论智能机器的不可判定特征
On Formally Undecidable Traits of Intelligent Machines
AI总结:
基于 Alfonseca 等人的研究,本文提出一种数学上独立于形式语言理论的形式化体系,用于判定机器特征,并证明 Rice 定理不能一般性地判定机器是否具备特定特征,故判定机器智能或道德等并非逻辑不可能。
摘要:
基于 Alfonseca 等人 (2021) 的工作,我们研究了证明任意人工智能机器将表现出特定行为在逻辑上所需满足的条件。为此,我们开发了一种形式化体系,它类似于——但在数学上不同于——形式语言理论及其属性。我们的形式化体系不仅提供了一种精确的方法来讨论我们对机器所期望的特征(例如它们是智能的、受控的、道德的等等),而且还详细说明了在逻辑上判定给定任意机器是否具备此类特征所需的条件。与 Alfonseca 等人 (2021) 的结果相反,我们发现可计算性理论中的 Rice 定理通常不能用于判定任意机器是否具备给定特征。因此,判定任意机器是否智能、受控、道德等,在逻辑上并不一定是不可能的。
英文摘要:
Building on work by Alfonseca et al. (2021), we study the conditions necessary for it to be logically possible to prove that an arbitrary artificially intelligent machine will exhibit certain behavior. To do this, we develop a formalism like -- but mathematically distinct from -- the theory of formal languages and their properties. Our formalism affords a precise means for not only talking about the traits we desire of machines (such as them being intelligent, contained, moral, and so forth), but also for detailing the conditions necessary for it to be logically possible to decide whether a given arbitrary machine possesses such a trait or not. Contrary to Alfonseca et al.'s (2021) results, we find that Rice's theorem from computability theory cannot in general be used to determine whether an arbitrary machine possesses a given trait or not. Therefore, it is not necessarily the case that deciding whether an arbitrary machine is intelligent, contained, moral, and so forth is logically impossible.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。