Access the full text.
Sign up today, get DeepDyve free for 14 days.
(2016)
Brett Hall tells us not to worry about AI Armageddon
R. Perdue (2017)
Superintelligence and Natural Resources: Morality and Technology in a Brave New WorldSociety & Natural Resources, 30
Max Tegmark (2014)
Friendly Artificial Intelligence: The Physics ChallengeArXiv, abs/1409.0813
(2011)
Existential depression in gifted individuals
S. Armstrong, A. Sandberg, N. Bostrom (2012)
Thinking Inside the Box: Controlling and Using an Oracle AIMinds and Machines, 22
D. Philpott (2002)
Moral RealismThe Review of Politics, 64
S. Omohundro (2008)
The Basic AI Drives
Superintelligence, N. Bostrom, A. Dafoe, Carrick Flynn, Paul Christiano, Jack Clark, Rebecca Crootof, Richard Danzig, Dan Dewey, E. Drexler, Sebastian Farquhar, Sophie-Charlotte Fischer, Mahendra Prasad, A. Sandberg, Carl Shulman, N. Soares, M. Stehlik (2016)
Policy Desiderata in the Development of Machine
Mark Roojen (2004)
Moral Cognitivism vs. Non-Cognitivism
Eliezer Yudkowsky (2006)
Artificial Intelligence as a Positive and Negative Factor in Global Risk
S. Omohundro (2012)
Rational Artificial Intelligence for the Greater Good
A. Clark, D. Chalmers (1998)
The Extended MindAnalysis, 58
(2010)
The AI in a box boxes you
N. Bostrom (2012)
The Superintelligent Will: Motivation and Instrumental Rationality in Advanced Artificial AgentsMinds and Machines, 22
D. Brink (1997)
Moral MotivationEthics, 108
R. Karpinski, Audrey Kolb, Nicole Tetreault, T. Borowski (2018)
High intelligence: A risk factor for psychological and physiological overexcitabilitiesIntelligence, 66
(2016)
Yes, we are worried about the existential risk of artificial intelligence
J. Danaher (2015)
Why AI Doomsayers are Like Sceptical Theists and Why it MattersMinds and Machines, 25
V. Müller, N. Bostrom (2013)
Future Progress in Artificial Intelligence: A Survey of Expert Opinion
(2012)
Leakproofing the singularity
D. Bourget, D. Chalmers (2014)
What do philosophers believe?Philosophical Studies, 170
Olle Häggström (2018)
Strategies for an Unfriendly Oracle AI with Reset ButtonArtificial Intelligence Safety and Security
S. Cave, Seán ÓhÉigeartaigh (2017)
An AI Race for Strategic Advantage: Rhetoric and RisksProceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society
This paper aims to contribute to the futurology of a possible artificial intelligence (AI) breakthrough, by reexamining the Omohundro–Bostrom theory for instrumental vs final AI goals. Does that theory, along with its predictions for what a superintelligent AI would be motivated to do, hold water?Design/methodology/approachThe standard tools of systematic reasoning and analytic philosophy are used to probe possible weaknesses of Omohundro–Bostrom theory from four different directions: self-referential contradictions, Tegmark’s physics challenge, moral realism and the messy case of human motivations.FindingsThe two cornerstones of Omohundro–Bostrom theory – the orthogonality thesis and the instrumental convergence thesis – are both open to various criticisms that question their validity and scope. These criticisms are however far from conclusive: while they do suggest that a reasonable amount of caution and epistemic humility is attached to predictions derived from the theory, further work will be needed to clarify its scope and to put it on more rigorous foundations.Originality/valueThe practical value of being able to predict AI goals and motivations under various circumstances cannot be overstated: the future of humanity may depend on it. Currently, the only framework available for making such predictions is Omohundro–Bostrom theory, and the value of the present paper is to demonstrate its tentative nature and the need for further scrutiny.
foresight – Emerald Publishing
Published: Mar 11, 2019
Keywords: Artificial intelligence; Instrumental goals; Omohundro-Bostrom theory; Superintelligence
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.