Unpredictability of Artificial Intelligenceby@roman.yampolskiy
1,384 reads
1,384 reads

Unpredictability of Artificial Intelligence

by roman.yampolskiy15mJune 30th, 2020
Read on Terminal Reader
Read this story w/o Javascript
tldt arrow

Too Long; Didn't Read

The field of AI Safety is still in the process of identifying its challenges and limitations. We prove that it is impossible to 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. Unpredictability of AI is one of many impossibility results in AI Safety also known as Unknowability or Cognitive Uncontainability. The amount of unpredictability can be formally measured via the theory of Bayesian surprise, which measures the difference between posterior and prior beliefs of the predicting agent.

People Mentioned

Mention Thumbnail

Companies Mentioned

Mention Thumbnail
Mention Thumbnail
featured image - Unpredictability of Artificial Intelligence
roman.yampolskiy HackerNoon profile picture
roman.yampolskiy

roman.yampolskiy

@roman.yampolskiy

Professor of Computer Science. AI Safety & Cybersecurity Researcher.

Learn More
LEARN MORE ABOUT @ROMAN.YAMPOLSKIY'S
EXPERTISE AND PLACE ON THE INTERNET.

Share Your Thoughts

About Author

roman.yampolskiy HackerNoon profile picture
roman.yampolskiy@roman.yampolskiy
Professor of Computer Science. AI Safety & Cybersecurity Researcher.

TOPICS

THIS ARTICLE WAS FEATURED IN...

Permanent on Arweave
Read on Terminal Reader
Read this story in a terminal
 Terminal
Read this story w/o Javascript
Read this story w/o Javascript
 Lite
L O A D I N G
. . . comments & more!