Artificially intelligent (AI) technologies are increasingly being used in many workplaces. It is recognised that there are ethical dimensions to the ways in which organisations implement AI alongside, or substituting for, their human workforces. How will these technologically driven disruptions impact the employee–employer exchange? We provide one way to explore this question by drawing on scholarship linking Integrative Social Contracts Theory (ISCT) to the psychological contract (PC). Using ISCT, we show that the macrosocial contract’s ethical AI norms of beneficence, non-maleficence, (...) autonomy, justice, and explicability can feed into national- and organisational-level microsocial contracts. We also outline the role of employees’ technology frames in this process. We then use an illustrative example to demonstrate how this multilevel normative background helps to inform the content of individuals’ PCs in the context of working with AI technologies. (shrink)

Artificially intelligent (AI) technologies are increasingly being used in many workplaces. It is recognised that there are ethical dimensions to the ways in which organisations implement AI alongside, or substituting for, their human workforces. How will these technologically driven disruptions impact the employee–employer exchange? We provide one way to explore this question by drawing on scholarship linking Integrative Social Contracts Theory (ISCT) to the psychological contract (PC). Using ISCT, we show that the macrosocial contract’s ethical AI norms of beneficence, non-maleficence, (...) autonomy, justice, and explicability can feed into national- and organisational-level microsocial contracts. We also outline the role of employees’ technology frames in this process. We then use an illustrative example to demonstrate how this multilevel normative background helps to inform the content of individuals’ PCs in the context of working with AI technologies. (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)

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)

Machine-based automation has long been a key factor in the modern era. However, lately, many people have been shocked by artificial intelligence (AI) applications, such as ChatGPT (OpenAI), that can perform tasks previously thought to be human-exclusive. With recent advances in natural language processing (NLP) technologies, AI can generate written content that is similar to human-made products, and this ability has a variety of applications. As the technology of large language models continues to progress by making use of (...) colossal reservoirs of digital information, AI is becoming more capable of recognizing patterns and associations within given contexts, making it especially helpful in assisting with various professional writing tasks [1]. In this paper, we will discuss several key points regarding the current state and future of AI in academia. Furthermore, since in certain aspects, acts can speak louder than words, we will also present some of our hands-on experiences of working with ChatGPT. (shrink)

In this work, a general framework for the analysis of governance of artificial intelligence is presented. A dashboard developed for this analysis comes from the perspective of political theory. This dashboard allows eventual comparisons between democratic and non democratic regimes, useful for countries in the global south and western countries. The dashboard allows us to assess the key features that determine the governance model for artificial intelligence at the national level, for local governments and for (...) other participant actors. The dashboard allows us to appraise aims of AI strategy and aims left aside in alternative strategies. The work shows the theoretical framework could be of use to advance case studies globally, and comparative endeavors. Applying the theoretical dashboard, the case study on China is undertaken. These are the main points the study tackles in the final discussion, conclusion and further recommendations: 1) the complex reality of AI command and control 2) uncertainties about future society and the polity against AI development and 3) particular cultural values enshrined in countries' AI development. (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)

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 theory and philosophy of artificial intelligence has come to a crucial point where the agenda for the forthcoming years is in the air. This special volume of Minds and Machines presents leading invited papers from a conference on the “Philosophy and Theory of Artificial Intelligence” that was held in October 2011 in Thessaloniki. Artificial Intelligence is perhaps unique among engineering subjects in that it has raised very basic questions about the nature of computing, (...) perception, reasoning, learning, language, action, interaction, consciousness, humankind, life etc. etc. – and at the same time it has contributed substantially to answering these questions. There is thus a substantial tradition of work, both on AI by philosophers and of theory within AI itself. - The volume contains papers by Bostrom, Dreyfus, Gomila, O'Regan and Shagrir. (shrink)

Dear Editors, -/- I found the content of your editorials to be highly intriguing [1,2]. Scientific journals are witnessing a growing prevalence of publications related to artificial intelligence (AI). Three letters to the editor were recently published in your journal [3-5]. The renowned journal Nature has dedicated approximately 25 publications solely to the subject of ChatGPT. Moreover, a quick search on Pubmed using the term "ChatGPT" yields around 900 articles, with the vast majority originating in 2023. These statistics (...) underscore the substantial interest of the scientific community in this area. -/- AI, especially the ChatGPT tool and the recent Bard, have faced criticism and been portrayed as significant adversaries of science. It is evident that many authors or researchers, who may not be well-versed in writing, can greatly benefit from these tools, as mentioned earlier. Without taking a contrarian stance, one should consider the potential advantages of such technologies for researchers in less privileged regions, where access to new technologies is limited, and local or regional challenges abound [6]. AI cannot be confounded with other technologies, as it specifically focuses on replicating human-like intelligence and decision-making processes, rather than simply automating tasks or improving performance based on data patterns. -/- The translation into English poses challenges due to the dominance of English in worldwide publications, with over 95% of articles being published in this language, and even reaching 98% in some fields. Although this manuscript was partially translated using AI, it can still benefit researchers from non-native English regions. Even simple tasks like text editing can be problematic for researchers in underprivileged areas. AI can play a crucial role in the evolution of online lectures and classes, providing valuable support for African maxillofacial surgeons who lack the luxury of taking breaks from work to update their knowledge, as they may be the only available option [7]. One of the remarkable features of AI is its ability to discover knowledge gaps. The use of simple tools like reference organizers is rapidly evolving and can become automated or semi-automated through AI. However, we must carefully consider whether we should refrain from relying too heavily on AI in certain cases, as this could be seen as a significant regression. -/- On the other hand, we must be cautious about freely allowing AI tools to circulate in scientific journals and books without proper regulation [8]. Currently, accurately identifying texts generated by AI is challenging, and their effectiveness remains relatively low, at less than 30%. This means that only about 30 out of every 100 texts can be confidently classified as AI-generated. The technology must advance further to increase detection accuracy or at least raise suspicion. Academic journals no longer view authors acknowledging artificial intelligence tools as co-authors in their research favorably. This is crucial to prevent certain unscrupulous individuals, such as "false prophets," charlatans, and flat-earthers, from infiltrating the realm of science, potentially impeding the progress of serious research conducted by professionals dedicated to advancing humanity through science. -/- It is essential to keep in mind that AI does not generate anything novel. Human authors can not be fully substituted [9]. In research involving groundbreaking concepts, innovations, case reports, or technical notes, the use of AI tends to be less frequent due to its lack of capability in creating innovative outcomes. On the other hand, reviews, whether narrative, systematic, or scoping, are based on existing publications. To address potential fraudulent practices, editors, reviewers, and journals themselves should exercise greater vigilance and apply more stringent filters for this type of publication. -/- An article from over a decade ago already discussed the professions most susceptible to replacement by computerization [10]. Maxillofacial surgeons, physicians, dentists, and psychologists are among the professions that are less likely to be displaced. This position can be attributed to the significant level of patient-professional interaction, the development of specific manual skills over time, and the ability to make adaptable decisions during procedures. These intricacies pose formidable challenges for AI to grasp, regardless of its level of advancement. -/- We should maintain a composed yet vigilant stance at this juncture. Just as Portuguese navigators feared encountering serpents and sea monsters when they ventured into uncharted waters, the uncertainty and novelty of AI can evoke apprehension in us all. Nonetheless, we must embrace the benefits that AI can offer while imposing strict regulations and appropriate penalties to prevent any potential abuses carried out "in the name of science." -/- Sincerely yours,. (shrink)

Decision theory has had a long-standing history in the behavioural and social sciences as a tool for constructing good approximations of human behaviour. Yet as artificially intelligent systems (AIs) grow in intellectual capacity and eventually outpace humans, decision theory becomes evermore important as a model of AI behaviour. What sort of decision procedure might an AI employ? In this work, I propose that policy-based causal decision theory (PCDT), which places a primacy on the decision-relevance of predictors and simulations of (...) agent behaviour, may be such a procedure. I compare this account to the recently-developed functional decision theory (FDT), which is motivated by similar concerns. I also address potentially counterintuitive features of PCDT, such as its refusal to condition on observations made at certain times. (shrink)

In this paper, we focus on the most efficacious AI applications for life extension and anti-aging at three expected stages of AI development: narrow AI, AGI and superintelligence. First, we overview the existing research and commercial work performed by a select number of startups and academic projects. We find that at the current stage of “narrow” AI, the most promising areas for life extension are geroprotector-combination discovery, detection of aging biomarkers, and personalized anti-aging therapy. These advances could help currently (...) living people reach longevity escape velocity and survive until more advanced AI appears. When AI comes close to human level, the main contribution to life extension will come from AI integration with humans through brain-computer interfaces, integrated AI assistants capable of autonomously diagnosing and treating health issues, and cyber systems embedded into human bodies. Lastly, we speculate about the more remote future, when AI reaches the level of superintelligence and such life-extension methods as uploading human minds and creating nanotechnological bodies may become possible, thus lowering the probability of human death close to zero. We suggest that medical AI based superintelligence could be safer than, say, military AI, as it may help humans to evolve into part of the future superintelligence via brain augmentation, uploading, and a network of self-improving humans. Medical AI’s value system is focused on human benefit. (shrink)

Technological progress has brought about the emergence of machines that have the capacity to take human lives without human control. These represent an unprecedented threat to humankind. This paper starts from the example of chemical weapons, now banned worldwide by the Geneva protocol, to illustrate how technological development initially aimed at the benefit of humankind has, ultimately, produced what is now called the “Weaponization of Artificial Intelligence (AI)”. Autonomous Weapon Systems (AWS) fail the so-called discrimination principle, yet, the (...) wider public is largely unaware of this problem. Given that ongoing scientific research on AWS, performed in the military sector, is generally not made available to the public domain, many of the viewpoints on this subject, expressed across different media, invoke common sense rather than scientific evidence. Yet, the implications of a potential weaponization of our work as scientists, especially in the field of AI, are reaching further than some may think. The potential consequences of a deployment of AWS for citizen stakeholders are incommensurable, and it is time to raise awareness in the public domain of the kind of potential threats identified, and to encourage legal policies ensuring that these threats will not materialize. (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 presentation discusses a notion encountered across disciplines, and in different facets of human activity: autonomous activity. We engage it in an interdisciplinary way. We start by considering the reactions and behaviors of biological entities to biotechnological intervention. An attempt is made to characterize the degree of freedom of embryos & clones, which show openness to different outcomes when the epigenetic developmental landscape is factored in. We then consider the claim made in programming and artificial intelligence that automata (...) could show self-directed behavior as to the determination of their step-wise decisions on courses of action. This question remains largely open and calls for some important qualifications. We try to make sense of the presence of claims of freedom in agency, first in common sense, then by ascribing developmental plasticity in biology and biotechnology, and in the mapping of programmed systems in the presence of environmental cues and self-referenced circuits as well as environmental coupling. This is the occasion to recall attempts at working out a logical and methodological approach to the openness of concepts that are still to be found, and assess whether they can operate the structuring intelligibility of a yet undeveloped or underdeveloped field of study, where a “bisociation" and a unification of knowledge might be possible. (shrink)

Definition of the problem The umbrella term “explicability” refers to the reduction of opacity of artificial intelligence (AI) systems. These efforts are challenging for medical AI applications because higher accuracy often comes at the cost of increased opacity. This entails ethical tensions because physicians and patients desire to trace how results are produced without compromising the performance of AI systems. The centrality of explicability within the informed consent process for medical AI systems compels an ethical reflection on the (...) trade-offs. Which levels of explicability are needed to obtain informed consent when utilizing medical AI? Arguments We proceed in five steps: First, we map the terms commonly associated with explicability as described in the ethics and computer science literature, i.e., disclosure, intelligibility, interpretability, and explainability. Second, we conduct a conceptual analysis of the ethical requirements for explicability when it comes to informed consent. Third, we distinguish hurdles for explicability in terms of epistemic and explanatory opacity. Fourth, this then allows to conclude the level of explicability physicians must reach and what patients can expect. In a final step, we show how the identified levels of explicability can technically be met from the perspective of computer science. Throughout our work, we take diagnostic AI systems in radiology as an example. Conclusion We determined four levels of explicability that need to be distinguished for ethically defensible informed consent processes and showed how developers of medical AI can technically meet these requirements. (shrink)

The present paper looks at one of the most thorough articles on the intelligence of GPT, research conducted by engineers at Microsoft. Although there is a great deal of value in their work, I will argue that, for familiar philosophical reasons, their methodology, ‘Black-box Interpretability’ is wrongheaded. But there is a better way. There is an exciting and emerging discipline of ‘Inner Interpretability’ (also sometimes called ‘White-box Interpretability’) that aims to uncover the internal activations and weights of models (...) in order to understand what they represent and the algorithms they implement. In my view, a crucial mistake in Black-box Interpretability is the failure to appreciate that how processes are carried out matters when it comes to intelligence and understanding. I can’t pretend to have a full story that provides both necessary and sufficient conditions for being intelligent, but I do think that Inner Interpretability dovetails nicely with plausible philosophical views of what intelligence requires. So the conclusion is modest, but the important point in my view is seeing how to get the research on the right track. Towards the end of the paper, I will show how some of the philosophical concepts can be used to further refine how Inner Interpretability is approached, so the paper helps draw out a profitable, future two-way exchange between Philosophers and Computer Scientists. (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)

The AI Robotics Ethics Society (AIRES) is a non-profit organization founded in 2018 by Aaron Hui to promote awareness and the importance of ethical implementation and regulation of AI. AIRES is now an organization with chapters at universities such as UCLA (Los Angeles), USC (University of Southern California), Caltech (California Institute of Technology), Stanford University, Cornell University, Brown University, and the Pontifical Catholic University of Rio Grande do Sul (Brazil). AIRES at PUCRS is the first international chapter of AIRES, and (...) as such, we are committed to promoting and enhancing the AIRES Mission. Our mission is to focus on educating the AI leaders of tomorrow in ethical principles to ensure that AI is created ethically and responsibly. As there are still few proposals for how we should implement ethical principles and normative guidelines in the practice of AI system development, the goal of this work is to try to bridge this gap between discourse and praxis. Between abstract principles and technical implementation. In this work, we seek to introduce the reader to the topic of AI Ethics and Safety. At the same time, we present several tools to help developers of intelligent systems develop "good" models. This work is a developing guide published in English and Portuguese. Contributions and suggestions are welcome. (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)

It is well known that people from other disciplines have made significant contributions to philosophy and have influenced philosophers. It is also true (though perhaps not often realized, since philosophers are not on the receiving end, so to speak) that philosophers have made significant contributions to other disciplines and have influenced researchers in these other disciplines, sometimes more so than they have influenced philosophy itself. But what is perhaps not as well known as it ought to be is that researchers (...) in other disciplines, writing in those other disciplines' journals and conference proceedings, are doing philosophically sophisticated work, work that we in philosophy ignore at our peril. Work in cognitive science and artificial intelligence (AI) often overlaps such paradigmatic philosophical specialties as logic, the philosophy of mind, the philosophy of language, and the philosophy of action. This special issue offers a sampling of research in cognitive science and AI that is philosophically relevant and philosophically sophisticated. (shrink)

Mark Coeckelbergh is a Belgian philosopher who specializes in the philosophy of technology. His work primarily explores the intersection of technology and society, specifically the philosophical implications of emerging technologies such as AI and robotics. He has written on whether machines can be moral agents and how ethical frameworks should be applied to autonomous machines. He has a broad philosophical perspective drawing on classical sources, Eastern philosophy, Marxism, Foucault, phenomenology, and the postmodernists. In this short text, he brings his (...) remarkable insights and erudition to bear on our attempts at self-improvement in the age of AI. (shrink)

Sam Harris is a contemporary illustration of the difficulties standing in the way of coherent interdisciplinary thinking in an age where science and the humanities have drifted so far apart. We are here with Harris’s views on AI, and specifically with his view according to which, with the advance of AI, there will evolve a machine superintelligence with powers that far exceed those of the human mind. This he sees as something that is not merely possible, but rather a matter (...) of inevitability. If, however, we look carefully at what intelligence is, and at how computers really work on the basis of mathematical models, then we can see that it is forever impossible to emulate inside a computer even the intelligence of crows or rabbits, let alone that of human beings. (shrink)

This study was conducted with the aim of developing the academic work in the Palestinian universities. No one can deny the technological stage that we are witnessing in the present era. Our mission is to use this development to develop the educational process. The Artificial Intelligence of the most important branches of computer science, which is interested in the development of computer software in order to make them simulate intelligent human, recently it emerged promised based on (...) class='Hi'>artificial intelligence applications are intelligent tutoring system one of the most prominent of these applications is the most useful in the field of education. Intelligent tutoring system are programs that are helping the student and the teacher in the educational process, so that the student exploits these systems to increase his education and the acquisition of scientific skills, and we are not exaggerating if we say that the future of the development of the educational process is through the development of intelligent private teaching systems because it adapts to me intellectual level of the student as well as easy to use and available 24 hours every day. In this study, a smart tutor was designed using the ITSB tool developed by Prof. Sami Abu Nasser to develop the process of teaching the computer skills course. This course is a university course that teaches students of Israa University on different samples of students. After completion of the course, and evaluate the special lecturers who studied the course and used the system in the process of teaching and arrived at a set of conclusions and recommendations make sure that the use of the tutor Smart smartphone is important in the development of laboratory teaching has positive results in improving the level of scientific student . (shrink)

This study was conducted with the aim of developing the academic work in the Palestinian universities. No one can deny the technological stage that we are witnessing in the present era. Our mission is to use this development to develop the educational process. The Artificial Intelligence of the most important branches of computer science, which is interested in the development of computer software in order to make them simulate intelligent human, recently it emerged promised based on (...) class='Hi'>artificial intelligence applications are intelligent tutoring system one of the most prominent of these applications is the most useful in the field of education. Intelligent tutoring system are programs that are helping the student and the teacher in the educational process, so that the student exploits these systems to increase his education and the acquisition of scientific skills, and we are not exaggerating if we say that the future of the development of the educational process is through the development of intelligent private teaching systems because it adapts to me intellectual level of the student as well as easy to use and available 24 hours every day. In this study, a smart tutor was designed using the ITSB tool developed by Prof. Sami Abu Nasser to develop the process of teaching the computer skills course. This course is a university course that teaches students of Israa University on different samples of students. After completion of the course, and evaluate the special lecturers who studied the course and used the system in the process of teaching and arrived at a set of conclusions and recommendations make sure that the use of the tutor Smart smartphone is important in the development of laboratory teaching has positive results in improving the level of scientific student . (shrink)

In August 2022, only a few months before ChatGPT was released, Barry Smith, well-known contemporary philosopher, together with Jobst Landgrebe, artificial intelligence entrepreneur, published a book entitled Why Machines will Never Rule the World: Artificial Intelligence without Fear (Landgrebe and Smith 2022). In this important, dense and far-reaching work, Landgrebe and Smith argue from the mathematical theory of complex systems, and a sophisticated analysis of the capabilities of human intelligence, that AGI— at the level (...) of human intelligence—will never be possible. In broad outline, Landgrebe and Smith claim that intelligent human behaviour is a facility that develops from a complex world and for a complex world; that the complexities of the real world and our behaviour in it can never be fully specified or simulated mathematically; that digital systems can only execute what can be simulated mathematically; and that therefore human-level intelligence will never be manifested by a digital system. The present collection of articles is in response to and inspired by Landgrebe and Smith. It provides reflections from a variety of perspectives and disciplines on the possibility of AGI, as well as on the transformations that AI technology is already bringing even in its current incarnation. (shrink)

Using artificial intelligence (AI) to make decisions in human resource management (HRM) raises questions of how fair employees perceive these decisions to be and whether they experience respectful treatment (i.e., interactional justice). In this experimental survey study with open-ended qualitative questions, we examine decision making in six HRM functions and manipulate the decision maker (AI or human) and decision valence (positive or negative) to determine their impact on individuals’ experiences of interactional justice, trust, dehumanization, and perceptions of decision-maker (...) role appropriate- ness. In terms of decision makers, the use of human decision makers over AIs generally resulted in better perceptions of respectful treatment. In terms of decision valence, people experiencing positive over negative decisions generally resulted in better perceptions of respectful treatment. In instances where these cases conflict, on some indicators people preferred positive AI decisions over negative human decisions. Qualitative responses show how people identify justice concerns with both AI and human decision making. We outline implications for theory, practice, and future research. (shrink)

If complexity is a necessary but not sufficient premise for the existence and expression of the living, anticipation is the distinguishing characteristic of what is alive. Anticipation is at work even at levels of existence where we cannot refer to intelligence. The prospect of artificially generating aesthetic artifacts and ethical constructs of relevance to a world in which the natural and the artificial are coexistent cannot be subsumed as yet another product of scientific and technological advancement. Beyond (...) the artificial, the synthetic conjures the understanding of aesthetics and ethics no longer from the perspective of the How? type of question, but rather the Why? Given the current infatuation with synthetic biology (i.e., making life from non-life), there is a practical consequence to such considerations. Synthetic life, as any other form of life, implies the possibility of evolution. Anticipation, which is the underlying factor of evolution, is thus expected. At the level of human existence, anticipation is expressed, for instance (but not exclusively), in aesthetic forms and ethical values. This translates, in turn, into an argument for the role aesthetics and ethics play in the process. Consequently, to qualify as life, the synthesis of the physical and the living will have to efficiently handle ambiguity. Current computational facilities, regardless of their nature or performance, operate exclusively in the semiotic domain of the well defined non-ambiguous. (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)

This paper focuses on the research field of machine ethics and how it relates to a technological singularity—a hypothesized, futuristic event where artificial machines will have greater-than-human-level intelligence. One problem related to the singularity centers on the issue of whether human values and norms would survive such an event. To somehow ensure this, a number of artificial intelligence researchers have opted to focus on the development of artificial moral agents, which refers to machines capable of (...) moral reasoning, judgment, and decision-making. To date, different frameworks on how to arrive at these agents have been put forward. However, there seems to be no hard consensus as to which framework would likely yield a positive result. With the body of work that they have contributed in the study of moral agency, philosophers may contribute to the growing literature on artificial moral agency. While doing so, they could also think about how the said concept could affect other important philosophical concepts. (shrink)

In her seminal text, What Should We Do With Our Brain? (2008), Catherine Malabou gestured towards neuroplasticity to upend Bergson's famous parallel of the brain as a "central telephonic exchange," whereby the function of the brain is simply that of a node where perceptions get in touch with motor mechanisms, the brain as an instrument limited to the transmission and divisions of movements. Drawing from the history of cybernetics one can trace how Bergson's 'telephonic exchange' prefigures the neural 'cybernetic metaphor.' (...) It is elsewhere, however, that What Should We Do With Our Brain? finds its crux: inspired a dialectical-speculative opposition between plasticity and flexibility (wherein plasticity is the way in which time shapes or fashions us, constitutes our subjectivity and at the same time allows for resistance), Malabou invalidates the 'telephonic exchange' metaphor for failing to take into account synaptic and neuronal vitality. Bolstered by neurologist Marc Jeannerod's research in The Nature of Mind (2002), Malabou further demonstrated, in her past work, that the cybernetic metaphor has also had its day. In Morphing Intelligence, by problematizing intelligence as strictly empirical and biologically determined, Malabou also troubles the traditional distinction between intelligence and intuition. This division is perhaps best exemplified by Bergson’s analysis of intellectual measurement magnitudes in his appeal to intensity, and intensity alone. Malabou, drawing from Dewey and the pragmatism mode of thought, characterizes this fetid standstill as little more than provincialism, charging that, ater Bergson, no truly new argument was offered to counter intelligence as defined by psychologists and biologists, including the most recent cognitivist version. Despite I disagree with her claims regarding cognitivism, in echoing Georges Canguilhem, Malabou castigates psychology’s instrumentalist regard for intelligence, making the claim that it is able to measure only the human ability to “become an instrument.” Malabou contends that Alfred Binet (who heavily critiqued Bergson) had it right—intelligence is constituted by intensities and qualities. This book picks up from this critique and works genealogically; in my exegetical review, I engage with Malabou's and its implications, given her past work. (shrink)

The emergence of Large Language Models (LLMs) and advancements in Artificial Intelligence (AI) offer an opportunity for computational social science research at scale. Building upon prior explorations of LLM agent design, our work introduces a simulated agent society where complex social relationships dynamically form and evolve over time. Agents are imbued with psychological drives and placed in a sandbox survival environment. We conduct an evaluation of the agent society through the lens of Thomas Hobbes's seminal Social Contract (...) Theory (SCT). We analyze whether, as the theory postulates, agents seek to escape a brutish "state of nature" by surrendering rights to an absolute sovereign in exchange for order and security. Our experiments unveil an alignment: Initially, agents engage in unrestrained conflict, mirroring Hobbes's depiction of the state of nature. However, as the simulation progresses, social contracts emerge, leading to the authorization of an absolute sovereign and the establishment of a peaceful commonwealth founded on mutual cooperation. This congruence between our LLM agent society's evolutionary trajectory and Hobbes's theoretical account indicates LLMs' capability to model intricate social dynamics and potentially replicate forces that shape human societies. By enabling such insights into group behavior and emergent societal phenomena, LLM-driven multi-agent simulations, while unable to simulate all the nuances of human behavior, may hold potential for advancing our understanding of social structures, group dynamics, and complex human systems. (shrink)

Accountability is a cornerstone of the governance of artificial intelligence (AI). However, it is often defined too imprecisely because its multifaceted nature and the sociotechnical structure of AI systems imply a variety of values, practices, and measures to which accountability in AI can refer. We address this lack of clarity by defining accountability in terms of answerability, identifying three conditions of possibility (authority recognition, interrogation, and limitation of power), and an architecture of seven features (context, range, agent, forum, (...) standards, process, and implications). We analyse this architecture through four accountability goals (compliance, report, oversight, and enforcement). We argue that these goals are often complementary and that policy-makers emphasise or prioritise some over others depending on the proactive or reactive use of accountability and the missions of AI governance. (shrink)

Recent research into the nature of self in artificial and biological systems raises interest in a uniquely determining immutable sense of self, a “metaphysical ‘I’” associated with inviolable personal values and moral convictions that remain constant in the face of environmental change, distinguished from an object “me” that changes with its environment. Complementary research portrays processes associated with self as multimodal routines selectively enacted on the basis of contextual cues informing predictive self or world models, with the notion of (...) the constant, per-vasive and invariant sense of self associated with a multistable attractor set aiming to ensure personal integrity against threat of disintegrative change. This paper proposes that an immutable sense of self emerges as a global attractor which can be described as a project ideal self-situation embodied in frontal medial processes during more or less normal adolescent development, and that thereafter serves to orient agency in the more or less free development of embodied potentials over the life course in effort to realize project conditions, phenomenally identified with the felt pull towards this end as purpose of and source of meaning in life. So oriented, life-long self-development aims to embody solutions to problems at different timescales depending on this embodied purpose, ultimately in the service of evolutionary processes securing organism populations against threats of disintegrative change over timespans far beyond that of the individual. After characterizing the target sense of self, research circling this target is briefly surveyed. Self as global project and developmental neural correlates are proposed. Then, the paper discusses some implications for research in biological and artificial systems. Building from earlier work in cognitive neurorobotics, discussion affirms the value of reinforcement rituals including prayer in metaphysical self-development, considers implications for value alignment and rights associated with free will in the context of artificial intelligence and robot religion, and concludes by emphasizing the importance of self-development toward project ideals as source of meaning in life in the current social-political environment. (shrink)

Artificial intelligence systems have been widely applied to various contexts, including high-stake decision processes in healthcare, banking, and judicial systems. Some developed AI models fail to offer a fair output for specific minority groups, sparking comprehensive discussions about AI fairness. We argue that the development of AI systems is marked by a central paradox: the less participation one stakeholder has within the AI system’s life cycle, the more influence they have over the way the system will function. This (...) means that the impact on the fairness of the system is in the hands of those who are less impacted by it. However, most of the existing works ignore how different aspects of AI fairness are dynamically and adaptively affected by different stages of AI system development. To this end, we present a use case to discuss fairness in the development of corporate wellness programs using smart wearables and AI algorithms to analyze data. The four key stakeholders throughout this type of AI system development process are presented. These stakeholders are called service designer, algorithm designer, system deployer, and end-user. We identify three core aspects of AI fairness, namely, contextual fairness, model fairness, and device fairness. We propose a relative contribution of the four stakeholders to the three aspects of fairness. Furthermore, we propose the boundaries and interactions between the four roles, from which we make our conclusion about the possible unfairness in such an AI developing process. (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)

AI, especially in the case of Deepfakes, has the capacity to undermine our confidence in the original, genuine, authentic nature of what we see and hear. And yet digital technologies, in the form of databases and other detection tools also make it easier to spot forgeries and to establish the authenticity of a work. Using the notion of ectypes, this paper discusses current conceptions of authenticity and reproduction and examines how, in the future, these might be adapted for use (...) in the digital sphere. (shrink)

Artificial Intelligence (AI) is a diverse technology. It is already having significant effects on many jobs and sectors of the economy and over the next ten to twenty years it will drive profound changes in the way New Zealanders live and work. Within the workplace AI will have three dominant effects. This report (funded by the New Zealand Law Foundation) addresses: Chapter 1 Defining the Technology of Interest; Chapter 2 The changing nature and value of work; (...) Chapter 3 AI and the employment relationship; Chapter 4 Consumers, professions and society. The report includes recommendations to the New Zealand Government. (shrink)

The advance of scientific approaches to life has recorded a plethora of successes as well as failures. Man being at the center of its experiment is tossed toe and fro by the result of its inquiry. Predictions are that in the nearest time, humanity might be living absolutely under the directives of Technology based on Artificial intelligence. At present, Technology based on Artificial Intelligence is quickly finding its way into various areas of life including health and (...) social services. This spread and or interplay connotes the relinquishing of health responsibilities from man to sensor technology as well as dependency on the data and result of this technology. This effort questions this unethical dependency as well as raises moral issues associated with the use of Technology base on artificial intelligence on psychiatric patient. It dabbles into medical values such as; autonomy of the patient cum consent, Kantian universal principle and its implication to implementing the universal usage of technology in mental health care services, and so on. The work of Patricia A. Arean (2016) titled Mobile Technology for Mental Health Assessment gave an in-depth analysis of the available approaches, doting advantages of sensor technology on psychiatric patient. The paper applied the analytic, descriptive and prescriptive method of philosophy to achieve its objective. To this end, it is in the view of this work imperative for the mental-medical community to consider reflectively these issues and the philosophic recommendations provided herein. (shrink)

Henry Shevlin’s paper—“How could we know when a robot was a moral patient?” – argues that we should recognize robots and artificial intelligence (AI) as psychological moral patients if they are cognitively equivalent to other beings that we already recognize as psychological moral patients (i.e., humans and, at least some, animals). In defending this cognitive equivalence strategy, Shevlin draws inspiration from the “behavioral equivalence” strategy that I have defended in previous work but argues that it is flawed (...) in crucial respects. Unfortunately—and I guess this is hardly surprising—I cannot bring myself to agree that the cognitive equivalence strategy is the superior one. In this article, I try to explain why in three steps. First, I clarify the nature of the question that I take both myself and Shevlin to be answering. Second, I clear up some potential confusions about the behavioral equivalence strategy, addressing some other recent criticisms of it. Third, I will explain why I still favor the behavioral equivalence strategy over the cognitive equivalence one. (shrink)

Artificial intelligence (AI) is increasingly expected to disrupt the ordinary functioning of society. From how we fight wars or govern society, to how we work and play, and from how we create to how we teach and learn, there is almost no field of human activity which is believed to be entirely immune from the impact of this emerging technology. This poses a multifaceted problem when it comes to designing and understanding regulatory responses to AI. This article (...) aims to: (i) defend the need for a novel conceptual model for understanding the systemic legal disruption caused by new technologies such as AI; (ii) to situate this model in relation to preceding debates about the interaction of regulation with new technologies (particularly the ‘cyberlaw’ and ‘robolaw’ debates); and (iii) to set out a detailed model for understanding the legal disruption precipitated by AI, examining both pathways stemming from new affordances that can give rise to a regulatory ‘disruptive moment’, as well as the Legal Development, Displacement or Destruction that can ensue. The article proposes that this model of legal disruption can be broadly generalisable to understanding the legal effects and challenges of other emerging technologies. (shrink)

An important module in the Belief-Desire-Intention architecture for artificial agents (which builds on Michael Bratman's work in the philosophy of action) focuses on the task of intention reconsideration. The theoretical task is to formulate principles governing when an agent ought to undo a prior committed intention and reopen deliberation. Extant proposals for such a principle, if sufficiently detailed, are either too task-specific or too computationally demanding. I propose that an agent ought to reconsider an intention whenever some incompatible (...) prospect is sufficiently valuable along some dimension that can be assessed at zero or near-zero computational cost. (shrink)

The fact that real-world decisions made by artificial intelligences (AI) are often ethically loaded has led a number of authorities to advocate the development of “moral machines”. I argue that the project of building “ethics” “into” machines presupposes a flawed understanding of the nature of ethics. Drawing on the work of the Australian philosopher, Raimond Gaita, I argue that ethical dilemmas are problems for particular people and not (just) problems for everyone who faces a similar situation. Moreover, the (...) force of an ethical claim depends in part on the life history of the person who is making it. For both these reasons, machines could at best be engineered to provide a shallow simulacrum of ethics, which would have limited utility in confronting the ethical and policy dilemmas associated with AI. (shrink)

Abstract: In this article I argue that the best way to understand the information turn is in terms of a fourth revolution in the long process of reassessing humanity's fundamental nature and role in the universe. We are not immobile, at the centre of the universe (Copernicus); we are not unnaturally distinct and different from the rest of the animal world (Darwin); and we are far from being entirely transparent to ourselves (Freud). We are now slowly accepting the idea that (...) we might be informational organisms among many agents (Turing), inforgs not so dramatically different from clever, engineered artefacts, but sharing with them a global environment that is ultimately made of information, the infosphere. (shrink)

The viewpoint that consciousness, including feeling, could be fully expressed by a computational device is known as strong artificial intelligence or strong AI. Here I offer a defense of strong AI based on machine-state functionalism at the quantum level, or quantum-state functionalism. I consider arguments against strong AI, then summarize some counterarguments I find compelling, including Torkel Franzén’s work which challenges Roger Penrose’s claim, based on Gödel incompleteness, that mathematicians have nonalgorithmic levels of “certainty.” Some consequences of (...) strong AI are then considered. A resolution is offered of some problems including John Searle’s Chinese Room problem and the problem of consciousness propagation under isomorphism. (shrink)

This volume celebrates the various facets of Alan Turing (1912–1954), the British mathematician and computing pioneer, widely considered as the father of computer science. It is aimed at the general reader, with additional notes and references for those who wish to explore the life and work of Turing more deeply. -/- The book is divided into eight parts, covering different aspects of Turing’s life and work. -/- Part I presents various biographical aspects of Turing, some from a personal (...) point of view. -/- Part II presents Turing’s universal machine (now known as a Turing machine), which provides a theoretical framework for reasoning about computation. His 1936 paper on this subject is widely seen as providing the starting point for the field of theoretical computer science. -/- Part III presents Turing’s working on codebreaking during World War II. While the War was a disastrous interlude for many, for Turing it provided a nationally important outlet for his creative genius. It is not an overstatement to say that without Turing, the War would probably have lasted longer, and may even have been lost by the Allies. The sensitive nature of Turning’s wartime work meant that much of this has been revealed only relatively recently. -/- Part IV presents Turing’s post-War work on computing, both at the National Physical Laboratory and at the University of Manchester. He made contributions to both hardware design, through the ACE computer at the NPL, and software, especially at Manchester. Part V covers Turing’s contribution to machine intelligence (now known as Artificial Intelligence or AI). Although Turing did not coin the term, he can be considered a founder of this field which is still active today, authoring a seminal paper in 1950. -/- Part VI covers morphogenesis, Turing’s last major scientific contribution, on the generation of seemingly random patterns in biology and on the mathematics behind such patterns. Interest in this area has increased rapidly in recent times in the field of bioinformatics, with Turing’s 1952 paper on this subject being frequently cited. -/- Part VII presents some of Turing’s mathematical influences and achievements. Turing was remarkably free of external influences, with few co-authors – Max Newman was an exception and acted as a mathematical mentor in both Cambridge and Manchester. -/- Part VIII considers Turing in a wider context, including his influence and legacy to science and in the public consciousness. -/- Reflecting Turing’s wide influence, the book includes contributions by authors from a wide variety of backgrounds. Contemporaries provide reminiscences, while there are perspectives by philosophers, mathematicians, computer scientists, historians of science, and museum curators. Some of the contributors gave presentations at Turing Centenary meetings in 2012 in Bletchley Park, King’s College Cambridge, and Oxford University, and several of the chapters in this volume are based on those presentations – some through transcription of the original talks, especially for Turing’s contemporaries, now aged in their 90s. Sadly, some contributors died before the publication of this book, hence its dedication to them. -/- For those interested in personal recollections, Chapters 2, 3, 11, 12, 16, 17, and 36 will be of interest. For philosophical aspects of Turing’s work, see Chapters 6, 7, 26–31, and 41. Mathematical perspectives can be found in Chapters 35 and 37–39. Historical perspectives can be found in Chapters 4, 8, 9, 10, 13–15, 18, 19, 21–25, 34, and 40. With respect to Turing’s body of work, the treatment in Parts II–VI is broadly chronological. We have attempted to be comprehensive with respect to all the important aspects of Turing’s achievements, and the book can be read cover to cover, or the chapters can be tackled individually if desired. There are cross-references between chapters where appropriate, and some chapters will inevitably overlap. -/- We hope that you enjoy this volume as part of your library and that you will dip into it whenever you wish to enter the multifaceted world of Alan Turing. (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)

Artificial Intelligence (AI) is a technology that makes machines smart and capable of doing things that usually require human intelligence. AI works by training machines to learn from data and experiences. Such devices can recognize patterns, understand spoken language, see and understand images, and even make predictions based on their learning. Voice assistants like Siri or Alexa can understand our voice commands, answer questions, and perform tasks for us. AI-based self-driving cars can sense their surroundings, make decisions, (...) and drive safely without a human driver. AI also helps doctors diagnose diseases, detect fraud in financial transactions, and recommend movies or songs based on one’s preferences. Furthermore, AI has started to make its presence felt in Punjabi culture through various avenues. (shrink)

The ethical concerns regarding the successful development of an Artificial Intelligence have received a lot of attention lately. The idea is that even if we have good reason to believe that it is very unlikely, the mere possibility of an AI causing extreme human suffering is important enough to warrant serious consideration. Others look at this problem from the opposite perspective, namely that of the AI itself. Here the idea is that even if we have good reason to (...) believe that it is very unlikely, the mere possibility of humanity causing extreme suffering to an AI is important enough to warrant serious consideration. This paper starts from the observation that both concerns rely on problematic philosophical assumptions. Rather than tackling these assumptions directly, it proceeds to present an argument that if one takes these assumptions seriously, then one has a moral obligation to advocate for a ban on the development of a conscious AI. (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)