Making good decisions depends on having accurate information – quickly, and in a form in which it can be readily communicated and acted upon. Two features of medical practice can help: deliberation in groups and the use of scores and grades in evaluation. We study the contributions of these features using a multi-agent computer simulation of groups of physicians. One might expect individual differences in members’ grading standards to reduce the capacity of the group to discover the facts on which (...) well-informed decisions depend. Observations of the simulated groups suggest on the contrary that this kind of diversity can in fact be conducive to epistemic performance. Sometimes, it is adopting common standards that may be expected to result in poor decisions. (shrink)

Mandevillian intelligence is a specific form of collective intelligence in which individual cognitive shortcomings, limitations and biases play a positive functional role in yielding various forms of collective cognitive success. When this idea is transposed to the epistemological domain, mandevillian intelligence emerges as the idea that individual forms of intellectual vice may, on occasion, support the epistemic performance of some form of multi-agent ensemble, such as a socio-epistemic system, a collective doxastic agent, or an (...) epistemic group agent. As a specific form of collective intelligence, mandevillian intelligence is relevant to a number of debates in social epistemology, especially those that seek to understand how group (or collective) knowledge arises from the interactions between a collection of individual epistemic agents. Beyond this, however, mandevillian intelligence raises issues that are relevant to the research agendas of both virtue epistemology and applied epistemology. From a virtue epistemological perspective, mandevillian intelligence encourages us to adopt a relativistic conception of intellectual vice/virtue, enabling us to see how individual forms of intellectual vice may (sometimes) be relevant to collective forms of intellectual virtue. In addition, mandevillian intelligence is relevant to the nascent sub-discipline of applied epistemology. In particular, mandevillian intelligence forces us see the potential epistemic value of (e.g., technological) interventions that create, maintain or promote individual forms of intellectual vice. (shrink)

This eleventh volume of Collected Papers includes 90 papers comprising 988 pages on Physics, Artificial Intelligence, Health Issues, Decision Making, Economics, Statistics, written between 2001-2022 by the author alone or in collaboration with the following 84 co-authors (alphabetically ordered) from 19 countries: Abhijit Saha, Abu Sufian, Jack Allen, Shahbaz Ali, Ali Safaa Sadiq, Aliya Fahmi, Atiqa Fakhar, Atiqa Firdous, Sukanto Bhattacharya, Robert N. Boyd, Victor Chang, Victor Christianto, V. Christy, Dao The Son, Debjit Dutta, Azeddine Elhassouny, Fazal Ghani, Fazli (...) Amin, Anirudha Ghosha, Nasruddin Hassan, Hoang Viet Long, Jhulaneswar Baidya, Jin Kim, Jun Ye, Darjan Karabašević, Vasilios N. Katsikis, Ieva Meidutė-Kavaliauskienė, F. Kaymarm, Nour Eldeen M. Khalifa, Madad Khan, Qaisar Khan, M. Khoshnevisan, Kifayat Ullah,, Volodymyr Krasnoholovets, Mukesh Kumar, Le Hoang Son, Luong Thi Hong Lan, Tahir Mahmood, Mahmoud Ismail, Mohamed Abdel-Basset, Siti Nurul Fitriah Mohamad, Mohamed Loey, Mai Mohamed, K. Mohana, Kalyan Mondal, Muhammad Gulfam, Muhammad Khalid Mahmood, Muhammad Jamil, Muhammad Yaqub Khan, Muhammad Riaz, Nguyen Dinh Hoa, Cu Nguyen Giap, Nguyen Tho Thong, Peide Liu, Pham Huy Thong, Gabrijela Popović‬‬‬‬‬‬‬‬‬‬, Surapati Pramanik, Dmitri Rabounski, Roslan Hasni, Rumi Roy, Tapan Kumar Roy, Said Broumi, Saleem Abdullah, Muzafer Saračević, Ganeshsree Selvachandran, Shariful Alam, Shyamal Dalapati, Housila P. Singh, R. Singh, Rajesh Singh, Predrag S. Stanimirović, Kasan Susilo, Dragiša Stanujkić, Alexandra Şandru, Ovidiu Ilie Şandru, Zenonas Turskis, Yunita Umniyati, Alptekin Ulutaș, Maikel Yelandi Leyva Vázquez, Binyamin Yusoff, Edmundas Kazimieras Zavadskas, Zhao Loon Wang.‬‬‬‬. (shrink)

ABSTRACT. The paper explores the philosophical intelligibility of contemporary defences of collective political forgiveness against a background of sceptical doubt, both general and particular. Three genera sceptical arguments are examined: one challenges the idea that political collectives exist; another challenges the idea that moral agency can be projected upon political collectives; a final argument challenges the attribution of emotions, especially anger, to collectives. Each of these sceptical arguments is rebutted. At a more particular level, the contrasts between individual forgiveness (...) and collective forgiveness gives rise to various problems and the ‘desiderata’ for their resolution - authority, specificity and temporal proximity - are briefly explored. (shrink)

There is a common misconception across the lntelligence Community (IC) to the effect that information trapped within multiple heterogeneous data silos can be semantically integrated by the sorts of meaning-blind statistical methods employed in much of artificial intelligence (Al) and natural language processlng (NLP). This leads to the misconception that incoming data can be analysed coherently by relying exclusively on the use of statistical algorithms and thus without any shared framework for classifying what the data are about. Unfortunately, such (...) approaches do not yield sustainable results where we are dealing with widely distributed, highly heterogeneous and often changing bodies of data. We argue here that the needed integration requires the use of what we call an lntegrating Semantic Framework (ISF), which provldes a consistent set of categories and relationships that can be reused over and over again to tag successive bodies of data in ways which foster more coherent representation and reasoning. (shrink)

2022 UPDATE: The approach of this monograph has been updated and developed further in Appendix II, "Epistemological Intelligence," of the author’s 2021 book _Critique of Impure Reason: Horizons of Possibility and Meaning_. The book is available both in a printed edition (under ISBN 978-0-578-88646-6 from Barnes & Noble, Amazon, and other booksellers) and an Open Access eBook edition (available through Philpapers under the book’s title and other philosophy online archives). ●●●●● -/- The monograph’s twofold purpose is to recognize epistemological (...) intelligence as a distinguishable variety of human intelligence, one that is especially important to philosophers, and to understand the challenges posed by the psychological profile of philosophers that can impede the development and cultivation of the skills associated with epistemological intelligence. (shrink)

In this paper, I provide an overview of today’s philosophical approaches to the problem of “intelligence” in the field of artificial intelligence by examining several important papers on phenomenology and the philosophy of biology such as those on Heideggerian AI, Jonas's metabolism model, and slime mold type intelligence.

The intelligence cycle is a set of processes used to provide useful information for decision-making. The cycle consists of several processes. The related counter-intelligence area is tasked with preventing information efforts from others. A basic model of the process of collecting and analyzing information is called the "intelligence cycle". This model can be applied, and, like all the basic models, it does not reflect the fullness of real-world operations. Through intelligence cycle activities, information is collected and (...) assembled, raw information is transformed into processed information, analyzed and made available to users. DOI: 10.13140/RG.2.2.25665.81760. (shrink)

Methodology, in intelligence, consists of the methods used to make decisions about threats, especially in the intelligence analysis discipline. The enormous amount of information collected by intelligence agencies often puts them in the inability to analyze them all. The US intelligence community collects over one billion daily information. The nature and characteristics of the information gathered as well as their credibility also have an impact on the intelligence analysis. Clark proposed a methodology for analyzing information (...) by addressing the target-centric intelligence cycle as an alternative to the traditional information cycle. DOI: 10.13140/RG.2.2.23471.89769. (shrink)

The analysts are in the field of "knowledge". Intelligence refers to knowledge and the types of problems addressed are knowledge problems. So, we need a concept of work based on knowledge. We need a basic understanding of what we know and how we know, what we do not know, and even what can be known and what is not known. The analysis should provide a useful basis for conceptualizing intelligence functions, of which the most important are "estimation" and (...) "prediction". The intelligence itself, in its basic form, has a decision-making function. Intelligence analysis applies individual and collective cognitive methods to assess data and test assumptions in a secret socio-cultural context. DOI: 10.13140/RG.2.2.25298.40646. (shrink)

This book is a collection of all the papers published in the special issue “Artificial Intelligence, Robots, and Philosophy,” Journal of Philosophy of Life, Vol.13, No.1, 2023, pp.1-146. The authors discuss a variety of topics such as science fiction and space ethics, the philosophy of artificial intelligence, the ethics of autonomous agents, and virtuous robots. Through their discussions, readers are able to think deeply about the essence of modern technology and the future of humanity. All papers were invited (...) and completed in spring 2020, though because of the Covid-19 pandemic and other problems, the publication was delayed until this year. I apologize to the authors and potential readers for the delay. I hope that readers will enjoy these arguments on digital technology and its relationship with philosophy. *** -/- Contents*** -/- Introduction : Descartes and Artificial Intelligence; Masahiro Morioka*** -/- Isaac Asimov and the Current State of Space Science Fiction : In the Light of Space Ethics; Shin-ichiro Inaba*** -/- Artificial Intelligence and Contemporary Philosophy : Heidegger, Jonas, and Slime Mold; Masahiro Morioka*** -/- Implications of Automating Science : The Possibility of Artificial Creativity and the Future of Science; Makoto Kureha*** -/- Why Autonomous Agents Should Not Be Built for War; István Zoltán Zárdai*** -/- Wheat and Pepper : Interactions Between Technology and Humans; Minao Kukita*** -/- Clockwork Courage : A Defense of Virtuous Robots; Shimpei Okamoto*** -/- Reconstructing Agency from Choice; Yuko Murakami*** -/- Gushing Prose : Will Machines Ever be Able to Translate as Badly as Humans?; Rossa Ó Muireartaigh***. (shrink)

Is there a field of social intelligence? Many various disciplines ap-proach the subject and it may only seem natural to suppose that different fields of study aim at explaining different phenomena; in other words, there is no spe-cial field of study of social intelligence. In this paper, I argue for an opposite claim. Namely, there is a way to integrate research on social intelligence, as long as one accepts the mechanistic account to explanation. Mechanistic inte-gration of different (...) explanations, however, comes at a cost: mechanism requires explanatory models to be fairly complete and realistic, and this does not seem to be the case for many models concerning social intelligence, especially models of economical behavior. Such models need either be made more realistic, or they would not count as contributing to the same field. I stress that the focus on integration does not lead to ruthless reductionism; on the contrary, mechanistic explanations are best understood as explanatorily pluralistic. (shrink)

Artificial intelligence has arrived. In the online world it is already a part of everyday life, sitting invisibly behind a wide range of search engines and online commerce sites. It offers huge potential to enable more efficient and effective business and government but the use of artificial intelligence brings with it important questions about governance, accountability and ethics. Realising the full potential of artificial intelligence and avoiding possible adverse consequences requires societies to find satisfactory answers to these (...) questions. This report sets out some possible approaches, and describes some of the ways government is already engaging with these issues. (shrink)

Imagine you are the CEO of a hospital [. . .]. Decisions are constantly being made in your organization about how to spend the organization's money. The amount of money available to spend is never adequate to pay for everything you wish you could spend it on, therefore you must set spending priorities. There are two questions you need to be able to answer . . . How should we set priorities in this organization? How do we know when we (...) are doing it well? When people seek to achieve good public policy, the result will tend to be good public policy. In a collective choice process, public‐spirited individual participants produce good public policy by deliberating—talking with each other, listening to each other's arguments, and being willing to learn and change their minds based on such dialogue. –Steven Kelman (1992: 181) Public policy scholars agree that those persons (or agencies) vested with the authority to establish health care priorities should elicit public input before making rationing decisions. The two most common approaches are (i) consultation and (ii) deliberation. Though deliberation has obvious advantages over consultation, it falters in the face of the objection that ordinary citizens lack the cognitive resources for the extended, rigorous inquiry required of them in undertaking the priority‐setting task. To overcome this objection, I propose that deliberative forums for health care rationing should be designed so that they imitate the natural pattern of human experience. The experience of deliberation should encompass both prolonged periods of less‐demanding cognitive activity, in which citizens passively receive information, and briefer periods of more‐demanding cognitive activity, in which they engage in active problem‐solving. In arguing for this thesis, I rely on two theoretical sources and one practical case study, in the following order: (i) John Dewey's metaphysics of experience, (ii) cognitive science research on schemas and frames, and (iii) the Health Care Council in São Paulo, Brazil. (shrink)

This selective review explores biologically inspired learning as a model for intelligent robot control and sensing technology on the basis of specific examples. Hebbian synaptic learning is discussed as a functionally relevant model for machine learning and intelligence, as explained on the basis of examples from the highly plastic biological neural networks of invertebrates and vertebrates. Its potential for adaptive learning and control without supervision, the generation of functional complexity, and control architectures based on self-organization is brought forward. Learning (...) without prior knowledge based on excitatory and inhibitory neural mechanisms accounts for the process through which survival-relevant or task-relevant representations are either reinforced or suppressed. The basic mechanisms of unsupervised biological learning drive synaptic plasticity and adaptation for behavioral success in living brains with different levels of complexity. The insights collected here point toward the Hebbian model as a choice solution for “intelligent” robotics and sensor systems. Keywords: Hebbian learning; synaptic plasticity; neural networks; self-organization; brain; reinforcement; sensory processing; robot control . (shrink)

I develop a contractualist theory of just intelligence collection based on the collective moral responsibility to deliver security to a community and use the theory to justify certain kinds of signals interception. I also consider the rights of various intelligence targets like intelligence officers, service personnel, government employees, militants, and family members of all of these groups in order to consider how targets' waivers or forfeitures might create the moral space for just surveillance. Even people who (...) are not doing anything prejudicial to other states' security can be modeled as ceding rights against diagnostic collection--light touch collection limited to ascertaining if someone is likely an intelligence threat--as part of their duty to support just foreign institutions. Foreign intelligence officers could not perform the same job potential targets can reasonably demand their intelligence agencies perform on their behalf without this ceding of rights. More invasive forms of collection can only be justified if officers can reasonably model their citizens consenting to being the target of the same sort of collection by adversary states. (shrink)

For several years, scholars have (for good reason) been largely preoccupied with worries about the use of artificial intelligence and machine learning (AI/ML) tools to make decisions about us. Only recently has significant attention turned to a potentially more alarming problem: the use of AI/ML to influence our decision-making. The contexts in which we make decisions—what behavioral economists call our choice architectures—are increasingly technologically-laden. Which is to say: algorithms increasingly determine, in a wide variety of contexts, both the sets (...) of options we choose from and the way those options are framed. Moreover, artificial intelligence and machine learning (AI/ML) makes it possible for those options and their framings—the choice architectures—to be tailored to the individual chooser. They are constructed based on information collected about our individual preferences, interests, aspirations, and vulnerabilities, with the goal of influencing our decisions. At the same time, because we are habituated to these technologies we pay them little notice. They are, as philosophers of technology put it, transparent to us—effectively invisible. I argue that this invisible layer of technological mediation, which structures and influences our decision-making, renders us deeply susceptible to manipulation. Absent a guarantee that these technologies are not being used to manipulate and exploit, individuals will have little reason to trust them. (shrink)

Inspired by recent progress in multi-agent Reinforcement Learning (RL), in this work we examine the collective intelligent behaviour of theoretical universal agents by introducing a weighted mixture operation. Given a weighted set of agents, their weighted mixture is a new agent whose expected total reward in any environment is the corresponding weighted average of the original agents' expected total rewards in that environment. Thus, if RL agent intelligence is quantified in terms of performance across environments, the weighted mixture's (...) intelligence is the weighted average of the original agents' intelligences. This operation enables various interesting new theorems that shed light on the geometry of RL agent intelligence, namely: results about symmetries, convex agent-sets, and local extrema. We also show that any RL agent intelligence measure based on average performance across environments, subject to certain weak technical conditions, is identical (up to a constant factor) to performance within a single environment dependent on said intelligence measure. (shrink)

Intelligence analysis has many important epistemological resemblances with science (problem solving, discovery, skillful use of tools, knowledge verification) and is more interested in a posteriori than a priori knowledge, on how or the basis on which a proposition may be known. The puzzle metaphor is used in both information and archeology. Both disciplines involve collecting evidence to build as complete a picture as possible. The process of converting raw information into actionable processed intelligence is almost identical for governmental (...) and business organizations. The medical practice of diagnosing identification, collection, analysis and dissemination is similar to that of intelligence. DOI: 10.13140/RG.2.2.26511.12963. (shrink)

Position: (1) Partial solutions to machine intelligence can lead to systems which may be useful creating interesting and expressive musical works. (2) An appropriate general goal for this field is augmenting human expression. (3) The study of the aesthetics of human augmentation in musical performance is in its infancy. -/- CHI 2015 Workshop on Collaborating with Intelligent Machines: Interfaces for Creative Sound, April 18, 2015, Seoul, Republic of Korea.

Bringing together literary scholars, computer scientists, ethicists, philosophers of mind, and scholars from affiliated disciplines, this collection of essays offers important and timely insights into the pasts, presents, and, above all, possible futures of Artificial Intelligence. This book covers topics such as ethics and morality, identity and selfhood, and broader issues about AI, addressing questions about the individual, social, and existential impacts of such technologies. Through the works of science fiction authors such as Isaac Asimov, Stanislaw Lem, Ann Leckie, (...) Iain M. Banks, and Martha Wells, alongside key visual productions such as Ex Machina, Westworld, and Her, contributions illustrate how science fiction might inform potential futures as well as acting as a springboard to bring disciplinary knowledge to bear on significant developments of Artificial Intelligence. Addressing a broad, interdisciplinary audience, both expert and non-expert readers gain an in-depth understanding of the wide range of pressing issues to which Artificial Intelligence gives rise, and the ways in which science fiction narratives have been used to represent them. Using science fiction in this manner enables readers to see how even fictional worlds and imagined futures have very real impacts on how we understand these technologies. As such, readers are introduced to theoretical positions on Artificial Intelligence through fictional works as well as encouraged to reflect on the diverse aspects of Artificial Intelligence through its many philosophical, social, legal, scientific, and cultural ramifications. (shrink)

Today, humanity is trying to turn the artificial intelligence that it produces into natural intelligence. Although this effort is technologically exciting, it often raises ethical concerns. Therefore, the intellectual ability of artificial intelligence will always bring new questions. Although there have been significant developments in the consciousness of artificial intelligence, the issue of consciousness must be fully explained in order to complete this development. When consciousness is fully understood by human beings, the subject of “free will” (...) will be explained. Therefore, human consciousness should be re-examined and perceptions that we are not aware of from a philosophical point of view should be examined. The relevance of the perceptions we do not realize to the unconscious, and finally the impact on consciousness goes back to the sources of philosophy. Hegel, in particular, we may find information about these perceptions unusual. Consciousness cannot be separated from the unconscious. Consciousness should be rethought in the context of memory models and unconscious in this sense. Seeing how Hegel's human cognition acts, especially in Hegel's perception, raises the unconscious question again. If we expect something different from an artificial intelligence, we need to rethink the artificial cognitive model. This paper argues that without the unconscious component of artificial intelligence, it cannot approach human cognition. -/- Key Words: Artificial Intelligence, Creativity, Memory, perception . (shrink)

Science deals with the physical aspect of reality; its subject matter is data that, in principle, can be collected solely by physical devices. If physical devices cannot measure something, then that something is not the subject matter of science. Of course, the whole of reality encompasses more than the physical.

The following looks at several problems and questions concerning our understanding of the word ‘intelligence’ and the phrase ‘artificial intelligence’ (AI), including: how to define these terms; whether intelligence can exist in AI; if artificial intelligence in AI is identifiable; and what (if any) kind of intelligence is important to AI.

Computers can mimic human intelligence, sometimes quite impressively. This has led some to claim that, a.) computers can actually acquire intelligence, and/or, b.) the human mind may be thought of as a very sophisticated computer. In this paper I argue that neither of these inferences are sound. The human mind and computers, I argue, operate on radically different principles.

The present study was carried out to study the emotional intelligence of Electrical Engineering students in Dire Dawa University Ethiopia. The sample for the study was 90 (30 Industrial control engineering streams, 30 Power system engineering streams, and 30 Communication engineering streams) randomly selected from Dire Dawa university, school of electrical and computer engineering. A sample scale was employed for the data collection and a t-test was employed for the analysis of data. The outcome of the study shows that (...) Industrial control engineering and Power system engineering students do not differ significantly on various dimensions of Emotional intelligence and Industrial control engineering and Communication engineering students do not differ significantly on various dimensions of Emotional intelligence and Power system engineering and Communication engineering students differ significantly on various dimensions of Emotional intelligence. (shrink)

Papers from the conference on AI Risk (published in JETAI), supplemented by additional work. --- If the intelligence of artificial systems were to surpass that of humans, humanity would face significant risks. The time has come to consider these issues, and this consideration must include progress in artificial intelligence (AI) as much as insights from AI theory. -- Featuring contributions from leading experts and thinkers in artificial intelligence, Risks of Artificial Intelligence is the first volume of (...) collected chapters dedicated to examining the risks of AI. The book evaluates predictions of the future of AI, proposes ways to ensure that AI systems will be beneficial to humans, and then critically evaluates such proposals. 1 Vincent C. Müller, Editorial: Risks of Artificial Intelligence - 2 Steve Omohundro, Autonomous Technology and the Greater Human Good - 3 Stuart Armstrong, Kaj Sotala and Sean O’Heigeartaigh, The Errors, Insights and Lessons of Famous AI Predictions - and What they Mean for the Future - 4 Ted Goertzel, The Path to More General Artificial Intelligence - 5 Miles Brundage, Limitations and Risks of Machine Ethics - 6 Roman Yampolskiy, Utility Function Security in Artificially Intelligent Agents - 7 Ben Goertzel, GOLEM: Toward an AGI Meta-Architecture Enabling Both Goal Preservation and Radical Self-Improvement - 8 Alexey Potapov and Sergey Rodionov, Universal Empathy and Ethical Bias for Artificial General Intelligence - 9 András Kornai, Bounding the Impact of AGI - 10 Anders Sandberg, Ethics and Impact of Brain Emulations 11 Daniel Dewey, Long-Term Strategies for Ending Existential Risk from Fast Takeoff - 12 Mark Bishop, The Singularity, or How I Learned to Stop Worrying and Love AI -. (shrink)

Our digital society increasingly relies in the power of others’ aggregated judgments to make decisions. Questions as diverse as which film we will watch, what scientific news we will decide to read, which path we will follow to find a place, or what political candidate we will vote for are usually associated to a rating that influences our final decisions.

Nowadays, the economic and social nature of contemporary business organizations chiefly banks binds them to face with the sheer volume of data and information and the key to commercial success in this area is the proper use of data for making better, faster and flawless decisions. To achieve this goal organizations requires strong and effective tools to enable them in automating task analysis, decision-making, strategy formulation and risk prediction to prevent bankruptcy and fraud .Business Intelligence is a set of (...) skills, technologies and application systems used to collect, store, analyze and create effective access to the task to help organizations better understand the business context and make accurate decision timely and respond quickly toward inflation, rate fluctuations and the market price. In this paper we review recent literature in the search for trends in business intelligence applications for the banking industry and its challenges and finally some articles that comprise this special issue are introduced and characterized in terms of business intelligence research framework. (shrink)

About the analogy between the epistemological and methodological aspects of the activity of intelligence agencies and some scientific disciplines, advocating for a more scientific approach to the process of collecting and analyzing information within the intelligence cycle. I assert that the theoretical, ontological and epistemological aspects of the activity of many intelligence agencies are underestimated, leading to incomplete understanding of current phenomena and confusion in inter-institutional collaboration. After a brief Introduction, which includes a history of the evolution (...) of the intelligence concept after World War II, Intelligence Activity defines the objectives and organization of intelligence agencies, the core model of these organizations (the intelligence cycle), and the relevant aspects of the intelligence gathering and intelligence analysis. In the Ontology section, I highlight the ontological aspects and the entities that threaten and are threatened. The Epistemology section includes aspects specific to intelligence activity, with the analysis of the traditional (Singer) model, and a possible epistemological approach through the concept of tacit knowledge developed by scientist Michael Polanyi. In the Methodology section there are various methodological theories with an emphasis on structural analytical techniques, and some analogies with science, archeology, business and medicine. In Conclusions I argue on the possibility of a more scientific approach to methods of intelligence gathering and analysis of intelligence agencies. -/- ISBN 978-606-033-219-0, DOI: 10.58679/MM58823. (shrink)

Forests, cars and orchestras are very different ontological entities, and yet very similar in some aspects. The relationships they have with the elements they are composed of is often assumed to be reducible to standard ontological relations, like parthood and constitution, but how this could be done is still debated. This paper sheds light on the issue starting from a linguistic and philosophical analysis aimed at understanding notions like plurality, collective and composite, and propos- ing a formal approach to (...) characterise them. We conclude the presentation with a discussion and analysis of social groups within this framework. (shrink)

Instinct and Intelligence is an essay about creative writing. The two elements of the title are present in human thought in general, but the writing process - especially in philosophy - pushes them to extremes. Through this process we can notice and document the nature of each side, conceptualising them in order to create a structural description of thought's creation that may become operative within creation itself.

The discussion and debates around Ethical AI cannot simply ignore the fact that ethics is not a self-standing discipline by is part of Philosophy and can only be approached as such.

A subdiscipline has emerged around AI ethics, which is comprised of a wide array of individuals: computer scientists, ethicists, cognitive scientists, roboticists, legal professionals, economists, sociologists, gender, and race theorists. This has led to a very interesting branch of research, addressing issues surrounding the development and use of AI. This chapter will give a very brief snapshot of some of the most pertinent ethical concerns. Many of the issues in the Big Data Ethics chapter in this collection are often applicable (...) to AI ethics, because of the data that these technologies retrieve, store, and use, so will not be duplicated here.1 -/- While data-related issues are not new or unique to AI, AI does hold the potential to dramatically retrieve and analyze data that would not be possible otherwise. Data is being used in unique and transformative ways, such as the use of facial recognition to identify individuals from photos or CCTV; AI robots to retrieve live video feed about the patient(s) that it is monitoring; or in new ways, such as self-driving cars collecting an abundance of data about our surroundings, how we drive, and passengers in the car. There is the potential to infringe on individuals’ privacy, restriction of resources, or at worst, the creation of a surveillance society. (shrink)

Borrowing the functional modeling approach common in systems and software engineering, an implementable model of the functions of human consciousness proposed to have the capacity for general problem solving ability transferable to any domain, or true self-aware intelligence, is presented. Being a functional model that is independent of implementation, this model is proposed to also be applicable to artificial consciousness, and to platforms that organize individuals into what is defined here as a first order collective consciousness, or at (...) higher orders into what is defined here as Nth order collective consciousness. Part I of this two-part article includes: Summary; Introduction; Set of Postulates One; Set of Postulates Two; Overview of the Model; Model of Homeostasis; Model of the Functional Units; Model of the Body System; Model of the Other Basic Life Processes; Model of the Other Functional Systems; Model of Perceptions in the Perceptual Fields; Model of Body Processes as Paths in the Perceptual Field; & Model of Conscious Awareness. (shrink)

Some prominent scientists and philosophers have stated openly that moral and political considerations should influence whether we accept or promulgate scientific theories. This widespread view has significantly influenced the development, and public perception, of intelligence research. Theories related to group differences in intelligence are often rejected a priori on explicitly moral grounds. Thus the idea, frequently expressed by commentators on science, that science is “self-correcting”—that hypotheses are simply abandoned when they are undermined by empirical evidence—may not be correct (...) in all contexts. In this paper, documentation spanning from the early 1970s to the present is collected, which reveals the influence of scientists’ moral and political commitments on the study of intelligence. It is suggested that misrepresenting findings in science to achieve desirable social goals will ultimately harm both science and society. (shrink)

THE CASE FOR GOVERNMENT BY ARTIFICIAL INTELLIGENCE. Tired of election madness? The rhetoric of politicians? Their unreliable promises? And less than good government? -/- Until recently, it hasn’t been hard for people to give up control to computers. Not very many people miss the effort and time required to do calculations by hand, to keep track of their finances, or to complete their tax returns manually. But relinquishing direct human control to self-driving cars is expected to be more of (...) a challenge, despite the predicted decrease in vehicle accidents thanks to artificial intelligence that isn’t subject to human distractions and errors of judgment. -/- If turning vehicle control over to artificial intelligence is a challenge, it is a very mild one compared with the idea that we might one day recognize and want to implement the advantages of human government by AI. But, like autonomous vehicle control, government by AI is likely to offer decided benefits. -/- In other publications, the author has studied a variety of widespread human limitations that, throughout human history, have led to much human suffering as well as ecological destruction. For the first time, these psychological and cognitive human shortcomings are taken into account in an essay that makes the case for government by artificial intelligence. (shrink)

The content of this paper is an elaboration of Hubert L. Dreyfus’s philosophical critique of Artificial Intelligence (AI), computers and the internet. Hubert L. Dreyfus (1929-2017) is Ua SA philosopher and alumni of Harvard University who teach at the Massachusetts Institute of Technology (MIT) and University of California, Berkeley. He is a phenomenological philosopher who criticize computer researchers and the artificial intelligence community. In 1965, Dreyfus wrote an article for Rand Corporation titled “Alchemy and Artificial Intelligence” which (...) criticizes the masterminds of Artificial Intelligence. Dreyfus also criticized the order of computers via two books: (1) What Computers Can’t Do (1972) and (2) What Computers Stills Can’t Do (1992). He favored human intuition rather than the computer logic in his book Mind over Machine: The Power of Human Intuition and Expertise in the Era of the Computer (1986). In 2001, Dreyfus wrote a book On the Internet, which considers the prominent phenomenon in the recent Industry 4.0. By elaborating on Dreyfus’s philosophy on the computer, artificial intelligence, and the internet, we will know the philosophical debate on the result of industry 3.0 (computer and artificial intelligence) and 4.0 (artificial intelligence and internet). Moreover, we will know the relation between humans and those industrial products. (shrink)

The method of supergrading is introduced for deriving a ranking of items from scores or grades awarded by several people. Individual inputs may come in different languages of grades. Diversity in grading standards is an advantage, enabling rankings derived by this method to separate more items from one another. A framework is introduced for studying grading on the basis of observations. Measures of accuracy, reliability and discrimination are developed within this framework. Ability in grading is characterized for individuals and groups (...) as the capacity to grade reliably, accurately and at a high level of discrimination. It is shown that the collective ability of a supergrading group with diverse standards can be greater than that of a less diverse group whose members have greater ability. (shrink)

Commonsense reasoning is one of the main open problems in the field of Artificial Intelligence (AI) while, on the other hand, seems to be a very intuitive and default reasoning mode in humans and other animals. In this talk, we discuss the different paradigms that have been developed in AI and Computational Cognitive Science to deal with this problem (ranging from logic-based methods, to diagrammatic-based ones). In particular, we discuss - via two different case studies concerning commonsense categorization and (...) knowledge invention tasks - how cognitively inspired heuristics can help (both in terms of efficiency and efficacy) in the realization of intelligent artificial systems able to reason in a human-like fashion, with results comparable to human-level performances. (shrink)

This article argues that the creation of artificial offspring could make our lives more meaningful. By ‘artificial offspring’ I mean beings that we construct, with a mix of human and non-human-like qualities. Robotic artificial intelligences are paradigmatic examples of the form. There are two reasons for thinking that the creation of such beings could make our lives more meaningful and valuable. The first is that the existence of a collective afterlife—i.e. a set of human-like lives that continue after we (...) die—is likely to be an important source and sustainer of meaning in our present lives. The second is that the creation of artificial offspring provides a plausible and potentially better pathway to a collective afterlife than the traditional biological pathway. Both of these arguments are defended from a variety of objections and misunderstandings. (shrink)

Moses deviced healthy laws to keep his people united as a nation. Moses is , alongside with Plato, Aristotle, Mahomet, Kung Fu, Lao Tse and Cicero, one of the "intelligent designers" of mankind in the last 5.000 years.

What follows is a contribution to the horizontal integration of warfighter intelligence data as defined in Chairman of the Joint Chiefs of Staff Instruction J2 CJCSI 3340.02AL: -/- Horizontally integrating warfighter intelligence data improves the consumers’ production, analysis and dissemination capabilities. HI requires access (including discovery, search, retrieval, and display) to intelligence data among the warfighters and other producers and consumers via standardized services and architectures. These consumers include, but are not limited to, the combatant commands, Services, (...) Defense agencies, and the Intelligence Community. (shrink)

I propose a framework, derived from moral theory, for assessing the moral status of intelligent machines. Using this framework, I claim that some current and foreseeable intelligent machines have approximately as much moral status as plants, trees, and other environmental entities. This claim raises the question: what obligations could a moral agent (e.g., a normal adult human) have toward an intelligent machine? I propose that the threshold for any moral obligation should be the "functional morality" of Wallach and Allen [20], (...) while the upper limit of our obligations should not exceed the upper limit of our obligations toward plants, trees, and other environmental entities. (shrink)

Since the noun phrase `artificial intelligence' (AI) was coined, it has been debated whether humans are able to create intelligence using technology. We shed new light on this question from the point of view of themodynamics and mathematics. First, we define what it is to be an agent (device) that could be the bearer of AI. Then we show that the mainstream definitions of `intelligence' proposed by Hutter and others and still accepted by the AI community are (...) too weak even to capture what is involved when we ascribe intelligence to an insect. We then summarise the highly useful definition of basic (arthropod) intelligence proposed by Rodney Brooks, and we identify the properties that an AI agent would need to possess in order to be the bearer of intelligence by this definition. Finally, we show that, from the perspective of the disciplines needed to create such an agent, namely mathematics and physics, these properties are realisable by neither implicit nor explicit mathematical design nor by setting up an environment in which an AI could evolve spontaneously. (shrink)

In making sense of the world, we typically cooperate, join forces, and draw on one another’s competence and expertise. A group or community in which there is a well-functioning division of cognitive-epistemic labor can achieve levels of understanding that a single agent who relies exclusively on her own capacities would probably never achieve. However, is understanding also collective? I.e., is understanding something that can be possessed by a group or community rather than by individuals? In this paper, I develop (...) an account of understanding phenomena according to which understanding a phenomenon requires reasonably endorsing an adequate and intelligible epistemic mediator that accounts for this phenomenon. I then show that understanding, conceived along these lines, can be attributed to collective entities. An important result of my arguments will be that a collective entity’s understanding cannot (always) be reduced to the sum of the understandings of the individuals belonging to it. This is because a collective entity can sometimes be rightfully claimed to understand a phenomenon while none of its individual members understands it. (shrink)

This article analyzes emerging artificial intelligence (AI)-enhanced lie detection systems from ethical and human resource (HR) management perspectives. I show how these AI enhancements transform lie detection, followed with analyses as to how the changes can lead to moral problems. Specifically, I examine how these applications of AI introduce human rights issues of fairness, mental privacy, and bias and outline the implications of these changes for HR management. The changes that AI is making to lie detection are altering the (...) roles of human test administrators and human subjects, adding machine learning-based AI agents to the situation and establishing invasive data collection processes as well as introducing certain biases in results. I project that the potentials for pervasive and continuous lie detection initiatives (“truth machines”) are substantial, displacing human-centered efforts to establish trust and foster integrity in organizations. I argue that if it is possible for HR managers to do so, they should cease using technologically-based lie detection systems entirely and work to foster trust and accountability on a human scale. However, if these AI-enhanced technologies are put into place by organizations by law, agency mandate, or other compulsory measures, care should be taken that the impacts of the technologies on human rights and wellbeing are considered. The article explores how AI can displace the human agent in some aspects of lie detection and credibility assessment scenarios, expanding the prospects for inscrutable, “black box” processes and novel physiological constructs (such as “biomarkers of deceit”) that may increase the potential for such human rights concerns as fairness, mental privacy, and bias. Employee interactions with autonomous lie detection systems rather with than human beings who administer specific tests can reframe organizational processes and rules concerning the assessment of personal honesty and integrity. The dystopian projection of organizational life in which analyses and judgments of the honesty of one’s utterances are made automatically and in conjunction with one’s personal profile provides unsettling prospects for the autonomy of self-representation. (shrink)

In this work, we will approach some of the essential questions about the collective imaginary and their relations with reality and truth. We should face this subject in a conceptual framework, followed by the corresponding factual analysis of demonstrable behavioral realities. We will adopt not only the methodology, but mostly the tenets and propositions of the analytic philosophy, which for sure will be apparent throughout the study, and may be identified by the features described by Perez : Rabossi (1975) (...) defends the idea that analytic philosophy can be identified by considering certain family resemblances. He suggests the following family traits: a positive attitude toward scientific knowledge; a cautious attitude toward metaphysics; a conception of philosophy as a conceptual task, which takes conceptual analysis as a method; a close relationship between language and philosophy; a concern with seeking argumentative answers to philosophical problems; search for conceptual clarity Perez, Diana Ines, "Analytic Philosophy in Latin America”, The Stanford Encyclopedia of Philosophy ). These core concepts involve cultural, social, religious, scientific, philosophic, moral, and political contents, belonging to the individual and collective existence of each one of us. In this paper, we will not debate nor demonstrate. Our purpose is not to systematically methodize, criticize, or bring to evidence anything, anyhow. The present work grounds itself on analytical reflection. We will just speculate the most comprehensive and profound way we can and express the results of our thoughts. Notwithstanding the multidisciplinary nature of the subject and the methodological openness for accepting contributions from any field of science, this work belongs to the aim of psychology and ontology or, in other terms, social and ontological psychology. The free methodology guiding such reflections embraces and takes into account everything approaching coherence with the philosophical and psychological epistemology. This methodology does not pursue reaching evidence but just looks for the interrelation among already existing evidence, of any nature and magnitude, inferring a coherent meaning to the real things. Many of the great thinkers at any time never searched for demonstrations, theorizations, or systematizations. These thinkers just thought, meditated, and with the enlightenment of their humility could approach the truth. They will be our reference and the example to be followed. For sure, we will not find the truth, but we may be sure about something: in many moments, we will get close to the truth, and in all moments, we will be retreating from untruth and lie. The main scope of this paper is to observe how some of the essential evolutionary attributes of humankind, like creativity, imagination, and association, can become a hazardous sickness, sheltered in the misty shadows of the intelligence. (shrink)

The impossibility results in judgement aggregation show a clash between fair aggregation procedures and rational collective outcomes. In this paper, we are interested in analysing the notion of rational outcome by proposing a proof-theoretical understanding of collective rationality. In particular, we use the analysis of proofs and inferences provided by linear logic in order to define a fine-grained notion of group reasoning that allows for studying collective rationality with respect to a number of logics. We analyse the (...) well-known paradoxes in judgement aggregation and we pinpoint the reasoning steps that trigger the inconsistencies. Moreover, we extend the map of possibility and impossibility results in judgement aggregation by discussing the case of substructural logics. In particular, we show that there exist fragments of linear logic for which general possibility results can be obtained. (shrink)