Content deleted Content added
Shinkolobwe (talk | contribs) m Punctuations |
Shinkolobwe (talk | contribs) Minor copyedit + cleanup of the source code of the page |
||
Line 1:
{{
{{Use mdy dates|date=October 2023}}
{{Artificial intelligence|Philosophy}}
Line 10:
<blockquote>Yudkowsky (2008) goes into more detail about how to design a '''Friendly AI'''. He asserts that friendliness (a desire not to harm humans) should be designed in from the start, but that the designers should recognize both that their own designs may be flawed, and that the robot will learn and evolve over time. Thus the challenge is one of mechanism design—to define a mechanism for evolving AI systems under a system of checks and balances, and to give the systems utility functions that will remain friendly in the face of such changes.</blockquote>
== Risks of unfriendly AI ==
{{
The roots of concern about artificial intelligence are very old. Kevin LaGrandeur showed that the dangers specific to AI can be seen in ancient literature concerning artificial humanoid servants such as the [[golem]], or the proto-robots of [[Gerbert of Aurillac]] and [[Roger Bacon]]. In those stories, the extreme intelligence and power of these humanoid creations clash with their status as slaves (which by nature are seen as sub-human), and cause disastrous conflict.<ref>{{cite journal|url=https://www.academia.edu/704751|author=Kevin LaGrandeur|title=The Persistent Peril of the Artificial Slave|journal=Science Fiction Studies|year=2011|volume=38|issue=2|page=232|doi=10.5621/sciefictstud.38.2.0232|access-date=2013-05-06|author-link=Kevin LaGrandeur|archive-date=2023-01-13|archive-url=https://web.archive.org/web/20230113152138/https://www.academia.edu/704751|url-status=live}}</ref> By 1942 these themes prompted [[Isaac Asimov]] to create the "[[Three Laws of Robotics]]"—principles hard-wired into all the robots in his fiction, intended to prevent them from turning on their creators, or allowing them to come to harm.<ref>{{cite book| title=The Rest of the Robots| chapter-url=https://archive.org/details/restofrobots00asim| chapter-url-access=registration| publisher=Doubleday| year=1964| isbn=0-385-09041-2| chapter=Introduction| author=Isaac Asimov}}</ref>
In modern times as the prospect of [[Superintelligence|superintelligent AI]] looms nearer, philosopher [[Nick Bostrom]] has said that superintelligent AI systems with goals that are not aligned with human ethics are intrinsically dangerous unless extreme measures are taken to ensure the safety of humanity.
<blockquote>Basically we should assume that a 'superintelligence' would be able to achieve whatever goals it has. Therefore, it is extremely important that the goals we endow it with, and its entire motivation system, is 'human friendly.'</blockquote>
Line 30:
In 2014, Luke Muehlhauser and Nick Bostrom underlined the need for 'friendly AI';<ref name=think13>{{Cite journal|last1=Muehlhauser|first1=Luke|last2=Bostrom|first2=Nick|title=Why We Need Friendly AI|date=2013-12-17|journal=Think|volume=13|issue=36|pages=41–47|doi=10.1017/s1477175613000316|s2cid=143657841|issn=1477-1756}}</ref> nonetheless, the difficulties in designing a 'friendly' superintelligence, for instance via programming counterfactual moral thinking, are considerable.<ref name=boyles2019>{{Cite journal|last1=Boyles|first1=Robert James M.|last2=Joaquin|first2=Jeremiah Joven|date=2019-07-23|title=Why friendly AIs won't be that friendly: a friendly reply to Muehlhauser and Bostrom|journal=AI & Society|volume=35|issue=2|pages=505–507|doi=10.1007/s00146-019-00903-0|s2cid=198190745|issn=0951-5666}}</ref><ref>{{Cite journal|last=Chan|first=Berman|date=2020-03-04|title=The rise of artificial intelligence and the crisis of moral passivity|journal=AI & Society|volume=35|issue=4|pages=991–993|language=en|doi=10.1007/s00146-020-00953-9|s2cid=212407078|issn=1435-5655|url=https://philpapers.org/rec/CHATRO-56|access-date=2023-01-21|archive-date=2023-02-10|archive-url=https://web.archive.org/web/20230210114013/https://philpapers.org/rec/CHATRO-56|url-status=live}}</ref>
== Coherent extrapolated volition ==
Yudkowsky advances the Coherent Extrapolated Volition (CEV) model. According to him, our coherent extrapolated volition is "our wish if we knew more, thought faster, were more the people we wished we were, had grown up farther together; where the extrapolation converges rather than diverges, where our wishes cohere rather than interfere; extrapolated as we wish that extrapolated, interpreted as we wish that interpreted".<ref name=cevpaper />
Rather than a Friendly AI being designed directly by human programmers, it is to be designed by a "seed AI" programmed to first study [[human nature]] and then produce the AI
== Other approaches ==
{{See also|AI control problem#Alignment|AI safety}}
[[Steve Omohundro]] has proposed a "scaffolding" approach to [[AI safety]], in which one provably safe AI generation helps build the next provably safe generation.<ref name=Hendry2014>{{cite news|last1=Hendry|first1=Erica R.|title=What Happens When Artificial Intelligence Turns On Us?|url=http://www.smithsonianmag.com/innovation/what-happens-when-artificial-intelligence-turns-us-180949415/|access-date=15 July 2014|work=Smithsonian Magazine|date=21 Jan 2014|archive-date=19 July 2014|archive-url=https://web.archive.org/web/20140719142131/http://www.smithsonianmag.com/innovation/what-happens-when-artificial-intelligence-turns-us-180949415/|url-status=live}}</ref>
[[Seth Baum]] argues that the development of safe, socially beneficial artificial intelligence or artificial general intelligence is a function of the social psychology of AI research communities
In his book ''[[Human Compatible]]'', AI researcher [[Stuart J. Russell]] lists three principles to guide the development of beneficial machines. He emphasizes that these principles are not meant to be explicitly coded into the machines; rather, they are intended for the human developers. The principles are as follows:<ref name="HC">{{cite book |last=Russell |first=Stuart |date=October 8, 2019 |title=Human Compatible: Artificial Intelligence and the Problem of Control |url=https://archive.org/details/humancompatiblea0000russ |___location=United States |publisher=Viking |isbn=978-0-525-55861-3 |author-link=Stuart J. Russell |oclc=1083694322 |url-access=registration }}</ref>{{rp|173}}
Line 45:
{{quote|
# The machine's only objective is to maximize the realization of human preferences.
# The machine is initially uncertain about what those preferences are.
# The ultimate source of information about human preferences is human behavior.}}
The "preferences" Russell refers to "are all-encompassing; they cover everything you might care about, arbitrarily far into the future."<ref name="HC"/>{{rp|173}} Similarly, "behavior" includes any choice between options,<ref name="HC"/>{{rp|177}} and the uncertainty is such that some probability, which may be quite small, must be assigned to every logically possible human preference.<ref name="HC"/>{{rp|201}}
== Public policy ==
[[James Barrat]], author of ''[[Our Final Invention]]'', suggested that "a public-private partnership has to be created to bring A.I.-makers together to share ideas about security—something like the [[International Atomic Energy Agency]], but in partnership with corporations." He urges AI researchers to convene a meeting similar to the [[Asilomar Conference on Recombinant DNA]], which discussed [[risks of biotechnology]].<ref name=Hendry2014 />
[[John McGinnis]] encourages governments to accelerate friendly AI research. Because the goalposts of friendly AI are not necessarily eminent, he suggests a model similar to the [[National Institutes of Health]], where "Peer review panels of computer and cognitive scientists would sift through projects and choose those that are designed both to advance AI and assure that such advances would be accompanied by appropriate safeguards." McGinnis feels that peer review is better "than regulation to address technical issues that are not possible to capture through bureaucratic mandates". McGinnis notes that his proposal stands in contrast to that of the [[Machine Intelligence Research Institute]], which generally aims to avoid government involvement in friendly AI.<ref name=McGinnis2010>{{cite journal|last1=McGinnis|first1=John O.|title=Accelerating AI|journal=Northwestern University Law Review|date=Summer 2010|volume=104|issue=3|pages=1253–1270|url=http://www.law.northwestern.edu/LAWREVIEW/Colloquy/2010/12/|access-date=16 July 2014|archive-date=1 December 2014|archive-url=https://web.archive.org/web/20141201201600/http://www.law.northwestern.edu/LAWREVIEW/Colloquy/2010/12/|url-status=live}}</ref>
== Criticism ==
{{
Some critics believe that both human-level AI and superintelligence are unlikely
Some philosophers claim that any truly "rational" agent, whether artificial or human, will naturally be benevolent; in this view, deliberate safeguards designed to produce a friendly AI could be unnecessary or even harmful.<ref>{{cite journal | last=Kornai | first=András | title=Bounding the impact of AGI | journal=Journal of Experimental & Theoretical Artificial Intelligence | publisher=Informa UK Limited | volume=26 | issue=3 | date=2014-05-15 | issn=0952-813X | doi=10.1080/0952813x.2014.895109 | pages=417–438 | s2cid=7067517 |quote=...the essence of AGIs is their reasoning facilities, and it is the very logic of their being that will compel them to behave in a moral fashion... The real nightmare scenario (is one where) humans find it advantageous to strongly couple themselves to AGIs, with no guarantees against self-deception.}}</ref> Other critics question whether
The inner workings of advanced AI systems may be complex and difficult to interpret, leading to concerns about transparency and accountability.<ref>{{Cite book |last=Norvig |first=Peter |title=Artificial Intelligence: A Modern Approach |last2=Russell |first2=Stuart |publisher=Pearson |year=2010 |isbn=978-0136042594 |edition=3rd}}</ref>
== See also ==
{{div col|colwidth=30em}}
* [[Affective computing]]
Line 95:
{{div col end}}
== References ==
{{Reflist|30em}}
== Further reading ==
* Yudkowsky, E. (2008). [http://intelligence.org/files/AIPosNegFactor.pdf Artificial Intelligence as a Positive and Negative Factor in Global Risk]. In ''Global Catastrophic Risks'', Oxford University Press.<br />Discusses Artificial Intelligence from the perspective of [[Existential risk]]. In particular, Sections 1-4 give background to the definition of Friendly AI in Section 5. Section 6 gives two classes of mistakes (technical and philosophical) which would both lead to the accidental creation of non-Friendly AIs. Sections 7-13 discuss further related issues.
* Omohundro, S. (2008). The Basic AI Drives Appeared in AGI-08 – Proceedings of the First Conference on Artificial General Intelligence.
* Mason, C. (2008). [https://aaai.org/Papers/Workshops/2008/WS-08-07/WS08-07-023.pdf Human-Level AI Requires Compassionate Intelligence] {{Webarchive|url=https://web.archive.org/web/20220109170511/https://aaai.org/Papers/Workshops/2008/WS-08-07/WS08-07-023.pdf |date=2022-01-09 }} Appears in [[AAAI]] 2008 Workshop on Meta-Reasoning: Thinking About Thinking.
* Froding, B. and Peterson, M. (2021). [https://link.springer.com/article/10.1007/s10676-020-09556-w Friendly AI] Ethics and Information Technology,
== External links ==
* [https://nickbostrom.com/ethics/ai Ethical Issues in Advanced Artificial Intelligence] by Nick Bostrom
* [https://intelligence.org/ie-faq/#WhatIsFriendlyAI What is Friendly AI?] — A brief description of Friendly AI by the Machine Intelligence Research Institute.
| |||