Friendly AI
   HOME
*



picture info

Friendly AI
Friendly artificial intelligence (also friendly AI or FAI) refers to hypothetical artificial general intelligence (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 and is closely related to machine ethics. 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 The term was coined by Eliezer Yudkowsky, who is best known for popularizing the idea, to discuss superintelligent artificial agents that reliably implement human values. Stuart J. Russell and Peter Norvig's leading artificial intelligence textbook, '' Artificial Intelligence: A Modern Approach'', describes the idea: Yudkowsky (2008) goes into more detail ...
[...More Info...]      
[...Related Items...]     OR:     [Wikipedia]   [Google]   [Baidu]  


picture info

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 fiction and futures studies. AGI is also called strong AI,: Kurzweil describes strong AI as "machine intelligence with the full range of human intelligence." full AI, or general intelligent action, although some academic sources reserve the term "strong AI" for computer programs that experience sentience or consciousness. Strong AI contrasts with '' weak AI'' (or ''narrow AI''), which is not intended to have general cognitive abilities; rather, weak AI is any program that is designed to solve exactly one problem. (Academic sources reserve "weak AI" for programs that do not experience consciousness or do not have a mind in the same sense people do.) A 2020 survey identified 72 active AGI R&D projects spread across 37 countries. Characteristics ...
[...More Info...]      
[...Related Items...]     OR:     [Wikipedia]   [Google]   [Baidu]  


picture info

Superintelligence
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 translators or engineering assistants) whether or not these high-level intellectual competencies are embodied in agents that act in the world. A superintelligence may or may not be created by an intelligence explosion and associated with a technological singularity. University of Oxford philosopher Nick Bostrom defines ''superintelligence'' as "any intellect that greatly exceeds the cognitive performance of humans in virtually all domains of interest". The program Fritz falls short of superintelligence—even though it is much better than humans at chess—because Fritz cannot outperform humans in other tasks. Following Hutter and Legg, Bostrom treats superintelligence as general dominance at goal-oriented behavior, leaving open whether ...
[...More Info...]      
[...Related Items...]     OR:     [Wikipedia]   [Google]   [Baidu]  




Moral Universalism
Moral universalism (also called moral objectivism) is the meta-ethical position that some system of ethics, or a universal ethic, applies universally, that is, for "all similarly situated individuals", regardless of culture, race, sex, religion, nationality, sexual orientation, gender identity, or any other distinguishing feature. Moral universalism is opposed to moral nihilism and moral relativism. However, not all forms of moral universalism are absolutist, nor are they necessarily value monist; many forms of universalism, such as utilitarianism, are non-absolutist, and some forms, such as that of Isaiah Berlin, may be value pluralist. In addition to the theories of moral realism, moral universalism includes other cognitivist moral theories, such as the subjectivist ideal observer theory and divine command theory, and also the non-cognitivist moral theory of universal prescriptivism. Overview According to philosophy professor R. W. Hepburn: "To move towards the ...
[...More Info...]      
[...Related Items...]     OR:     [Wikipedia]   [Google]   [Baidu]  


Metaethics
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 to be and act) and applied ethics (practical questions of right behavior in given, usually contentious, situations). While normative ethics addresses such questions as "What should I do?", evaluating specific practices and principles of action, meta-ethics addresses questions such as "What ''is'' goodness?" and "How can we tell what is good from what is bad?", seeking to understand the assumptions underlying normative theories. Another distinction often made is that normative ethics involves first-order or substantive questions; meta-ethics involves second-order or formal questions. Some theorists argue that a metaphysical account of morality is necessary for the proper evaluation of actual moral theories and for making practical moral d ...
[...More Info...]      
[...Related Items...]     OR:     [Wikipedia]   [Google]   [Baidu]  


Decision Theory
Decision theory (or the theory of choice; not to be confused with choice theory) is a branch of applied probability theory concerned with the theory of making decisions based on assigning probabilities to various factors and assigning numerical consequences to the outcome. There are three branches of decision theory: # Normative decision theory: Concerned with the identification of optimal decisions, where optimality is often determined by considering an ideal decision-maker who is able to calculate with perfect accuracy and is in some sense fully rational. # Prescriptive decision theory: Concerned with describing observed behaviors through the use of conceptual models, under the assumption that those making the decisions are behaving under some consistent rules. # Descriptive decision theory: Analyzes how individuals actually make the decisions that they do. Decision theory is closely related to the field of game theory and is an interdisciplinary topic, studied by economi ...
[...More Info...]      
[...Related Items...]     OR:     [Wikipedia]   [Google]   [Baidu]  


picture info

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 philosophers such as Jeremy Bentham and John Stuart Mill. The term has been adapted and reapplied within neoclassical economics, which dominates modern economic theory, as a utility function that represents a single consumer's preference ordering over a choice set but is not comparable across consumers. This concept of utility is personal and based on choice rather than on pleasure received, and so is specified more rigorously than the original concept but makes it less useful (and controversial) for ethical decisions. Utility function Consider a set of alternatives among which a person can make a preference ordering. The utility obtained from these alternatives is an unknown function of the utilities obtained from each alternative, not the s ...
[...More Info...]      
[...Related Items...]     OR:     [Wikipedia]   [Google]   [Baidu]  


picture info

Evolutionary Psychology
Evolutionary psychology is a theoretical approach in psychology that examines cognition and behavior from a modern evolutionary perspective. It seeks to identify human psychological adaptations with regards to the ancestral problems they evolved to solve. In this framework, psychological traits and mechanisms are either functional products of natural and sexual selection, non-adaptive by-products of other adaptive traits, or noise. Adaptationist thinking about physiological mechanisms, such as the heart, lungs, and the liver, is common in evolutionary biology. Evolutionary psychologists apply the same thinking in psychology, arguing that just as the heart evolved to pump blood, and the liver evolved to detoxify poisons, there is modularity of mind in that different psychological mechanisms evolved to solve different adaptive problems. These evolutionary psychologists argue that much of human behavior is the output of psychological adaptations that evolved to solve recurren ...
[...More Info...]      
[...Related Items...]     OR:     [Wikipedia]   [Google]   [Baidu]  


picture info

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 what it 'means' to be human. This usage has proven to be controversial in that there is dispute as to whether or not such an essence actually exists. Arguments about human nature have been a central focus of philosophy for centuries and the concept continues to provoke lively philosophical debate. While both concepts are distinct from one another, discussions regarding human nature are typically related to those regarding the comparative importance of genes and environment in human development (i.e., ' nature versus nurture'). Accordingly, the concept also continues to play a role in academic fields, such as the natural sciences, social sciences, history, and philosophy, in which various theorists claim to have yielded insight into hu ...
[...More Info...]      
[...Related Items...]     OR:     [Wikipedia]   [Google]   [Baidu]  


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 Center for Internet & Society as of November, 2013. He is a board member of the Electronic Frontier Foundation, Access Now, and The Tor Project; and an advisory board member of Electronic Privacy Information Center and VerifiedVoting.org. He is the author of several books on general security topics, computer security and cryptography and is a squid enthusiast. In 2015, Schneier received the EPIC Lifetime Achievement Award from Electronic Privacy Information Center. Early life Bruce Schneier is the son of Martin Schneier, a Brooklyn Supreme Court judge. He grew up in the Flatbush neighborhood of Brooklyn, New York, attending P.S. 139 and Hunter College High School. After receiving a physics bachelor's degree from the University of Rocheste ...
[...More Info...]      
[...Related Items...]     OR:     [Wikipedia]   [Google]   [Baidu]  


picture info

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 artificial general intelligence. MIRI's work has focused on a friendly AI approach to system design and on predicting the rate of technology development. History In 2000, Eliezer Yudkowsky founded the Singularity Institute for Artificial Intelligence with funding from Brian and Sabine Atkins, with the purpose of accelerating the development of artificial intelligence (AI). However, Yudkowsky began to be concerned that AI systems developed in the future could become superintelligent and pose risks to humanity, and in 2005 the institute moved to Silicon Valley and began to focus on ways to identify and manage those risks, which were at the time largely ignored by scientists in the field. Starting in 2006, the Institute organized the Singulari ...
[...More Info...]      
[...Related Items...]     OR:     [Wikipedia]   [Google]   [Baidu]  




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 nanotechnology, Wissner-Gross triple-majored in physics, electrical engineering and mathematics. He was awarded the Marshall Scholarship, and was the last student to triple-major at MIT before the option was discontinued. Wissner-Gross also has a Ph.D in physics from Harvard University. Entrepreneurship In 2007, Wissner-Gross founded the technology company CO2Stats, which measures the amount of carbon dioxide emitted by using a website. CO2Stats is based in Cambridge, Massachusetts, and received funding from the seed venture capital firm Y Combinator. The company attracted controversy when Wissner-Gross was reported to have claimed, which he has denied, that a single Google search emitted seven grams of , which Google disputed. Activities W ...
[...More Info...]      
[...Related Items...]     OR:     [Wikipedia]   [Google]   [Baidu]  


Instrumental Convergence
Instrumental convergence is the hypothetical tendency for most sufficiently intelligent beings (both human and non-human) to pursue similar sub-goals, even if their ultimate goals are quite different. More precisely, agents (beings with agency) may pursue instrumental goals—goals which are made in pursuit of some particular end, but are not the end goals themselves—without end, provided that their ultimate (intrinsic) goals may never be fully satisfied. Instrumental convergence posits that an intelligent agent with unbounded but apparently harmless goals can act in surprisingly harmful ways. For example, a computer with the sole, unconstrained goal of solving an incredibly difficult mathematics problem like the Riemann hypothesis could attempt to turn the entire Earth into one giant computer in an effort to increase its computational power so that it can succeed in its calculations. Proposed basic AI drives include utility function or goal-content integrity, self-protection, ...
[...More Info...]      
[...Related Items...]     OR:     [Wikipedia]   [Google]   [Baidu]