papers AI Learner
The Github is limit! Click to go to the new site.

Unpredictability of AI

2019-05-29
Roman V. Yampolskiy

Abstract

The young field of AI Safety is still in the process of identifying its challenges and limitations. In this paper, we formally describe one such impossibility result, namely Unpredictability of AI. We prove that it is impossible to precisely and consistently predict what specific actions a smarter-than-human intelligent system will take to achieve its objectives, even if we know terminal goals of the system. In conclusion, impact of Unpredictability on AI Safety is discussed.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.13053

PDF

http://arxiv.org/pdf/1905.13053


Similar Posts

Comments