AGI and show how quantum mechanics affects fundamental features of agency. We show how quantum ontology may change AGI capabilities, both via affording computational advantages and via imposing novel constraints.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。