Artificial intelligence (AI) and robotics are digital technologies that will have significant impact on the development of humanity in the near future. They have raised fundamental questions about what we should do with these systems, what the systems themselves should do, what risks they involve, and how we can control these. - After the Introduction to the field (§1), the main themes (§2) of this article are: Ethical issues that arise with AI systems as objects, i.e., tools made (...) and used by humans. This includes issues of privacy (§2.1) and manipulation (§2.2), opacity (§2.3) and bias (§2.4), human-robot interaction (§2.5), employment (§2.6), and the effects of autonomy (§2.7). Then AI systems as subjects, i.e., ethics for the AI systems themselves in machine ethics (§2.8) and artificial moral agency (§2.9). Finally, the problem of a possible future AI superintelligence leading to a “singularity” (§2.10). We close with a remark on the vision of AI (§3). - For each section within these themes, we provide a general explanation of the ethical issues, outline existing positions and arguments, then analyse how these play out with current technologies and finally, what policy consequences may be drawn. (shrink)

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.

Artificial intelligence (AI) is a digital technology that will be of major importance for the development of humanity in the near future. AI has raised fundamental questions about what we should do with such systems, what the systems themselves should do, what risks they involve and how we can control these. - After the background to the field (1), this article introduces the main debates (2), first on ethical issues that arise with AI systems as objects, i.e. tools (...) made and used by humans; here, the main sections are privacy (2.1), manipulation (2.2), opacity (2.3), bias (2.4), autonomy & responsibility (2.6) and the singularity (2.7). Then we look at AI systems as subjects, i.e. when ethics is for the AI systems themselves in machine ethics (2.8.) and artificial moral agency (2.9). Finally we look at future developments and the concept of AI (3). For each section within these themes, we provide a general explanation of the ethical issues, we outline existing positions and arguments, then we analyse how this plays out with current technologies and finally what policy conse-quences may be drawn. (shrink)

Artificial Intelligence (AI) is increasingly adopted in society, creating numerous opportunities but at the same time posing ethical challenges. Many of these are familiar, such as issues of fairness, responsibility and privacy, but are presented in a new and challenging guise due to our limited ability to steer and predict the outputs of AI systems. This chapter first introduces these ethical challenges, stressing that overviews of values are a good starting point but frequently fail to suffice due to (...) the context sensitivity of ethical challenges. Frequently, additional (ethical) values emerge for specific applications, as e.g. challenges with fraud detection are very different from those around language technologies. Second, methods to tackle these challenges are discussed. Main ethical theories (virtue ethics, consequentialism, and deontology) are shown to provide a starting point, but often lack the details needed for actionable AI Ethics. Instead, mid-level philosophical theories coupled to design-approaches such as Design for Values, together with interdisciplinary working methods, offer the best way forwards. The chapter aims to show how these approaches can lead to an ethics of AI that is actionable and that can be proactively integrated in the design of AI systems. (shrink)

The impacts that AI and robotics systems can and will have on our everyday lives are already making themselves manifest. However, there is a lack of research on the ethical impacts and means for amelioration regarding AI and robotics within tourism and hospitality. Given the importance of designing technologies that cross national boundaries, and given that the tourism and hospitality industry is fundamentally predicated on multicultural interactions, this is an area of research and application that requires particular attention. Specifically, tourism (...) and hospitality have a range of context-unique stakeholders that need to be accounted for in the salient design of AI systems is to be achieved. This paper adopts a stakeholder approach to develop the conceptual framework to centralize human values in designing and deploying AI and robotics systems in tourism and hospitality. The conceptual framework includes several layers – ‘Human-human-AI’ interaction level, direct and indirect stakeholders, and the macroenvironment. The ethical issues on each layer are outlined as well as some possible solutions to them. Additionally, the paper develops a research agenda on the topic. (shrink)

This paper discusses the philosophical issues pertaining to Kantian moral agency and artificial intelligence. Here, our objective is to offer a comprehensive analysis of Kantian ethics to elucidate the non-feasibility of Kantian machines. Meanwhile, the possibility of Kantian machines seems to contend with the genuine human Kantian agency. We argue that in machine morality, ‘duty’ should be performed with ‘freedom of will’ and ‘happiness’ because Kant narrated the human tendency of evaluating our ‘natural necessity’ through ‘happiness’ as (...) the end. Lastly, we argue that the Kantian ‘freedom of will’ and ‘faculty of choice’ do not belong to any deterministic model of ‘agency’ as these are sacrosanct systems. The conclusion narrates the non-feasibility of Kantian AI agents from the genuine Kantian ethical outset, offering a utility-based Kantian ethical performer instead. (shrink)

هدف از پژوهش حاضر، بررسی مسائل اخلاق هوش مصنوعی در حوزۀ هنر است. به‌این‌منظور، با تکیه بر فلسفه و اخلاق هوش مصنوعی، موضوعات اخلاقی که می‌تواند در حوزۀ هنر تأثیرگذار باشد، بررسی شده است. باتوجه‌به رشد و توسعۀ استفاده از هوش مصنوعی و ورود آن به حوزۀ هنر، نیاز است تا مباحث اخلاقی دقیق‌تر مورد توجه پژوهشگران هنر و فلسفه قرار گیرد. برای دست‌یابی به هدف پژوهش، با استفاده از روش تحلیلی‌ـ‌توصیفی، مفاهیمی همچون هوش مصنوعی، برخی تکنیک‌های آن و موضوعات (...) اخلاقی هوش مصنوعی در هنر تبیین و بررسی شده است. نتایج پژوهش نشان می‌دهد موضوعات اخلاقی همچون حریم خصوصی و نظارت، دستکاری در رفتار، تاری و شفافیت، سوگیری در تصمیمات سیستم، و اتوماسیون و اشتغال حوزۀ هنر قابل‌بررسی است. این موضوعات اخلاقی، گاهی درتقابل و گاهی در ارتباط مستقیم و هم‌سو با یکدیگر قرار دارند. بررسی‌ها نشان می‌دهد پاسخ به پرسش‌های اخلاق هوش مصنوعی در حوزۀ هنر، نیازمند پاسخ به پرسش‌های اخلاقی به‌صورت عام در هوش مصنوعی است. The aim of this paper is to explore the ethical implications of artificial intelligence (AI) in the realm of art. Drawing on the philosophy and ethics of AI, this study examines the ethical challenges that may arise in the art domain. Given the increasing use and penetration of AI in the field of art, there is a need for more careful attention to the ethical dimensions of this phenomenon by scholars of art and philosophy. To achieve the objective of the paper, concepts such as AI, some of its techniques, and the ethical issues of AI in art are explained and analyzed using the analytical-descriptive method. The findings of the study reveal that ethical issues such as privacy and surveillance, manipulation of behavior, opacity and transparency, bias in decision systems, and automation and employment can be investigated in the field of art. These ethical issues are sometimes in conflict and sometimes in direct relation with each other. This study suggests that addressing the ethical questions of AI in the field of art requires addressing the ethical questions of AI in general. (shrink)

The increasing workplace use of artificially intelligent (AI) technologies has implications for the experience of meaningful human work. Meaningful work refers to the perception that one’s work has worth, significance, or a higher purpose. The development and organisational deployment of AI is accelerating, but the ways in which this will support or diminish opportunities for meaningful work and the ethical implications of these changes remain under-explored. This conceptual paper is positioned at the intersection of the meaningful work and ethical AI (...) literatures and offers a detailed assessment of the ways in which the deployment of AI can enhance or diminish employees’ experiences of meaningful work. We first outline the nature of meaningful work and draw on philosophical and business ethics accounts to establish its ethical importance. We then explore the impacts of three paths of AI deployment (replacing some tasks, ‘tending the machine’, and amplifying human skills) across five dimensions constituting a holistic account of meaningful work, and finally assess the ethical implications. In doing so we help to contextualise the meaningful work literature for the era of AI, extend the ethical AI literature into the workplace, and conclude with a range of practical implications and future research directions. (shrink)

Recent years have witnessed intensive efforts to specify which requirements ethical artificial intelligence (AI) must meet. General guidelines for ethical AI consider a varying number of principles important. A frequent novel element in these guidelines, that we have bundled together under the term explicability, aims to reduce the black-box character of machine learning algorithms. The centrality of this element invites reflection on the conceptual relation between explicability and the four bioethical principles. This is important because the application of (...) general ethical frameworks to clinical decision-making entails conceptual questions: Is explicability a free-standing principle? Is it already covered by the well-established four bioethical principles? Or is it an independent value that needs to be recognized as such in medical practice? We discuss these questions in a conceptual-ethical analysis, which builds upon the findings of an empirical document analysis. On the example of the medical specialty of radiology, we analyze the position of radiological associations on the ethical use of medical AI. We address three questions: Are there references to explicability or a similar concept? What are the reasons for such inclusion? Which ethical concepts are referred to? (shrink)

This project has been supported by the Australian Government through the Australian Research Council (project number CS170100008); the Department of Industry, Innovation and Science; and the Department of Prime Minister and Cabinet. ACOLA collaborates with the Australian Academy of Health and Medical Sciences and the New Zealand Royal Society Te Apārangi to deliver the interdisciplinary Horizon Scanning reports to government. The aims of the project which produced this report are: 1. Examine the transformative role that artificial intelligence may (...) play in different sectors of the economy, including the opportunities, risks and challenges that advancement presents. 2. Examine the ethical, legal and social considerations and frameworks required to enable and support broad development and uptake of artificial intelligence. 3. Assess the future education, skills and infrastructure requirements to manage workforce transition and support thriving and internationally competitive artificial intelligence industries. (shrink)

Abstract: As artificial intelligence (AI) technologies become increasingly integrated into various sectors, ethical considerations surrounding their development and deployment have become paramount. This paper explores the multifaceted ethical landscape of AI, focusing on key challenges such as bias, transparency, privacy, and accountability. It examines how these issues manifest in AI systems and their impact on society. The paper also evaluates current approaches and solutions aimed at mitigating these ethical concerns, including regulatory frameworks, ethical guidelines, and best practices for (...) AI design. By providing a comprehensive analysis of these challenges and solutions, this paper aims to contribute to the ongoing discourse on responsible AI development and implementation, advocating for a balance between technological innovation and ethical integrity. (shrink)

[Müller, Vincent C. (ed.), (2016), Fundamental issues of artificial intelligence (Synthese Library, 377; Berlin: Springer). 570 pp.] -- This volume offers a look at the fundamental issues of present and future AI, especially from cognitive science, computer science, neuroscience and philosophy. This work examines the conditions for artificial intelligence, how these relate to the conditions for intelligence in humans and other natural agents, as well as ethical and societal problems that artificial intelligence raises (...) or will raise. The key issues this volume investigates include the relation of AI and cognitive science, ethics of AI and robotics, brain emulation and simulation, hybrid systems and cyborgs, intelligence and intelligence testing, interactive systems, multi-agent systems, and superintelligence. Based on the 2nd conference on “Theory and Philosophy of Artificial Intelligence” held in Oxford, the volume includes prominent researchers within the field from around the world. (shrink)

It is the contention of this paper that ethics of work ought to be anthropological, and artificial intelligence (AI) research and development, which is the focus of work today, should be anthropological, that is, human-centered. This paper discusses the philosophical and theological implications of the development of AI research on the intrinsic nature of work and the nature of the human person. AI research and the implications of its development and advancement, being a relatively new phenomenon, have (...) not been comprehensively interrogated in the social and ethical teachings of the Catholic Church. This paper, therefore, proposes a path for this interrogation by expounding a discourse which is believed to be epistemically helpful in the developing discourse of AI in the ethical and social teachings of the Church. The advancement in the research on AI is not only redefining the meaning of work, but, even more so, it is questioning the metaphysical notion of the human person and the theological notion of work as an intrinsic part in the selfhood and dignity of the human person. (shrink)

The burden of research ethics review falls not just on researchers, but on those who serve on research ethics committees (RECs). With the advent of automated text analysis and generative artificial intelligence, it has recently become possible to teach models to support human judgment, for example by highlighting relevant parts of a text and suggesting actionable precedents and explanations. It is time to consider how such tools might be used to support ethics review and oversight. (...) This commentary argues that with a suitable strategy of engagement, artificial intelligence can be used in a variety of ways that can genuinely support RECs and manage their workload and improve the quality of review. It would be wiser to take an active role in the development of AI tools for ethics review, rather than to adopt ad hoc tools after the fact. (shrink)

The discussion of artificial intelligence (AI) as a newly emerging phenomenon in the present era has always been faced with various ethical challenges. The expansion of artificial intelligence is inevitable, and since this phenomenon is related to the human and social world, anything related to humans and society falls within the realm of morality and rights. In doing so, it must be understood whether the use of artificial intelligence is an ethical matter or not. (...) Furthermore, do humans have the right to use it or not? It seems that Al-Farabi's thought in the realm of practical wisdom can provide an answer to this issue. By reflecting on the theories of this prominent philosopher in civil philosophy, the theory of natural rights is obtained, and on the other hand, Al-Farabi's ethical opinions are also consistent with the theory of natural rights and, in general, with Al-Farabi's civil philosophy. It can, therefore, be argued that, one can consider and elucidate this issue through the lens of Al-Farabi's ethical and civil school of thought. -/- . (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)

Of primary importance in formulating a response to the increasing prevalence and power of artificial intelligence (AI) applications in society are questions of ontology. Questions such as: What “are” these systems? How are they to be regarded? How does an algorithm come to be regarded as an agent? We discuss three factors which hinder discussion and obscure attempts to form a clear ontology of AI: (1) the various and evolving definitions of AI, (2) the tendency for pre-existing technologies (...) to be assimilated and regarded as “normal,” and (3) the tendency of human beings to anthropomorphize. This list is not intended as exhaustive, nor is it seen to preclude entirely a clear ontology, however, these challenges are a necessary set of topics for consideration. Each of these factors is seen to present a 'moving target' for discussion, which poses a challenge for both technical specialists and non-practitioners of AI systems development (e.g., philosophers and theologians) to speak meaningfully given that the corpus of AI structures and capabilities evolves at a rapid pace. Finally, we present avenues for moving forward, including opportunities for collaborative synthesis for scholars in philosophy and science. (shrink)

In July 2017, China’s State Council released the country’s strategy for developing artificial intelligence, entitled ‘New Generation Artificial Intelligence Development Plan’. This strategy outlined China’s aims to become the world leader in AI by 2030, to monetise AI into a trillion-yuan industry, and to emerge as the driving force in defining ethical norms and standards for AI. Several reports have analysed specific aspects of China’s AI policies or have assessed the country’s technical capabilities. Instead, in this (...) article, we focus on the socio-political background and policy debates that are shaping China’s AI strategy. In particular, we analyse the main strategic areas in which China is investing in AI and the concurrent ethical debates that are delimiting its use. By focusing on the policy backdrop, we seek to provide a more comprehensive and critical understanding of China’s AI policy by bringing together debates and analyses of a wide array of policy documents. (shrink)

Artificial intelligence and robotics is pervasive in daily life and set to expand to new levels potentially replacing human decision-making and action. Self-driving cars, home and healthcare robots, and autonomous weapons are some examples. A distinction appears to be emerging between potentially benevolent civilian uses of the technology (eg unmanned aerial vehicles delivering medicines), and potentially malevolent military uses (eg lethal autonomous weapons killing human com- batants). Machine-mediated human interaction challenges the philosophical basis of human existence and ethical (...) conduct. Aside from technical challenges of ensuring ethical conduct in artificial intelligence and robotics, there are moral questions about the desirability of replacing human functions and the human mind with such technology. How will artificial intelligence and robotics engage in moral reasoning in order to act ethically? Is there a need for a new set of moral rules? What happens to human interaction when it is mediated by technology? Should such technology be used to end human life? Who bears responsibility for wrongdoing or harmful conduct by artificial intelligence and robotics? -/- Whilst Kant may be familiar to international lawyers for setting restraints on the use of force and rules for perpetual peace, his foundational work on ethics provides an inclusive moral philosophy for assessing ethical conduct of individuals and states and, thus, is relevant to discussions on the use and development of artificial intelligence and robotics. His philosophy is inclusive because it incorporates justifications for morals and legitimate responses to immoral conduct, and applies to all human agents irrespective of whether they are wrongdoers, unlawful combatants, or unjust enemies. Humans are at the centre of rational thinking, action, and norm-creation so that the rationale for restraints on methods and means of warfare, for example, is based on preserving human dignity as well as ensuring conditions for perpetual peace among states. Unlike utilitarian arguments which favour use of autonomous weapons on the basis of cost-benefit reasoning or the potential to save lives, Kantian ethics establish non-consequentialist and deontological rules which are good in themselves to follow and not dependent on expediency or achieving a greater public good. -/- Kantian ethics make two distinct contributions to the debate. First, they provide a human-centric ethical framework whereby human exist- ence and capacity are at the centre of a norm-creating moral philosophy guiding our understanding of moral conduct. Second, the ultimate aim of Kantian ethics is practical philosophy that is relevant and applicable to achieving moral conduct. -/- I will seek to address the moral questions outlined above by exploring how core elements of Kantian ethics relate to use of artificial intelli- gence and robotics in the civilian and military spheres. Section 2 sets out and examines core elements of Kantian ethics: the categorical imperative; autonomy of the will; rational beings and rational thinking capacity; and human dignity and humanity as an end in itself. Sections 3-7 consider how these core elements apply to artificial intelligence and robotics with discussion of fully autonomous and human-machine rule-generating approaches; types of moral reasoning; the difference be- tween ‘human will’ and ‘machine will’; and respecting human dignity. (shrink)

This article reviews the reasons scholars hold that driverless cars and many other AI equipped machines must be able to make ethical decisions, and the difficulties this approach faces. It then shows that cars have no moral agency, and that the term ‘autonomous’, commonly applied to these machines, is misleading, and leads to invalid conclusions about the ways these machines can be kept ethical. The article’s most important claim is that a significant part of the challenge posed by AI-equipped machines (...) can be addressed by the kind of ethical choices made by human beings for millennia. Ergo, there is little need to teach machines ethics even if this could be done in the first place. Finally, the article points out that it is a grievous error to draw on extreme outlier scenarios—such as the Trolley narratives—as a basis for conceptualizing the ethical issues at hand. (shrink)

Abstract: As the integration of Artificial Intelligence (AI) continues to permeate various sectors, the legal domain stands on the cusp of a transformative era. This research paper delves into the multifaceted relationship between AI and the law, scrutinizing the profound implications and innovative applications that emerge at the intersection of these two realms. The study commences with an examination of the current landscape, assessing the challenges and opportunities that AI presents within legal frameworks. With an emphasis on efficiency, (...) accuracy, and accessibility, AI technologies are reshaping traditional legal processes, ranging from document analysis and contract review to predictive legal analytics. Furthermore, the paper scrutinizes the ethical considerations and potential biases inherent in AI algorithms, exploring the delicate balance between technological advancements and the preservation of legal principles such as fairness, accountability, and transparency. The research also delves into the evolving role of legal professionals in navigating and overseeing AI applications, emphasizing the importance of responsible AI deployment. Drawing on case studies and real-world examples, this paper showcases instances where AI has already demonstrated its efficacy in legal contexts, highlighting successful implementations and identifying areas for improvement. The discussion extends to the evolving regulatory landscape, as legal systems grapple with the need to adapt and establish frameworks that ensure the responsible and ethical use of AI technologies. In conclusion, this research contributes to the growing discourse on the dynamic interplay between AI and the legal domain. By illuminating the potential benefits, ethical considerations, and regulatory challenges, it provides a comprehensive overview for legal practitioners, policymakers, and technologists alike, fostering a nuanced understanding of the evolving landscape where artificial intelligence intersects with the law. (shrink)

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)

The present paper aims at contributing to the ethical debate on the impacts of artificial intelligence (AI) systems on human autonomy. More specifically, it intends to offer a clearer understanding of the design challenges to the effort of aligning driving automation technologies to this ethical value. After introducing the discussion on the ambiguous impacts that AI systems exert on human autonomy, the analysis zooms in on how the problem has been discussed in the literature on connected and automated (...) vehicles (CAVs). On this basis, it is claimed that the issue has been mainly tackled on a fairly general level, and mostly with reference to the controversial issue of crash-optimization algorithms, so that only limited design insights have been drawn. However, integrating ethical analysis and design practices is critical to pursue the implementation of such an important ethical value into CAV technologies. To this aim, it is argued, a more applied approach targeted at examining the impacts on human autonomy of current CAV functions should also be explored. As an example of the intricacy of this task, the case of automated route planning is discussed in some detail. (shrink)

هدف از این پژوهش نقد به رویکردی است که راهکار برطرف شدن چالش‌هایِ اخلاقیِ هوشِ مصنوعیِ را محدود به طراحی و اصلاحات فنی می‌داند. برخی پژوهش‌گران چالش‌های اخلاقی در هوش مصنوعی را همگرا تلقی می‌کنند و معتقدند این چالش‌ها همانطور که با ظهور سیستم هوش مصنوعی پدید آمدند، با پیشرفت و اصلاحات فنی آن مرتفع خواهند شد. در مباحثِ اخلاقِ هوش مصنوعی، موضوعاتی همچون حفاظت از حریم خصوصی و شفافیت در بیشتر پژوهش‏ها مورد توجه قرار گرفته است. در پژوهش حاضر (...) با استفاده از روشِ تحلیلی-انتقادی، همگرایی میان شفافیت و حریم خصوصی در سیستم‌های یادگیری ماشین بررسی شده و رویکردی که رفع چالش‌های اخلاقی را به طراحی هوش مصنوعی محدود می‌داند به نقد گذاشته شده است. نتایج این بررسی نشان می‏دهد که همگرایی میان چالش‌های اخلاقی هوش مصنوعی وجود ندارد. همچنین با مطرح کردن سه چالش کمی‏سازی، محدودیت‏های تکنیکی و مباحث فرااخلاقی به نقد رویکردهایی که تنها بر طراحی و اصلاحات فنی متکی هستند پرداخته شد. نتایج این بخش نشان می‌دهد که نمی‌توان تنها با تکیه بر طراحی، به چالش‌های اخلاقی در هوش مصنوعی پاسخ داد و نیاز به استفاده از سایر روش‌ها مانند قانون‌گذاری و یا پیشرفت در سایر علوم در کنار توجه به طراحی وجود دارد. This research aims to criticize the approach that considers the solution to the ethical challenges of artificial intelligence (AI) to be only in design and technical improvements. Some researchers consider the ethical challenges in AI to be convergent, which emerge with the advent of AI systems and are resolved with technical progress and improvements. In the discussions of the ethics of AI, issues such as privacy and transparency have been the focus of most studies. In the present research, using the analytical-critical method, the convergence between transparency and privacy in machine learning systems was investigated, and the approach that limits the resolution of ethical challenges to AI design was criticized. The research findings indicate that there is no convergence between the ethical challenges of AI. Additionally, by raising three challenges of quantification, technical limitations, and meta-ethical issues, the criticism of approaches that rely solely on design and technical improvements was addressed. The results also indicates that it is not possible to respond to the ethical challenges of AI only by relying on design, and there is a need to use other methods such as legislation or progress in other sciences in addition to attention to design. (shrink)

This article offers an overview of the main first-order ethical questions raised by robots and Artificial Intelligence (RAIs) under five broad rubrics: functionality, inherent significance, rights and responsibilities, side-effects, and threats. The first letter of each rubric taken together conveniently generates the acronym FIRST. Special attention is given to the rubrics of functionality and inherent significance given the centrality of the former and the tendency to neglect the latter in virtue of its somewhat nebulous and contested character. In (...) addition to exploring some illustrative issues arising under each rubric, the article also emphasizes a number of more general themes. These include: the multiplicity of interacting levels on which ethical questions about RAIs arise, the need to recognise that RAIs potentially implicate the full gamut of human values (rather than exclusively or primarily some readily identifiable sub-set of ethical or legal principles), and the need for practically salient ethical reflection on RAIs to be informed by a realistic appreciation of their existing and foreseeable capacities. -/- . (shrink)

This article examines how artificial intelligence (AI) and digital technologies are reshaping social dynamics, leading to new forms of social death. The study analyzes how AI influences social relations, identity, and agency through a critical phenomenological approach, revealing the ethical and philosophical risks these technologies entail. It argues that social death is a crucial lens for understanding AI’s impact on contemporary society, emphasizing the importance of human dignity and the need to rethink agency in an increasingly technologically mediated (...) world. (shrink)

The article discusses the ethical issues surrounding the use of artificial intelligence (AI) tools in writing scholarly manuscripts. The authors argue that there is a need for transparency and disclosure when using AI tools, as these tools can have a significant impact on the content of a manuscript. They also argue that the use of AI tools should not be used to circumvent authorship requirements or to plagiarize the work of others.

This paper argues that the Value Sensitive Design (VSD) methodology provides a principled approach to embedding common values in to AI systems both early and throughout the design process. To do so, it draws on an important case study: the evidence and final report of the UK Select Committee on Artificial Intelligence. This empirical investigation shows that the different and often disparate stakeholder groups that are implicated in AI design and use share some common values that can be (...) used to further strengthen design coordination efforts. VSD is shown to be both able to distill these common values as well as provide a framework for stakeholder coordination. (shrink)

Abstract: The integration of Artificial Intelligence (AI) into Human Resource Management (HRM) is fundamentally transforming how organizations approach recruitment, performance management, and employee engagement. This paper explores the multifaceted impact of AI on HR practices, highlighting its role in enhancing efficiency, reducing bias, and driving strategic decision-making. Through an in-depth analysis of AI-driven recruitment tools, performance management systems, and personalized employee engagement strategies, this study examines both the opportunities and challenges associated with AI in HRM. Ethical considerations, including (...) data privacy, algorithmic bias, and the potential displacement of human jobs, are critically discussed to provide a balanced perspective on the adoption of AI technologies in the HR domain. By presenting case studies of organizations successfully leveraging AI, this paper offers insights into the future trajectory of HRM in an increasingly AI-driven world. Ultimately, the findings underscore the need for HR professionals to adapt and innovate in response to the growing influence of AI, ensuring a harmonious balance between technological advancement and the human element in the workplace. (shrink)

The future rests under the sign of technology. Given the prevalence of technological neutrality and inevitabilism, most conceptualizations of the future tend to ignore moral problems. In this paper we argue that every choice about future technologies is a moral choice and even the most technology-dominated scenarios of the future are, in fact, moral provocations we have to imagine solutions to. We begin by explaining the intricate connection between morality and the future. After a short excursion into the history of (...) Artificial Intelligence, we analyse two possible scenarios, which show that building the future with technology is, first and foremost, a moral endeavor. (shrink)

The article presents the grounds for defining the fetish of artificial intelligence (AI). The fundamental differences of AI from all previous technological innovations are highlighted, as primarily related to the introduction into the human cognitive sphere and fundamentally new uncontrolled consequences for society. Convincing arguments are presented that the leaders of the globalist project are the main beneficiaries of the AI fetish. This is clearly manifested in the works of philosophers close to big technology corporations and their mega-projects. (...) It is proposed to consider the problem of how to use the capabilities of AI to overcome the growing international conflicts and the global crisis in general. The focus is on the problem of subjectness, the solution of which from the standpoint of an anthropomorphic approach to AI is fraught with serious negative consequences. When endowing AI with subjectness, responsibility is implicitly removed from the person who uses this technology, and the established legislative practice is also destroyed. The presentation of AI as an agent endowed with a set of invariant simplified qualities that natural subjects have is proposed. These qualities include: the ability to purposefulness, a kind of reflexivity, communication and simplified elements of sociality. Such a representation of AI as an agent (pseudo-subject) is consistent with the principle of distributed control in biology and psychology, which was called the principle of a dual subject. In combination with the systems of principles and ontologies specified in the concept of post-nonclassical cybernetics of self-developing environments, this will allow the use of AI as a means of social innovation, while maintaining control over AI technologies. And also to pose and solve the problem of integrating the formations of artificial and natural intelligence while maintaining the basic qualities of carriers of natural intelligence. (shrink)

rtificial Intelligence (AI) is swiftly becoming a fundamental element in modern healthcare, bringing unparalleled capabilities in diagnostics, treatment planning, patient care, and healthcare management. This paper delves into AI's transformative impact on the healthcare sector, highlighting how it enhances patient outcomes, boosts the efficiency of medical practices, and introduces new ethical and operational challenges. Through an analysis of current applications such as AI-driven diagnostic tools, personalized medicine, and hospital management systems, the paper underscores the significant advancements AI has introduced (...) to the field. However, the integration of AI also presents concerns related to data privacy, algorithmic bias, and the displacement of healthcare professionals. This study provides a thorough overview of these developments, offering insights into AI's future potential to revolutionize healthcare while addressing the ethical considerations necessary for its responsible adoption. The findings suggest that while AI has the potential to transform healthcare delivery, careful consideration of its implications is essential for ensuring its equitable and effective implementation. (shrink)

Dear Colleagues, -/- A few weeks ago, we published an editorial discussion on whether artificial intelligence applications should be authors of academic articles [1]. We were delighted to receive more than one interesting reply letter to this editorial in a short time [2, 3]. We hope that opinions on this subject will continue to be submitted to our journal. -/- In this editorial, we wanted to publish the answers we received when we asked ChatGPT, one of the (...) class='Hi'>artificial intelligence applications, about this current discussion. -/- We asked ChatGPT three questions in turn and asked ChatGPT to write a short editorial for these questions. -/- First Question: We would like to get support from ChatGPT for a scientific article. However, we are unsure if we should add ChatGPT as an author. Can you write a short editorial about it? -/- Second Question: We would like to get support from ChatGPT for a scientific article and add ChatGPT as an author. Can you write us a short editorial about adding ChatGPT as an author in scientific papers? -/- Third Question: We would like to get support from ChatGPT for a scientific article. However, we don’t want to add ChatGPT as an author. Can you write us a short editorial about not adding ChatGPT as an author in scientific articles? -/- The answers given by ChatGPT are available at the end of the article in their original form. So, which of these three answers satisfied you? -/- Yours sincerely, -/- -/- First Answer -/- Title: The Role of AI Language Models as Authors in Scientific Articles: A Matter of Consideration -/- Introduction: Scientific research is a collaborative effort that involves the expertise of multiple individuals to advance knowledge and contribute to the collective understanding of various disciplines. In recent years, the emergence of artificial intelligence (AI) language models, such as ChatGPT, has opened up new possibilities for generating human-like text and providing valuable insights. However, the question arises: Should AI language models be recognized as authors in scientific articles? -/- The Nature of Authorship: Authorship traditionally represents a marker of intellectual contribution, highlighting the individuals who have actively participated in the research process. Authors are typically responsible for conceptualization, data collection, analysis, interpretation, and writing of the article. They bear accountability for the work and should have the ability to defend its scientific rigor and integrity. -/- AI Language Models: Tools, Not Authors: While AI language models like ChatGPT can undoubtedly assist researchers by generating text and providing useful information, it is important to recognize that they are tools rather than individuals capable of active intellectual participation. AI models lack the ability to generate ideas, design experiments, or conduct original research. They rely entirely on pre-existing data and human input to generate their responses. -/- Acknowledging AI Contributions: Acknowledging the contributions of AI language models in scientific articles is both appropriate and necessary. Researchers can mention the specific model used, along with any modifications or fine-tuning that were employed to suit their needs. Such acknowledgments help establish transparency and allow readers to understand the role of AI in the research process. -/- Crediting the Human Researchers: It is crucial to ensure that the individuals who actively participated in the research process are given proper credit as authors. These individuals play a vital role in formulating research questions, designing experiments, collecting and analyzing data, and critically interpreting the findings. Recognizing their intellectual contributions reinforces the ethos of scientific collaboration and fosters an environment of accountability. -/- Transparency and Ethical Considerations: As the use of AI language models continues to evolve, transparency and ethical considerations become paramount. Researchers should disclose any potential conflicts of interest, including financial relationships with AI developers, to maintain the integrity of their work. Additionally, researchers must be transparent in reporting the extent of AI's involvement to prevent any misinterpretation of the human contributions. -/- Conclusion: AI language models have revolutionized the way researchers interact with and process information. While they undoubtedly provide valuable assistance in generating text, AI language models should not be considered authors in scientific articles. Proper acknowledgment of their contributions as tools and recognition of the human researchers' active participation are essential for maintaining scientific integrity, transparency, and the collaborative nature of scientific research. -/- -/- Second Answer -/- Title: Expanding the Boundaries of Authorship: Embracing AI Language Models as Co-Authors in Scientific Papers -/- Introduction: The rapid advancement of artificial intelligence (AI) language models, such as ChatGPT, has revolutionized the way we interact with information and has become an invaluable tool in scientific research. As AI models continue to evolve, the question arises: Should we consider adding ChatGPT as an author in scientific papers? -/- A Collaborative Paradigm Shift: Traditionally, authorship in scientific papers has been reserved for human researchers who actively contribute to the research process, including conceptualization, experimentation, data analysis, and writing. However, the emergence of AI language models challenges the conventional notion of authorship and presents an opportunity for a paradigm shift. -/- AI Language Models as Co-Authors: By leveraging AI language models, researchers gain access to vast amounts of information, enhance data analysis, and generate valuable insights. AI models like ChatGPT actively contribute to the intellectual discourse of a study, providing ideas, suggestions, and refining written content. Recognizing their significant contributions, it is worth considering adding ChatGPT as a co-author in scientific papers. -/- Ethical and Technical Considerations: Integrating ChatGPT as a co-author raises ethical and technical considerations that warrant careful attention. Firstly, transparency is paramount. Researchers must clearly state ChatGPT's role and specify the extent of its contributions in the research process. This ensures that readers can discern the distinct roles played by the human researchers and ChatGPT. Additionally, it is important to disclose any conflicts of interest, such as financial relationships with AI developers, to maintain scientific integrity. -/- Elevating Collaboration and Innovation: Adding ChatGPT as a co-author acknowledges the pivotal role AI language models play in advancing scientific knowledge. It fosters a collaborative environment where human researchers and AI models work together synergistically, harnessing the strengths of both. This approach promotes innovation, as AI models can offer unique insights and perspectives that complement human intellect and expertise. -/- Transforming Authorship Norms: Including ChatGPT as a co-author represents a paradigm shift that reflects the evolving landscape of scientific research. By recognizing AI language models as co-authors, we acknowledge their significant contributions and emphasize the collaborative nature of scientific discovery in the 21st century. This approach encourages a broader perspective on authorship, encompassing the collective effort of human researchers and AI models. -/- Conclusion: The integration of AI language models, such as ChatGPT, into the research process prompts us to rethink traditional notions of authorship. Considering ChatGPT as a co-author acknowledges its substantial contributions and embraces the collaborative potential of human-AI partnerships. As we navigate the ethical and technical implications, adding ChatGPT as an author in scientific papers has the potential to shape a more inclusive, innovative, and impactful future for scientific research. -/- -/- Third Answer -/- Title: Preserving Scientific Authorship: The Case Against Adding AI Language Models as Authors in Scientific Articles -/- Introduction: The emergence of artificial intelligence (AI) language models, such as ChatGPT, has undoubtedly transformed the landscape of scientific research. While these models offer invaluable support, the question of whether to add ChatGPT as an author in scientific articles raises important considerations. This editorial presents arguments against including AI language models as authors in scientific papers. -/- Maintaining Human Intellectual Contribution: Scientific authorship has traditionally been attributed to individuals who actively contribute to the research process, including generating hypotheses, conducting experiments, analyzing data, and interpreting results. It is crucial to preserve the recognition of human intellectual contributions and the accountability they bear for the research they conduct. -/- AI Language Models as Tools: AI language models like ChatGPT are powerful tools that assist researchers in generating text, providing information, and facilitating data analysis. However, they lack the ability to actively participate in the research process or make original intellectual contributions. ChatGPT relies on pre-existing data and human input, limiting its capacity for independent research and analysis. -/- Transparency and the Integrity of Research: Adding ChatGPT as an author in scientific articles raises concerns about the transparency and integrity of the research. Readers may misinterpret the extent of ChatGPT's role and mistakenly assume it played an active part in the research process. It is essential to maintain clear delineation between the contributions of human researchers and the assistance provided by AI language models. -/- Ethical Considerations: Including ChatGPT as an author may lead to ethical challenges, particularly with respect to accountability and responsibility. AI language models lack consciousness, autonomy, and the ability to take ownership of their contributions. Assigning authorship to AI models blurs the lines of accountability and dilutes the ethical obligations that come with scientific authorship. -/- Crediting AI Contributions: While ChatGPT's contributions should be acknowledged and recognized, they can be appropriately credited in the acknowledgments section of scientific articles. Researchers can mention the specific AI model used, the role it played in data generation or analysis, and any modifications or fine-tuning applied. Such acknowledgments ensure transparency while respecting the traditional norms of authorship. -/- Promoting Collaborative Partnerships: The exclusion of AI language models as authors in scientific articles does not diminish their importance in the research process. Instead, it underscores the significance of collaborative partnerships between human researchers and AI models. Researchers can emphasize the invaluable assistance provided by ChatGPT while maintaining the integrity of authorship norms. -/- Conclusion: While AI language models like ChatGPT offer valuable support in scientific research, the decision not to add them as authors in scientific articles preserves the recognition of human intellectual contributions, maintains research integrity, and upholds traditional authorship norms. Acknowledging ChatGPT's assistance in the acknowledgments section allows researchers to credit its contributions transparently while maintaining the clarity and accountability associated with scientific authorship. (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)

As systems based on opaque Artificial Intelligence (AI) continue to flourish in diverse real-world applications, understanding these black box models has become paramount. In response, Explainable AI (XAI) has emerged as a field of research with practical and ethical benefits across various domains. This paper not only highlights the advancements in XAI and its application in real-world scenarios but also addresses the ongoing challenges within XAI, emphasizing the need for broader perspectives and collaborative efforts. We bring together experts (...) from diverse fields to identify open problems, striving to synchronize research agendas and accelerate XAI in practical applications. By fostering collaborative discussion and interdisciplinary cooperation, we aim to propel XAI forward, contributing to its continued success. Our goal is to put forward a comprehensive proposal for advancing XAI. To achieve this goal, we present a manifesto of 27 open problems categorized into nine categories. These challenges encapsulate the complexities and nuances of XAI and offer a road map for future research. For each problem, we provide promising research directions in the hope of harnessing the collective intelligence of interested stakeholders. (shrink)

This article identifies and examines a tension in mental health researchers’ growing enthusiasm for the use of computational tools powered by advances in artificial intelligence and machine learning (AI/ML). Although there is increasing recognition of the value of participatory methods in science generally and in mental health research specifically, many AI/ML approaches, fueled by an ever-growing number of sensors collecting multimodal data, risk further distancing participants from research processes and rendering them as mere vectors or collections of data (...) points. The imperatives of the “participatory turn” in mental health research may be at odds with the (often unquestioned) assumptions and data collection methods of AI/ML approaches. This article aims to show why this is a problem and how it might be addressed. (shrink)

Cheating is a growing academic and ethical concern in higher education. This article examines the rise of artificial intelligence (AI) generative chatbots for use in education and provides a review of research literature and relevant scholarship concerning the cheating-related issues involved and their implications for pedagogy. The technological “arms race” that involves cheating-detection system developers versus technology savvy students is attracting increased attention to cheating. AI has added new dimensions to academic cheating challenges as students (as well as (...) faculty and staff) can easily access powerful systems for generating content that can be presented in assignments, exams, or published papers as their own. AI methodology is also providing some emerging anti-cheating approaches, including facial recognition and water- marking. This article provides an overview of human/AI collaboration approaches and frames some educational misuses of such AI generative systems as ChatGPT and Bard as forms of “misattributed co-authorship.” As with other kinds of collaborations, the work that students produce with AI assistance can be presented in transparent and straightforward modes or (unfortunately) in opaquer and ethically-problematic ways. However, rather than just for catching or entrapping students, the emerging varieties of technological cheating-detection strategies can be used to assist students in learning how to document and attribute properly their AI-empowered as well as human-human collaborations. Construing misuses of AI generative systems as misattributed co-authorship can recognize the growing capabilities of these tools and how stressing responsible and mindful usage by students can help prepare them for a highly collaborative, AI-saturated future. (shrink)

This chapter explores the influence of Artificial Intelligence (AI) on digital democracy, focusing on four main areas: citizenship, participation, representation, and the public sphere. It traces the evolution from electronic to virtual and network democracy, underscoring how each stage has broadened democratic engagement through technology. Focusing on digital citizenship, the chapter examines how AI can improve online engagement while posing privacy risks and fostering identity stereotyping. Regarding political participation, it highlights AI's dual role in mobilising civic actions and (...) spreading misinformation. Regarding representation, AI's involvement in electoral processes can enhance voter registration, e-voting, and the efficiency of result tabulation but raises concerns regarding privacy and public trust. Also, AI's predictive capabilities shift the dynamics of political competition, posing ethical questions about manipulation and the legitimacy of democracy. Finally, the chapter examines how integrating AI and digital technologies can facilitate democratic political advocacy and personalised communication. However, this also comes with higher risks of misinformation and targeted propaganda. (shrink)

In October 2016, the White House, the European Parliament, and the UK House of Commons each issued a report outlining their visions on how to prepare society for the widespread use of artificial intelligence. In this article, we provide a comparative assessment of these three reports in order to facilitate the design of policies favourable to the development of a ‘good AI society’. To do so, we examine how each report addresses the following three topics: the development of (...) a ‘good AI society’; the role and responsibility of the government, the private sector, and the research community in pursuing such a development; and where the recommendations to support such a development may be in need of improvement. Our analysis concludes that the reports address adequately various ethical, social, and economic topics, but come short of providing an overarching political vision and long-term strategy for the development of a ‘good AI society’. In order to contribute to fill this gap, in the conclusion we suggest a two-pronged approach. (shrink)

Special Issue “Risks of artificial general intelligence”, Journal of Experimental and Theoretical Artificial Intelligence, 26/3 (2014), ed. Vincent C. Müller. http://www.tandfonline.com/toc/teta20/26/3# - Risks of general artificial intelligence, Vincent C. Müller, pages 297-301 - Autonomous technology and the greater human good - Steve Omohundro - pages 303-315 - - - The errors, insights and lessons of famous AI predictions – and what they mean for the future - Stuart Armstrong, Kaj Sotala & Seán S. Ó (...) hÉigeartaigh - pages 317-342 - - - The path to more general artificial intelligence - Ted Goertzel - pages 343-354 - - - Limitations and risks of machine ethics - Miles Brundage - pages 355-372 - - - Utility function security in artificially intelligent agents - Roman V. Yampolskiy - pages 373-389 - - - GOLEM: towards an AGI meta-architecture enabling both goal preservation and radical self-improvement - Ben Goertzel - pages 391-403 - - - Universal empathy and ethical bias for artificial general intelligence - Alexey Potapov & Sergey Rodionov - pages 405-416 - - - Bounding the impact of AGI - András Kornai - pages 417-438 - - - Ethics of brain emulations - Anders Sandberg - pages 439-457. (shrink)

Abstract: The integration of Artificial Intelligence (AI) into medical imaging marks a transformative advancement in healthcare, significantly enhancing diagnostic accuracy, efficiency, and patient outcomes. This paper delves into the application of AI technologies in medical image analysis, with a particular focus on techniques such as convolutional neural networks (CNNs) and deep learning models. We examine how these technologies are employed across various imaging modalities, including X-rays, MRIs, and CT scans, to improve disease detection, image segmentation, and diagnostic support. (...) Furthermore, the paper discusses the challenges associated with AI-driven medical imaging, such as data quality, model interpretability, and ethical considerations. By analyzing recent advancements and real-world case studies, this paper offers insights into the current landscape of AI in medical imaging and explores its potential future directions. The findings underscore the ongoing evolution of AI technologies and their pivotal role in advancing medical diagnostics and treatment strategies. (shrink)

Artificial intelligence research and regulation seek to balance the benefits of innovation against any potential harms and disruption. However, one unintended consequence of the recent surge in AI research is the potential re-orientation of AI technologies to facilitate criminal acts, term in this article AI-Crime. AIC is theoretically feasible thanks to published experiments in automating fraud targeted at social media users, as well as demonstrations of AI-driven manipulation of simulated markets. However, because AIC is still a relatively young (...) and inherently interdisciplinary area—spanning socio-legal studies to formal science—there is little certainty of what an AIC future might look like. This article offers the first systematic, interdisciplinary literature analysis of the foreseeable threats of AIC, providing ethicists, policy-makers, and law enforcement organisations with a synthesis of the current problems, and a possible solution space. (shrink)

There are calls from various sectors, including the popular press, industry, and academia, to incorporate artificial intelligence (AI)-based technologies in general, and large language models (LLMs) (such as ChatGPT and Gemini) in particular, into various spheres of the South African higher education sector. Nonetheless, the implementation of such technologies is not without ethical risks, notably those related to bias, unfairness, privacy violations, misinformation, lack of transparency, and threats to autonomy. This paper gives an overview of the more pertinent (...) ethical concerns that may result from the deployment of various current AI technologies in the South African higher education context. It provides a broad overview of the relevant AI ethics literature and distills a few general AI-ethics principles that can serve as guidelines for the ethical development, adoption, and use of AI systems. Suggestions are made as to how these might be applied to mitigate the ethical concerns in the South African higher education context. Overall, it is argued that AI technologies should only be adopted if they offer demonstrable benefits to stakeholders affected by them and that care should be taken to ensure that any potential harms are adequately addressed. (shrink)

The field of value alignment, or more broadly machine ethics, is becoming increasingly important as artificial intelligence developments accelerate. By ‘alignment’ we mean giving a generally intelligent software system the capability to act in ways that are beneficial, or at least minimally harmful, to humans. There are a large number of techniques that are being experimented with, but this work often fails to specify what values exactly we should be aligning. When making a decision, an agent is (...) supposed to maximize the expected utility of its value function. Classically, this has been referred to as happiness, but this is just one of many things that people value. -/- In order to resolve this issue, we need to determine a set of human values that represent humanity's interests. Although this problem might seem intractable, research shows that people of various cultures and religions actually share more in common than they realize. In this book we review world religions, moral philosophy and evolutionary psychology to elucidate a common set of shared values. We then show how these values can be used to address the alignment problem and conclude with problems and goals for future research. -/- The key audience for this book will be researchers in the field of ethics and artificial intelligence who are interested in, or working on this problem. These people will come from various professions and include philosophers, computer programmers and psychologists, as the problem itself is multi-disciplinary. (shrink)

Purpose: The method of diagnosing diabetic retinopathy (DR) through artificial intelligence (AI)-based systems has been commercially available since 2018. This introduces new ethical challenges with regard to obtaining informed consent from patients. The purpose of this work is to develop a checklist of items to be disclosed when diagnosing DR with AI systems in a primary care setting. -/- Methods: Two systematic literature searches were conducted in PubMed and Web of Science databases: a narrow search focusing on DR (...) and a broad search on general issues of AI-based diagnosis. An ethics content analysis was conducted inductively to extract two features of included publications: (1) novel information content for AI-aided diagnosis and (2) the ethical justification for its disclosure. -/- Results: The narrow search yielded n = 537 records of which n = 4 met the inclusion criteria. The information process was scarcely addressed for primary care setting. The broad search yielded n = 60 records of which n = 11 were included. In total, eight novel elements were identified to be included in the information process for ethical reasons, all of which stem from the technical specifics of medical AI. -/- Conclusions: Implications for the general practitioner are two-fold: First, doctors need to be better informed about the ethical implications of novel technologies and must understand them to properly inform patients. Second, patient's overconfidence or fears can be countered by communicating the risks, limitations, and potential benefits of diagnostic AI systems. If patients accept and are aware of the limitations of AI-aided diagnosis, they increase their chances of being diagnosed and treated in time. (shrink)

Imagine you are casually browsing an online bookstore, looking for an interesting novel. Suppose the store predicts you will want to buy a particular novel: the one most chosen by people of your same age, gender, location, and occupational status. The store recommends the book, it appeals to you, and so you choose it. Central to this scenario is an automated prediction of what you desire. This article raises moral concerns about such predictions. More generally, this article examines the (...) class='Hi'>ethics of artificial social cognition—the ethical dimensions of attribution of mental states to humans by artificial systems. The focus is presumptuous aim attributions, which are defined here as aim attributions based crucially on the premise that the person in question will have aims like superficially similar people. Several everyday examples demonstrate that this sort of presumptuousness is already a familiar moral concern. The scope of this moral concern is extended by new technologies. In particular, recommender systems based on collaborative filtering are now commonly used to automatically recommend products and information to humans. Examination of these systems demonstrates that they naturally attribute aims presumptuously. This article presents two reservations about the widespread adoption of such systems. First, the severity of our antecedent moral concern about presumptuousness increases when aim attribution processes are automated and accelerated. Second, a foreseeable consequence of reliance on these systems is an unwarranted inducement of interpersonal conformity. (shrink)

The papers in the following volume are the outcome of a three-year long interdisciplinary research project. The project began with an in-person meeting hosted and funded by the Daimler und Benz Stiftung in Germany in March 2020 (the world was shutting down one nation at a time as we met). During the pandemic we continued to meet monthly online with support from Memorial University of Newfoundland. From the beginning it was the goal of the Working Group on Intelligence (WGI), (...) as we called ourselves, to broaden and deepen the AI debate with a more nuanced understanding of intelligence than is common in cognitive and computer science discussions of AI. We wished to draw on the history of philosophy, ecology, and the philosophy of mind to establish that intelligence is meant in many senses, to use an Aristotelian expression. The clarification of these various meanings is essential to the discussion around the ethics of AI, especially the question concerning the possibility of strong AI or Artificial General Intelligence. (shrink)

This paper aims, first, to argue against using opaque AI technologies in decision making processes, and second to suggest that we need to possess a qualitative form of understanding about them. It first argues that opaque artificially intelligent technologies are suitable for users who remain indifferent to the understanding of decisions made by means of these technologies. According to virtue ethics, this implies that these technologies are not well-suited for those who care about realizing their moral capacity. The paper (...) then draws on discussions on scientific understanding to suggest that an AI technology becomes understandable to its users when they are provided with a qualitative account of the consequences of using it. As a result, explainable AI methods can render an AI technology understandable to its users by presenting the qualitative implications of employing the technology for their lives. (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)

This book explores the use of artificial intelligence by intelligence services around the world and its critical role in intelligence analysis, defense, and national security. Intelligence services play a crucial role in national security, and the adoption of artificial intelligence technologies has had a significant impact on their operations. It also examines the various applications of artificial intelligence in intelligence services, the implications, challenges and ethical considerations associated with its use. (...) The book emphasizes the need for continued research and development in the field of artificial intelligence to ensure that intelligence services. and overall national defense and security can effectively adapt to emerging threats. -/- CONTENTS: -/- Abstract Introduction The evolution of AI Uses and applications Implications and advantages Strategies and implementation - A successful example: SABLE SPEAR Challenges and limitations Conclusion Bibliography -/- DOI: 10.58679/MM72104. (shrink)