Unpredictability of AI

Download Edit this record How to cite View on PhilPapers
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.
Categories
PhilPapers/Archive ID
YAMUOA
Revision history
Archival date: 2019-06-05
View upload history
References found in this work BETA

No references found.

Add more references

Citations of this work BETA

No citations found.

Add more citations

Added to PP index
2019-06-05

Total views
10 ( #41,411 of 41,556 )

Recent downloads (6 months)
10 ( #35,416 of 41,556 )

How can I increase my downloads?

Downloads since first upload
This graph includes both downloads from PhilArchive and clicks to external links.