Friendly artificial intelligence: Difference between revisions

Revision as of 08:45, 11 July 2022

Revision as of 03:15, 27 August 2022

Line 13:

== Risks of unfriendly AI ==

{{main|Existential risk from artificial general intelligence}}

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}}</ref> By 1942 these themes prompted [[Isaac Asimov]] to create the "[[Three Laws of Robotics]]" - principles—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. He put it this way:

Line 19:

<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>

In 2008 Eliezer Yudkowsky called for the creation of “friendly"friendly AI”AI" to mitigate [[existential risk from advanced artificial intelligence]]. He explains: "The AI does not hate you, nor does it love you, but you are made out of atoms which it can use for something else."<ref>{{cite book |author=[[Eliezer Yudkowsky]] |year=2008 |chapter-url=http://intelligence.org/files/AIPosNegFactor.pdf |chapter=Artificial Intelligence as a Positive and Negative Factor in Global Risk |title=Global Catastrophic Risks |pages=308–345 |editor1=Nick Bostrom |editor2=Milan M. Ćirković}}</ref>

[[Steve Omohundro]] says that a sufficiently advanced AI system will, unless explicitly counteracted, exhibit a number of [[Instrumental convergence#Basic AI drives|basic "drives"]], such as resource acquisition, self-preservation, and continuous self-improvement, because of the intrinsic nature of any goal-driven systems and that these drives will, "without special precautions", cause the AI to exhibit undesired behavior.<ref>{{cite journal |last=Omohundro |first=S. M. |date=February 2008 |title=The basic AI drives |journal=Artificial General Intelligence |volume=171 |pages=483–492 |url=https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.393.8356&rep=rep1&type=pdf |citeseerx=10.1.1.393.8356}}</ref><ref>{{cite book|last1=Bostrom|first1=Nick|title=Superintelligence: Paths, Dangers, Strategies|date=2014|publisher=Oxford University Press|___location=Oxford|isbn=9780199678112|title-link=Superintelligence: Paths, Dangers, Strategies |chapter=Chapter 7: The Superintelligent Will}}</ref>

Line 84:

==Further reading==

* Yudkowsky, E. [http://intelligence.org/files/AIPosNegFactor.pdf Artificial Intelligence as a Positive and Negative Factor in Global Risk]. In ''Global Catastrophic Risks'', Oxford University Press, 2008.<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 [httphttps://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.393.8356&rep=rep1&type=pdf 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] 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 volume 23, pp 207–214.

==External links==

* [httphttps://www.nickbostrom.com/ethics/ai.html Ethical Issues in Advanced Artificial Intelligence] by Nick Bostrom

* [https://intelligence.org/ie-faq/#WhatIsFriendlyAI What is Friendly AI?] &mdash; A brief description of Friendly AI by the Machine Intelligence Research Institute.

* [https://intelligence.org/files/CFAI.pdf Creating Friendly AI 1.0: The Analysis and Design of Benevolent Goal Architectures] &mdash; A near book-length description from the MIRI

* [http://www.ssec.wisc.edu/~billh/g/SIAI_critique.html Critique of the MIRI Guidelines on Friendly AI] &mdash; by [[Bill Hibbard]]

* [http://www.optimal.org/peter/siai_guidelines.htm Commentary on MIRI's Guidelines on Friendly AI] &mdash; by Peter Voss.

* [httphttps://www.thenewatlantis.com/publications/the-problem-with-friendly-artificial-intelligence The Problem with ‘Friendly’ Artificial Intelligence] &mdash; On the motives for and impossibility of FAI; by Adam Keiper and Ari N. Schulman.

{{Existential risk from artificial intelligence}}