Friendly artificial intelligence: Difference between revisions

Revision as of 20:52, 8 September 2024

Revision as of 22:27, 2 December 2024

Line 20:

<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 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 |access-date=2013-10-19 |archive-date=2013-10-19 |archive-url=https://web.archive.org/web/20131019182403/http://intelligence.org/files/AIPosNegFactor.pdf |url-status=live }}</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 |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 99:

==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, 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). 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 volume 23, pp. 207–214.

==External links==