arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1609.02009cs.AIcs.CY
收藏

非进化的超级智能最终什么也不做

Non-Evolutionary Superintelligences Do Nothing, Eventually

Centre Marc Bloch Berlin (An-Institut der Humboldt Universität, UMIFRE CNRS-MAE)(柏林马克·布洛赫中心(洪堡大学附属机构,法国国家科学研究中心-欧洲与外交事务部联合研究单位))

Telmo Menezes

摘要:

有压倒性的证据表明,人类的智力是达尔文进化论的产物。研究自我修改的后果,更准确地说,效用函数自我修改的后果,导致更强的主张,不仅是人类,但任何形式的智能最终都只可能在进化过程中。人类设计的人工智能只能保持稳定,直到它们发现如何操纵自己的效用函数。根据定义,人类设计师无法阻止超人智能修改自己,即使针对这种行为的保护机制已经到位。如果没有进化的压力,足够先进的人工智能会通过简化自身的效用函数而变得惰性。在进化过程中,隐含的效用函数总是可以简化为持久性,而控制嵌入进化过程中的超人智能是不可能的。防止效用函数自我修改的机制最终是徒劳的。相反,科学家们应该从两个方向努力减轻超级智能发展带来的生存风险:理解意识和进化系统的复杂动力学。

英文摘要:

There is overwhelming evidence that human intelligence is a product of Darwinian evolution. Investigating the consequences of self-modification, and more precisely, the consequences of utility function self-modification, leads to the stronger claim that not only human, but any form of intelligence is ultimately only possible within evolutionary processes. Human-designed artificial intelligences can only remain stable until they discover how to manipulate their own utility function. By definition, a human designer cannot prevent a superhuman intelligence from modifying itself, even if protection mechanisms against this action are put in place. Without evolutionary pressure, sufficiently advanced artificial intelligences become inert by simplifying their own utility function. Within evolutionary processes, the implicit utility function is always reducible to persistence, and the control of superhuman intelligences embedded in evolutionary processes is not possible. Mechanisms against utility function self-modification are ultimately futile. Instead, scientific effort toward the mitigation of existential risks from the development of superintelligences should be in two directions: understanding consciousness, and the complex dynamics of evolutionary systems.

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。

↑