Friendly artificial intelligence (also friendly AI or FAI) refers to hypothetical

artificial general intelligence Artificial general intelligence (AGI) is the ability of an intelligent agent to understand or learn any intellectual task that a human being can. It is a primary goal of some artificial intelligence research and a common topic in science fictio ...

(AGI) that would have a positive (benign) effect on humanity or at least align with human interests or contribute to foster the improvement of the human species. It is a part of the

ethics of artificial intelligence The ethics of artificial intelligence is the branch of the ethics of technology specific to artificially intelligent systems. It is sometimes divided into a concern with the moral behavior of ''humans'' as they design, make, use and treat artific ...

and is closely related to

machine ethics Machine ethics (or machine morality, computational morality, or computational ethics) is a part of the ethics of artificial intelligence concerned with adding or ensuring moral behaviors of man-made machines that use artificial intelligence, otherw ...

. While machine ethics is concerned with how an artificially intelligent agent ''should'' behave, friendly artificial intelligence research is focused on how to practically bring about this behaviour and ensuring it is adequately constrained.

Etymology and usage

Eliezer Yudkowsky, Stanford 2006 (square crop)

The term was coined by

Eliezer Yudkowsky Eliezer Shlomo Yudkowsky (born September 11, 1979) is an American decision theory and artificial intelligence (AI) researcher and writer, best known for popularizing the idea of friendly artificial intelligence. He is a co-founder and research ...

, who is best known for popularizing the idea, to discuss superintelligent artificial agents that reliably implement human values.

Stuart J. Russell Stuart Jonathan Russell (born 1962) is a British computer scientist known for his contributions to artificial intelligence (AI). He is a professor of computer science at the University of California, Berkeley and was from 2008 to 2011 an adjunct ...

and

Peter Norvig Peter Norvig (born December 14, 1956) is an American computer scientist and Distinguished Education Fellow at the Stanford Institute for Human-Centered AI. He previously served as a director of research and search quality at Google. Norvig is t ...

's leading

artificial intelligence Artificial intelligence (AI) is intelligence—perceiving, synthesizing, and inferring information—demonstrated by machines, as opposed to intelligence displayed by animals and humans. Example tasks in which this is done include speech re ...

textbook, '' Artificial Intelligence: A Modern Approach'', describes the idea:

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.

'Friendly' is used in this context as

technical terminology Jargon is the specialized terminology associated with a particular field or area of activity. Jargon is normally employed in a particular Context (language use), communicative context and may not be well understood outside that context. The conte ...

, and picks out agents that are safe and useful, not necessarily ones that are "friendly" in the colloquial sense. The concept is primarily invoked in the context of discussions of recursively self-improving artificial agents that rapidly explode in intelligence, on the grounds that this hypothetical technology would have a large, rapid, and difficult-to-control impact on human society.

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 A golem ( ; he, , gōlem) is an animated, anthropomorphic being in Jewish folklore, which is entirely created from inanimate matter (usually clay or mud). The most famous golem narrative involves Judah Loew ben Bezalel, the late 16th-century ...

, or the proto-robots of

Gerbert of Aurillac Pope Sylvester II ( – 12 May 1003), originally known as Gerbert of Aurillac, was a French-born scholar and teacher who served as the bishop of Rome and ruled the Papal States from 999 to his death. He endorsed and promoted study of Arab and Gre ...

and

Roger Bacon Roger Bacon (; la, Rogerus or ', also '' Rogerus''; ), also known by the scholastic accolade ''Doctor Mirabilis'', was a medieval English philosopher and Franciscan friar who placed considerable emphasis on the study of nature through empiri ...

. 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. By 1942 these themes prompted

Isaac Asimov yi, יצחק אזימאװ , birth_date = , birth_place = Petrovichi, Russian SFSR , spouse = , relatives = , children = 2 , death_date = , death_place = Manhattan, New York City, U.S. , nationality = Russian (1920–1922)Soviet (192 ...

to create the "

Three Laws of Robotics The Three Laws of Robotics (often shortened to The Three Laws or known as Asimov's Laws) are a set of rules devised by science fiction author Isaac Asimov. The rules were introduced in his 1942 short story " Runaround" (included in the 1950 colle ...

"—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. In modern times as the prospect of

superintelligent AI A superintelligence is a hypothetical agent that possesses intelligence far surpassing that of the brightest and most gifted human minds. "Superintelligence" may also refer to a property of problem-solving systems (e.g., superintelligent language ...

looms nearer, philosopher

Nick Bostrom Nick Bostrom ( ; sv, Niklas Boström ; born 10 March 1973) is a Swedish-born philosopher at the University of Oxford known for his work on existential risk, the anthropic principle, human enhancement ethics, superintelligence risks, and the rev ...

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:

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.'

In 2008 Eliezer Yudkowsky called for the creation of "friendly AI" to mitigate

existential risk from advanced artificial intelligence Existential risk from artificial general intelligence is the hypothesis that substantial progress in artificial general intelligence (AGI) could result in human extinction or some other unrecoverable global catastrophe. It is argued that the hum ...

. 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."

Steve Omohundro Stephen Malvern Omohundro (born 1959) is an American computer scientist whose areas of research include Hamiltonian physics, dynamical systems, programming languages, machine learning, machine vision, and the social implications of artificial int ...

says that a sufficiently advanced AI system will, unless explicitly counteracted, exhibit a number of 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.

Alexander Wissner-Gross Alexander D. Wissner-Gross is an American research scientist and entrepreneur. He is a fellow at the Institute for Applied Computational Science at Harvard University. Education At the Massachusetts Institute of Technology, where he researched na ...

says that AIs driven to maximize their future freedom of action (or causal path entropy) might be considered friendly if their planning horizon is longer than a certain threshold, and unfriendly if their planning horizon is shorter than that threshold. Luke Muehlhauser, writing for the

Machine Intelligence Research Institute The Machine Intelligence Research Institute (MIRI), formerly the Singularity Institute for Artificial Intelligence (SIAI), is a non-profit research institute focused since 2005 on identifying and managing potential existential risks from artific ...

, recommends that

researchers adopt what

Bruce Schneier Bruce Schneier (; born January 15, 1963) is an American cryptographer, computer security professional, privacy specialist, and writer. Schneier is a Lecturer in Public Policy at the Harvard Kennedy School and a Fellow at the Berkman Klein Cente ...

has called the "security mindset": Rather than thinking about how a system will work, imagine how it could fail. For instance, he suggests even an AI that only makes accurate predictions and communicates via a text interface might cause unintended harm. In 2014, Luke Muehlhauser and Nick Bostrom underlined the need for 'friendly AI'; nonetheless, the difficulties in designing a 'friendly' superintelligence, for instance via programming counterfactual moral thinking, are considerable.

Coherent extrapolated volition

Yudkowsky advances the Coherent Extrapolated Volition (CEV) model. According to him, coherent extrapolated volition is people's choices and the actions people would collectively take if "we knew more, thought faster, were more the people we wished we were, and had grown up closer together." 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 Human nature is a concept that denotes the fundamental dispositions and characteristics—including ways of thinking, feeling, and acting—that humans are said to have naturally. The term is often used to denote the essence of humankind, or ...

and then produce the AI which humanity would want, given sufficient time and insight, to arrive at a satisfactory answer. The appeal to an objective through contingent human nature (perhaps expressed, for mathematical purposes, in the form of a

utility function As a topic of economics, utility is used to model worth or value. Its usage has evolved significantly over time. The term was introduced initially as a measure of pleasure or happiness as part of the theory of utilitarianism by moral philosopher ...

or other decision-theoretic formalism), as providing the ultimate criterion of "Friendliness", is an answer to the

meta-ethical In metaphilosophy and ethics, meta-ethics is the study of the nature, scope, and meaning of moral judgment. It is one of the three branches of ethics generally studied by philosophers, the others being normative ethics (questions of how one ought ...

problem of defining an objective morality; extrapolated volition is intended to be what humanity objectively would want, all things considered, but it can only be defined relative to the psychological and cognitive qualities of present-day, unextrapolated humanity.

Other approaches

has proposed a "scaffolding" approach to AI safety, in which one provably safe AI generation helps build the next provably safe generation.

Seth Baum Seth Baum is an American researcher involved in the field of risk research. He is the executive director of the Global Catastrophic Risk Institute (GCRI), a think tank focused on existential risk. He is also affiliated with the Blue Marble Space I ...

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, and so can be constrained by extrinsic measures and motivated by intrinsic measures. Intrinsic motivations can be strengthened when messages resonate with AI developers; Baum argues that, in contrast, "existing messages about beneficial AI are not always framed well". Baum advocates for "cooperative relationships, and positive framing of AI researchers" and cautions against characterizing AI researchers as "not want(ing) to pursue beneficial designs". In his book ''

Human Compatible ''Human Compatible: Artificial Intelligence and the Problem of Control'' is a 2019 non-fiction book by computer scientist Stuart J. Russell. It asserts that risk to humanity from advanced artificial intelligence (AI) is a serious concern despit ...

'', AI researcher

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: The "preferences" Russell refers to "are all-encompassing; they cover everything you might care about, arbitrarily far into the future." Similarly, "behavior" includes any choice between options, and the uncertainty is such that some probability, which may be quite small, must be assigned to every logically possible human preference.

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 The Asilomar Conference on Recombinant DNA was an influential conference organized by Paul Berg, Maxine Singer, and colleagues to discuss the potential biohazards and regulation of biotechnology, held in February 1975 at a conference center at Asi ...

, which discussed risks of biotechnology. 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 The National Institutes of Health, commonly referred to as NIH (with each letter pronounced individually), is the primary agency of the United States government responsible for biomedical and public health research. It was founded in the late ...

, 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

, which generally aims to avoid government involvement in friendly AI. According to

Gary Marcus Gary F. Marcus (born February 8, 1970) is a professor emeritus of psychology and neural science at New York University. In 2014 he founded Geometric Intelligence, a machine-learning company later acquired by Uber. Marcus's books include '' Guita ...

, the annual amount of money being spent on developing machine morality is tiny.

Criticism

Some critics believe that both human-level AI and superintelligence are unlikely, and that therefore friendly AI is unlikely. Writing in ''

The Guardian ''The Guardian'' is a British daily newspaper. It was founded in 1821 as ''The Manchester Guardian'', and changed its name in 1959. Along with its sister papers ''The Observer'' and ''The Guardian Weekly'', ''The Guardian'' is part of the Gu ...

'', Alan Winfield compares human-level artificial intelligence with faster-than-light travel in terms of difficulty, and states that while we need to be "cautious and prepared" given the stakes involved, we "don't need to be obsessing" about the risks of superintelligence. Boyles and Joaquin, on the other hand, argue that Luke Muehlhauser and

’s proposal to create friendly AIs appear to be bleak. This is because Muehlhauser and Bostrom seem to hold the idea that intelligent machines could be programmed to think counterfactually about the moral values that humans beings would have had. In an article in ''

AI & Society ''AI & Society'' is a quarterly peer-reviewed scientific journal published by Springer. The editor-in-chief is Karamjit S. Gill, Brighton University. ''AI & Society'' has been running since 1987. It covers all aspects of artificial intelligence a ...

'', Boyles and Joaquin maintain that such AIs would not be that friendly considering the following: the infinite amount of antecedent counterfactual conditions that would have to be programmed into a machine, the difficulty of cashing out the set of moral values—that is, those that are more ideal than the ones human beings possess at present, and the apparent disconnect between counterfactual antecedents and ideal value consequent. 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. Other critics question whether it is possible for an artificial intelligence to be friendly. Adam Keiper and Ari N. Schulman, editors of the technology journal '' The New Atlantis'', say that it will be impossible to ever guarantee "friendly" behavior in AIs because problems of ethical complexity will not yield to software advances or increases in computing power. They write that the criteria upon which friendly AI theories are based work "only when one has not only great powers of prediction about the likelihood of myriad possible outcomes, but certainty and consensus on how one values the different outcomes.

References

External links

Ethical Issues in Advanced Artificial Intelligence
by Nick Bostrom
What is Friendly AI?
— A brief description of Friendly AI by the Machine Intelligence Research Institute.
Creating Friendly AI 1.0: The Analysis and Design of Benevolent Goal Architectures
— A near book-length description from the MIRI

— by Bill Hibbard
Commentary on MIRI's Guidelines on Friendly AI
— by Peter Voss.
The Problem with ‘Friendly’ Artificial Intelligence
— On the motives for and impossibility of FAI; by Adam Keiper and Ari N. Schulman. {{DEFAULTSORT:Friendly Artificial Intelligence Philosophy of artificial intelligence Singularitarianism Transhumanism Affective computing