Authors | |
Abstract |
Abstract: This article presents a model of self-improving AI in which improvement could happen on several levels: hardware, learning, code and goals system, each of which has several sublevels. We demonstrate that despite diminishing returns at each level and some intrinsic difficulties of recursive self-improvement—like the intelligence-measuring problem, testing problem, parent-child problem and halting risks—even non-recursive self-improvement could produce a mild form of superintelligence by combining small optimizations on different levels and the power of learning. Based on this, we analyze how self-improvement could happen on different stages of the development of AI, including the stages at which AI is boxed or hiding in the internet.
|
Keywords | recursive self-improvement artificial intelligence existential risks |
Categories | (categorize this paper) |
Options |
![]() ![]() ![]() |
Download options
References found in this work BETA
No references found.
Citations of this work BETA
No citations found.
Similar books and articles
Safety Engineering for Artificial General Intelligence.Roman Yampolskiy & Joshua Fox - 2013 - Topoi 32 (2):217-226.
Global Catastrophic and Existential Risks Communication Scale.Alexey Turchin & Denkeberger David - 2018 - Futures:not defiend yet.
Climate Change, Justice and the Right to Development.Lars Löfquist - 2011 - Journal of Global Ethics 7 (3):251-260.
Ethical Oversight in Quality Improvement and Quality Improvement Research: New Approaches to Promote a Learning Health Care System.Kevin Fiscella, Jonathan N. Tobin, Jennifer K. Carroll, Hua He & Gbenga Ogedegbe - 2015 - BMC Medical Ethics 16 (1):63.
Seven Propositions of the Science of Improvement: Exploring Foundations.Rocco J. Perla, Lloyd P. Provost & Gareth J. Parry - unknown
Advantages of Artificial Intelligences, Uploads, and Digital Minds.Kaj Sotala - 2012 - International Journal of Machine Consciousness 4 (01):275-291.
On Human Improvement.Asher Seidel - 1999 - International Journal of Applied Philosophy 13 (2):209-222.
Improvement Science Meets Improvement Scholarship: Reframing Research for Better Healthcare.Alan Cribb - 2018 - Health Care Analysis 26 (2):109-123.
“Don’T Mind the Gap!” Reflections on Improvement Science as a Paradigm.Trenholme Junghans - 2018 - Health Care Analysis 26 (2):124-139.
Philosophical and Anthropological Importance of Development of Artificially Created Intelligent Systems.Yu D. Gensitskiy - 2015 - Anthropological Measurements of Philosophical Research 8:86-96.
School Improvement: Reality and Illusion.Robert Coe - 2009 - British Journal of Educational Studies 57 (4):363-379.
Offline Improvement in Learning to Read a Novel Orthography Depends on Direct Letter Instruction.Tali Bitan & James R. Booth - 2012 - Cognitive Science 36 (5):896-918.
Conflicting Reasons in the Small-Improvement Argument.Johan E. Gustafsson & Nicolas Espinoza - 2010 - Philosophical Quarterly 60 (241):754-763.
Analytics
Added to PP index
2018-04-08
Total views
274 ( #38,577 of 2,498,521 )
Recent downloads (6 months)
26 ( #33,629 of 2,498,521 )
2018-04-08
Total views
274 ( #38,577 of 2,498,521 )
Recent downloads (6 months)
26 ( #33,629 of 2,498,521 )
How can I increase my downloads?
Downloads