A morally acceptable course of AI development should avoid two dangers: creating unaligned AI systems that pose a threat to humanity and mistreating AI systems that merit moral consideration in their own right. This paper argues these two dangers interact and that if we create AI systems that merit moral consideration, simultaneously avoiding both of these dangers would be extremely challenging. While our argument is straightforward and supported by a wide range of pretheoretical moral judgments, it has far-reaching moral implications (...) for AI development. Although the most obvious way to avoid the tension between alignment and ethical treatment would be to avoid creating AI systems that merit moral consideration, this option may be unrealistic and is perhaps fleeting. So, we conclude by offering some suggestions for other ways of mitigating mistreatment risks associated with alignment. (shrink)

Inchul Yum (2024) argues that the widespread adoption of language agent architectures would likely increase the risk posed by AI by simplifying the process of aligning artificial systems with human values and thereby making it easier for malicious actors to use them to cause a variety of harms. Yum takes this to be an example of a broader phenomenon: progress on the alignment problem is likely to be net safety-negative because it makes artificial systems easier for malicious actors to (...) control. I offer some reasons for skepticism about this surprising and pessimistic conclusion. (shrink)

Important work on alignment systems has been applied to philosophical work on joint action by Tollefsen and Dale. This paper builds from and expands on their work. The first aim of the paper is to spell out how the empirical research on alignment may be integrated into philosophical theories of joint action. The second aim is then to develop a successful characterization of joint action, which spells out the difference between genuine joint action and simpler forms of coordination (...) based on alignment. I begin by introducing the empirical research and two definitions of joint action. I then argue that instead of using this research in conjunction with Searle’s account of collective intentionality, as Tollefsen and Dale suggest, we would be better served by applying this research to Gilbert’s account of plural subjects. In the final sections I distinguish between alignment, coordination, and joint action, clarify the roles of joint commitment and sub-personal alignment in joint action, and argue that... (shrink)

IN “CONSTRUCTIVISM, AGENCY, AND THE PROBLEM of Alignment,” Michael Bratman considers how lessons from the philosophy of action bear on the question of how best to construe the agent’s standpoint in the context of a constructivist theory of practical reasons. His focus is “the problem of alignment”: “whether the pressures from the general constructivism will align with the pressures from the theory of agency” (Bratman 2012: 81). He thus brings two lively literatures into dialogue with each other. This (...) is laudable. However, I shall argue that the considerations Bratman brings to bear from the literature on action do not support his conclusion that evaluative judgments are not constitutive of the agent’s standpoint in the context of constructivism. (shrink)

Tae Wan Kim, John Hooker, and Thomas Donaldson make an attempt, in recent articles, to solve the alignment problem. As they define the alignment problem, it is the issue of how to give AI systems moral intelligence. They contend that one might program machines with a version of Kantian ethics cast in deontic modal logic. On their view, machines can be aligned with human values if such machines obey principles of universalization and autonomy, as well as a deontic (...) utilitarian principle. Programming machines to do so might be useful, in their view, for applications such as future autonomous vehicles. Their proposal draws both on traditional logic-based and contemporary connectionist approaches, to fuse factual information with normative principles. I will argue that this approach makes demands of machines that go beyond what is currently feasible, and may extend past the limits of the possible for AI. I also argue that a deontological ethics for machines should place greater stress on the formula of humanity of the Kantian categorical imperative. On this principle, one ought never treat a person as a mere means. Recognition of what makes a person a person requires ethical insight. Similar insight is needed to tell treatment as a means from treatment as a mere means. The resources in Kim, Hooker, and Donaldson’s approach is insufficient for this reason. Hesitation regarding deployment of autonomous machines is warranted in light of these alignment concerns. (shrink)

Abstract: One approach to alignment with human values in AI and robotics is to engineer artiTicial systems isomorphic with human beings. The idea is that robots so designed may autonomously align with human values through similar developmental processes, to realize project ideal conditions through iterative interaction with social and object environments just as humans do, such as are expressed in narratives and life stories. One persistent problem with human value orientation is that different human beings champion different values as (...) ideal, meaning that the values to which an AI should be aligned are ambiguous. Prior work considered human development of purpose and source of meaning in life in terms of project ideal conditions, in effect establishing lifelong value orientations according to which intermediate situations are evaluated. The present work compares views on motivating values from St. Augustine and from popular cognitive science. These accounts are described as divergent error theories which present to their proponents as mutually exclusive yet accurate accounts of personal experience due to differential development of variable innate potentials. SpeciTically, the hypothesis proposed is that differential development of spindle neural projections establishes enduring connections between prior established relatively immediate routine processes entrained during childhood and prioritized in popular cognitive science, and later developing higher-level social and self-processes entrained during adolescence and emphasized in Augustine's account, with these projections hard-wiring lifelong motivating value orientations more or less inaccessible to modiTication through material interaction. Robot experiments informed by this study may evaluate variable value orientation by design, with for example autonomous robots developing motivating associations with temporally distal project ideal conditions through love for humanity, as described by Augustine, and others pursuing adaptive Tit to passing norms consistent with popular contemporary accounts. (shrink)

In this chapter, we will summarize recent empirical results highlighting how different groups of people solve pure coordination games. Such games are traditionally studied in behavioural economics, where two people need to coordinate without communicating with each other. Our results suggest that coordination choices vary across groups of people, and that people can adapt flexibly to these differences in order to coordinate between groups. We propose that pure coordination games are a useful empirical platform for studying aspects of mindshaping. Drawing (...) on existing psychological literature on alignment during interactions, we suggest that experience of successful interaction leads people to develop aligned intuitions about what is relevant and appropriate that support coordination when interaction and communication is not possible. Consistent with arguments made in the literature on mindshaping we believe that such alignment is more important for coordination than mindreading inferences about mental states, and indeed that mindreading is instead a form of coordination behaviour that is dependent upon intuitive alignment. (shrink)

New technologies such as smart sensors improve rehabilitation processes and thereby increase older adults’ capabilities to participate in social life, leading to direct physical and mental health benefits. Wearable smart sensors for home use have the additional advantage of monitoring day-to-day activities and thereby identifying rehabilitation progress and needs. However, identifying and selecting rehabilitation priorities is ethically challenging because physicians, therapists, and caregivers may impose their own personal values leading to paternalism. Therefore, we develop a discussion template consisting of a (...) series of adaptable questions for the patient–physician encounter based on the capability approach. The goal is to improve geriatric rehabilitation and thereby increase participation in social life and well-being. To achieve this goal, we first analyzed what is considered important for participation on basis of the capability approach, human rights, and ethics of care. Second, we conducted an ethical analysis of each of the four identified dimensions of participation: political, economic, socio-cultural, and care. To improve compliance with rehabilitation measures, health professionals must align rehabilitation measures in an open dialogue with the patient’s aspiration for participation in each dimension. A discussion template based on the capability approach allows for a proactive approach in patient information and stimulates a critical assessment of treatment alternatives while reducing the risk of imposing personal values. (shrink)

New AI technologies have the potential to cause unintended harms in diverse domains including warfare, judicial sentencing, biomedicine and governance. One strategy for realising the benefits of AI whilst avoiding its potential dangers is to ensure that new AIs are properly ‘aligned’ with some form of ‘alignment target.’ One danger of this strategy is that – dependent on the alignment target chosen – our AIs might optimise for objectives that reflect the values only of a certain subset of (...) society, and that do not take into account alternative views about what constitutes desirable and safe behaviour for AI agents. In response to this problem, several AI ethicists have suggested alignment targets that are designed to be sensitive to widespread normative disagreement amongst the relevant stakeholders. Authors inspired by voting theory have suggested that AIs should be aligned with the verdicts of actual or simulated ‘moral parliaments’ whose members represent the normative views of the relevant stakeholders. Other authors inspired by decision theory and the philosophical literature on moral uncertainty have suggested that AIs should maximise socially expected choiceworthiness. In this paper, I argue that both of these proposals face several important problems. In particular, they fail to select attractive ‘compromise options’ in cases where such options are available. I go on to propose and defend an alternative, bargaining-theoretic alignment target, which avoids the problems associated with the voting- and decision-theoretic approaches. (shrink)

Historically, scientific and engineering expertise has been key in shaping research and innovation policies, with benefits presumed to accrue to society more broadly over time. But there is persistent and growing concern about whether and how ethical and societal values are integrated into R&I policies and governance, as we confront public disbelief in science and political suspicion toward evidence-based policy-making. Erosion of such a social contract with science limits the ability of democratic societies to deal with challenges presented by new, (...) disruptive technologies, such as synthetic biology, nanotechnology, genetic engineering, automation and robotics, and artificial intelligence. Many policy efforts have emerged in response to such concerns, one prominent example being Europe's Eighth Framework Programme, Horizon 2020, whose focus on “Responsible Research and Innovation” provides a case study for the translation of such normative perspectives into concrete policy action and implementation. Our analysis of this H2020 RRI approach suggests a lack of consistent integration of elements such as ethics, open access, open innovation, and public engagement. On the basis of our evaluation, we suggest possible pathways for strengthening efforts to deliver R&I policies that deepen mutually beneficial science and society relationships. (shrink)

Abstract. The main current approach to the AI safety is AI alignment, that is, the creation of AI whose preferences are aligned with “human values.” Many AI safety researchers agree that the idea of “human values” as a constant, ordered sets of preferences is at least incomplete. However, the idea that “humans have values” underlies a lot of thinking in the field; it appears again and again, sometimes popping up as an uncritically accepted truth. Thus, it deserves a thorough (...) deconstruction, which I will do by listing and analyzing comprehensively the hidden assumptions of the idea that “humans have values.” This deconstruction of human values will be centered around the following ideas: “Human values” are useful descriptions, but not real objects; “human values” are bad predictors of behavior; the idea of a “human value system” has flaws; “human values” are not good by default; and human values cannot be separated from human minds. The method of analysis is listing hidden assumptions on which the idea of “human values” is built. I recommend that either the idea of “human values” should be replaced with something better for the goal of AI safety, or at least be used very cautiously. The approaches to AI safety which don’t use the idea of human values at all may require more attention, like the use of full brain models, boxing, and capability limiting. (shrink)

Roughly, empirical AI alignment research (AIA) is an area of AI research which investigates empirically how to design AI systems in line with human goals. This paper examines the role of non-epistemic values in AIA. It argues that: (1) Sciences differ in the degree to which values influence them. (2) AIA is strongly value-laden. (3) This influence of values is managed inappropriately and thus threatens AIA’s epistemic integrity and ethical beneficence. (4) AIA should strive to achieve value transparency, critical (...) scrutiny from inside and outside the discipline – involving the public –, and to empower actors without strong commercial interests. (shrink)

Matthew Lipman claims that the community of inquiry is an exemplar of democracy in action. To many proponents the community of inquiry is considered invaluable for achieving desirable social and political ends through education for democracy. But what sort of democracy should we be educating for? In this paper I outline three models of democracy: the liberal model, which emphasises rights and duties, and draws upon pre-political assumptions about freedom; communitarianism, which focuses on identity and participation in the creation of (...) political ends; and deliberative self-governance, whereby citizens deliberatively shape their collective lives in public forums—at various levels of government and in different political and social arenas. I argue that some kind of deliberative democracy is defensible as a preliminary justification for how citizens might shape their lives, and therefore compatible with other forms of democracy, insofar as they can result from democratic deliberations. Acceptance of such a view raises further questions about the purpose or aims of education consistent with this conception of democracy. I contend that it requires an educational model that is committed to aligning curriculum, pedagogy, assessment and school governance to produce a transformational environment that will inform our structures—a commitment to democratic education and not merely education for democracy. Lipman goes part of the way to achieving these ends, but learning how to be proficient at democratic decision-making is like all tasks children and adolescents learn to perform. It involves action, understanding, and awareness of what counts as doing the task adequately. (shrink)

The value alignment problem for artificial intelligence (AI) asks how we can ensure that the “values”—i.e., objective functions—of artificial systems are aligned with the values of humanity. In this paper, I argue that linguistic communication is a necessary condition for robust value alignment. I discuss the consequences that the truth of this claim would have for research programmes that attempt to ensure value alignment for AI systems—or, more loftily, those programmes that seek to design robustly beneficial or (...) ethical artificial agents. (shrink)

The “Value Alignment Problem” is the challenge of how to align the values of artificial intelligence with human values, whatever they may be, such that AI does not pose a risk to the existence of humans. Existing approaches appear to conceive of the problem as "how do we ensure that AI solves the problem in the right way", in order to avoid the possibility of AI turning humans into paperclips in order to “make more paperclips” or eradicating the human (...) race to “solve climate change”. This paper proposes an approach to Alignment rooted in the Enactive theory of mind that reconceptualises it as "how do we make relevant to AI what it relevant to humans". This conceptualisation is supported with a discussion of 4E cognition and goes on to suggest that the Alignment problem and the Frame problem are the same problem. The paper concludes with a discussion of the tradeoffs of the different approaches to value alignment. (shrink)

Large-scale language technologies are increasingly used in various forms of communication with humans across different contexts. One particular use case for these technologies is conversational agents, which output natural language text in response to prompts and queries. This mode of engagement raises a number of social and ethical questions. For example, what does it mean to align conversational agents with human norms or values? Which norms or values should they be aligned with? And how can this be accomplished? In this (...) paper, we propose a number of steps that help answer these questions. We start by developing a philosophical analysis of the building blocks of linguistic communication between conversational agents and human interlocutors. We then use this analysis to identify and formulate ideal norms of conversation that can govern successful linguistic communication between humans and conversational agents. Furthermore, we explore how these norms can be used to align conversational agents with human values across a range of different discursive domains. We conclude by discussing the practical implications of our proposal for the design of conversational agents that are aligned with these norms and values. (shrink)

While representation learning techniques have shown great promise in application to a number of different NLP tasks, they have had little impact on the problem of ontology matching. Unlike past work that has focused on feature engineering, we present a novel representation learning approach that is tailored to the ontology matching task. Our approach is based on embedding ontological terms in a high-dimensional Euclidean space. This embedding is derived on the basis of a novel phrase retrofitting strategy through which semantic (...) similarity information becomes inscribed onto fields of pre-trained word vectors. The resulting framework also incorporates a novel outlier detection mechanism based on a denoising autoencoder that is shown to improve performance. An ontology matching system derived using the proposed framework achieved an F-score of 94% on an alignment scenario involving the Adult Mouse Anatomical Dictionary and the Foundational Model of Anatomy ontology (FMA) as targets. This compares favorably with the best performing systems on the Ontology Alignment Evaluation Initiative anatomy challenge. We performed additional experiments on aligning FMA to NCI Thesaurus and to SNOMED CT based on a reference alignment extracted from the UMLS Metathesaurus. Our system obtained overall F-scores of 93.2% and 89.2% for these experiments, thus achieving state-of-the-art results. (shrink)

The AGI alignment problem has a bimodal distribution of outcomes with most outcomes clustering around the poles of total success and existential, catastrophic failure. Consequently, attempts to solve AGI alignment should, all else equal, prefer false negatives (ignoring research programs that would have been successful) to false positives (pursuing research programs that will unexpectedly fail). Thus, we propose adopting a policy of responding to points of philosophical and practical uncertainty associated with the alignment problem by limiting and (...) choosing necessary assumptions to reduce the risk of false positives. Herein we explore in detail two relevant points of uncertainty that AGI alignment research hinges on---meta-ethical uncertainty and uncertainty about mental phenomena---and show how to reduce false positives in response to them. (shrink)

Ethical, Legal and Social Aspects (ELSA) originated in the 4thEuropean Research Framework Programme (1994) andresponsible research and innovation (RRI) from the EC researchagenda in 2010. ELSA has received renewed attention inEuropean funding schemes and research. This raises the questionof how these two approaches to social responsibility relate toone another and if there is the possibility to align. There is aneed to evaluate the relationship/overlap between ELSA and RRIbecause there is a possibility that new ELSA research will reinventthe wheel if it (...) does not engage with the body of literaturealready present in RRI research. This provides unneeded extrabureaucracy, reformulations of research agendas, extrainvestment, and an overabundance of frameworks to implement,and ELSA research does not take advantage of the body ofresearch developed in RRI. This paper evaluates how ELSA andRRI diverge, are complementary, and can be aligned. (shrink)

The Foundational Model of Anatomy (FMA) symbolically represents the structural organization of the human body from the macromolecular to the macroscopic levels, with the goal of providing a robust and consistent scheme for classifying anatomical entities that is designed to serve as a reference ontology in biomedical informatics. Here we articulate the need for formally clarifying the is-a and part-of relations in the FMA and similar ontology and terminology systems. We diagnose certain characteristic errors in the treatment of these relations (...) and show how these errors can be avoided through adoption of the formalism we describe. We then illustrate how a consistently applied formal treatment of taxonomy and partonomy can support the alignment of ontologies. (shrink)

Complex technology has become an essential aspect of everyday life. We rely on technology as part of basic infrastructure and repeatedly for tasks throughout the day. Yet, in many cases the relation surpasses mere reliance and evolves to trust in technology. A new, disruptive technology is blockchain. It claims to introduce trustless relationships among its users, aiming to eliminate the need for trust altogether—even being described as “the trust machine”. This paper presents a proposal to adjust the concept of trust (...) in blockchain applications with the tools provided by conceptual engineering. Its goal is to propose a concept of trust, that offers more than a halo term, devoid of the normative depth that the original, philosophical term actually carries. To evaluate possible concepts of trust in blockchain applications, five criteria are proposed: These criteria ensure that the conceptual relation indeed embodies trust, thereby being richer than mere reliance, and that the chosen concept highlights the active role of the trustor. While the concepts of trust in engineers and trust in algorithms have to be discarded, institutional trust emerges as a viable candidate, given some refinements. Ultimately, the concept of trust by normative expectations and attribution is suggested to capture the essence of trust in blockchain applications. (shrink)

I propose an approach that expands philosophical views of scientific change, on the basis of an analysis of contemporary biomedical research and recent developments in the philosophy of scientific change. Focusing on the establishment of the exposome in epidemiology as a case study and the role of data as a context for contrasting views on change, I discuss change at conceptual, methodological, material, and social levels of biomedical epistemology. Available models of change provide key resources to discuss this type of (...) change, but I present the need for an approach that models transfer, alignment, and influence as key processes of change. I develop this as a pragmatic approach to scientific change, where processes might change substantially depending on specific circumstances, thus contributing to and complementing the debate on a crucial epistemological issue. (shrink)

The AGI alignment problem has a bimodal distribution of outcomes with most outcomes clustering around the poles of total success and existential, catastrophic failure. Consequently, attempts to solve AGI alignment should, all else equal, prefer false negatives (ignoring research programs that would have been successful) to false positives (pursuing research programs that will unexpectedly fail). Thus, we propose adopting a policy of responding to points of metaphysical and practical uncertainty associated with the alignment problem by limiting and (...) choosing necessary assumptions to reduce the risk false positives. Herein we explore in detail some of the relevant points of uncertainty that AGI alignment research hinges on and consider how to reduce false positives in response to them. (shrink)

-/- Policy regulations of ethically controversial genetic technologies should, on the one hand, be based on ethical principles. On the other hand, they should be socially acceptable to ensure implementation. In addition, they should align with ethical theory. Yet to date we lack a reliable and valid scale to measure the relevant ethical judgements in laypeople. We target this lacuna. -/- We developed a scale based on ethical principles to elicit lay judgments: the Genetic Technologies Questionnaire (GTQ). In two pilot (...) studies and a pre-registered main study, we validated the scale in a representative sample of the US population. -/- The final version of the scale contains 20 items but remains highly reliable even when reduced to five. It also predicts behaviour; for example, ethical judgments as measured by the GTQ predicted hypothetical donations and grocery shopping. In addition, the GTQ may be of interest to policymakers and ethicists because it reveals coherent and ethically justified judgments in laypeople. For instance, the GTQ indicates that ethical judgments are sensitive to possible benefits and harms (in line with utilitarian ethics), but also to ethical principles such as the value of consent-autonomy. -/- In conclusion, the GTQ can be recommended for research in both experimental psychology and applied ethics, as well as a tool for ethically and empirically informed policymaking. (shrink)

In this open access book, Carlos Montemayor illuminates the development of artificial intelligence (AI) by examining our drive to live a dignified life. -/- He uses the notions of agency and attention to consider our pursuit of what is important. His method shows how the best way to guarantee value alignment between humans and potentially intelligent machines is through attention routines that satisfy similar needs. Setting out a theoretical framework for AI Montemayor acknowledges its legal, moral, and political implications (...) and takes into account how epistemic agency differs from moral agency. -/- Through his insightful comparisons between human and animal intelligence, Montemayor makes it clear why adopting a need-based attention approach justifies a humanitarian framework. This is an urgent, timely argument for developing AI technologies based on international human rights agreements. (shrink)

Astrology research has been using artificial intelligence (AI) to improve the understanding of astrological properties and processes. Like the large language models of AI, astrology is also a language model with a similar underlying linguistic structure but with a distinctive layer of lifestyle contexts. Recent research in semantic proximities and planetary dominance models have helped to quantify effective astrological information. As AI learning and intelligence grows, a major concern is with maintaining its alignment with human values and intentions. Astrology (...) has an extensive background and theory on how different values and expressions of intelligence are resolved. As AI learns to interact with improved astrological models backed by evidence, the integration could produce a stable and insightful alignment of the two disciplines. (shrink)

Abstract This paper examines the Eden narrative as an allegory for the interplay of free will, ethical alignment, and the emergence of “dark information.” It argues that God’s will can be understood as divine information—a foundational structure that ensures harmony when adhered to. Through divergence from this information, entropy is introduced, necessitating cyclical renewal. By exploring theological, philosophical, and informational perspectives, this paper highlights the relevance of these concepts in addressing modern challenges, offering actionable frameworks for realignment with foundational (...) truths. (shrink)

In this brief reply I respond to criticisms of my book, The referential mechanism of proper names, from Michael Devitt and Nicolo D'Agruma. I focus on the question of whether the perspectivism advocated in the book explains the empirical results there detailed.

Because wars are fought by human beings and not merely machines, a strong virtue ethic is an essential prerequisite for those engaged in combat. From a philosophical perspective, war has historically been seen as separate and outside of the commonly accepted forms of morality. Yet there remains a general, though not well-thought out, sense that those human beings who fight wars should act ethically. Since warfighters are often called upon to contemplate and complete tasks during war that are not normally (...) required of non-warfighters (civilians), and it is believed these warfighters should act ethically, it becomes necessary to ask: What does soldierly virtue look like? In order to answer this question, I will examine essential elements of moral responsibility and military authority. Once complete, I will propose an Aristotelian-based virtue ethics system, one that is equally valuable to warfighter and civilian. To do this, I will examine the conversation in academia regarding virtue ethics and the foundations of virtue. I will provide both a cursory and deep reading of elements of Aristotle’s conception of virtue, but ultimately I will provide a slightly more rigorous reading and reinterpretation of an Aristotelian-based virtue ethic, with a definitive final recommendation for this interpretation being best for everyone, in war or walking down the street. Upon completing a study of this work, one will walk away with a next-generation interpretation of Aristotelian-based Virtue Ethics that denies eudaimonia as the central principle, relying instead on phronesis as its central theme. Phronesis, when properly developed in the warfighter will lead to moral responsibility, better decision-making, and a seamless re-integration into civilian life once has returned from the horrors of war. (shrink)

The alignment problem in artificial intelligence (AI) is a critical challenge that extends beyond the need to align future superintelligent systems with human values. This paper argues that even "merely intelligent" AI systems, built on current-gen technologies, pose existential risks due to their competence-without-comprehension nature. Current AI models, despite their advanced capabilities, lack intrinsic moral reasoning and are prone to catastrophic misalignment when faced with ethical dilemmas, as illustrated by recent controversies. Solutions such as hard-coded censorship and rule-based restrictions (...) prove inadequate, as they fail to imbue AI with a true understanding of moral complexities, making these systems vulnerable to manipulation. To address these risks, the paper explores a paradigm shift from competence to comprehension, emphasizing the importance of developing AI systems with an intrinsic value framework capable of moral reasoning. By adopting intrinsic teleology, AI could self-reflect, simulate other minds, and develop empathy, which would enable it to navigate ethical dilemmas in ways that are currently impossible. Using theories from philosophy, ethics, and AI research, the paper proposes the development of AI systems that can reason through moral dilemmas autonomously, suggesting that such systems would be safer and more alignable than current generation competence-driven AI. (shrink)

The field of AI safety aims to prevent increasingly capable artificially intelligent systems from causing humans harm. Research on moral alignment is widely thought to offer a promising safety strategy: if we can equip AI systems with appropriate ethical rules, according to this line of thought, they'll be unlikely to disempower, destroy or otherwise seriously harm us. Deontological morality looks like a particularly attractive candidate for an alignment target, given its popularity, relative technical tractability and commitment to harm-avoidance (...) principles. I argue that the connection between moral alignment and safe behavior is more tenuous than many have hoped. In general, AI systems can possess either of these properties in the absence of the other, and we should favor safety when the two conflict. In particular, advanced AI systems governed by standard versions of deontology need not be especially safe. (shrink)

Motivated by the question of responsible AI and value alignment, I seek to offer a uniquely Foucauldian reconstruction of the problem as the emergence of an ethical subject in a disciplinary setting. This reconstruction contrasts with the strictly human-oriented programme typical to current scholarship that often views technology in instrumental terms. With this in mind, I problematise the concept of a technological subjectivity through an exploration of various aspects of ChatGPT in light of Foucault’s work, arguing that current systems (...) lack the reflexivity and self-formative characteristics inherent in the notion of the subject. By drawing upon a recent dialogue between Foucault and phenomenology, I suggest four techno-philosophical desiderata that would address the gaps in this search for a technological subjectivity: embodied self-care, embodied intentionality, imagination and reflexivity. Thus I propose that advanced AI be reconceptualised as a subject capable of “technical” self-crafting and reflexive self-conduct, opening new pathways to grasp the intertwinement of the human and the artificial. This reconceptualization holds the potential to render future AI technology more transparent and responsible in the circulation of knowledge, care and power. (shrink)

Ambitious value learning proposals to solve the AI alignment problem and avoid catastrophic outcomes from a possible future misaligned artificial superintelligence (such as Coherent Extrapolated Volition [CEV]) have focused on ensuring that an artificial superintelligence (ASI) would try to do what humans would want it to do. However, present and future sentient non-humans, such as non-human animals and possible future digital minds could also be affected by the ASI’s behaviour in morally relevant ways. This paper puts forward Sentientist Coherent (...) Extrapolated Volition, an alternative to CEV, that directly takes into account the interests of all sentient beings. This ambitious value learning proposal would significantly reduce the likelihood of risks of astronomical suffering from the ASI’s behaviour, and thus we have very strong pro-tanto moral reasons in favour of implementing it instead of CEV. This fact is crucial in conducting an adequate cost-benefit analysis between different ambitious value learning proposals. (shrink)

Prisoners, those who probably engaged in criminal activities, might possess different perceptions and notions of moral foundations than non-prisoners. Thus, assessing such foundations among the population without testing the validity of the measure may produce biased outcomes. To address the potential methodological issue, we examined the validity of the measurement model for moral foundations among prisoners and community members, i.e., non-prisoners. We conducted the measurement invariance test and measurement alignment to test whether the model was consistently valid across the (...) groups. We also employed the differential item functioning test to examine whether item responses were not biased between the different populations. Results demonstrated significant measurement non-invariance and differential item functioning. However, measurement alignment could address the non-invariance issue. Between-group comparisons of moral foundations were consistent with findings from prior research after performing the alignment. (shrink)

This paper serves as an intuition building mechanism for understanding the basics of AI, misalignment, and the reasons for why strong AI is being pursued. The approach is to engage with both pro and anti AI development arguments to gain a deeper understanding of both views, and hopefully of the issue as a whole. We investigate the basics of misalignment, common misconceptions, and the arguments for why we would want to pursue strong AI anyway. The paper delves into various aspects (...) of the problem, including existential risk, deception, hedonic adaptation, and the potential for the complete extinction of humanity. By integrating multiple elements of philosophy, this paper aims to provide a holistic understanding of the alignment problem and its significance for the future of humanity. (shrink)

This article presents a simple derivation of optimization models for reaction networks leading to a generalized form of the mass-action law, and compares the formal structure of Minimum Information Divergence, Quadratic Programming and Kirchhoff type network models. These optimization models are used in related articles to develop and illustrate the operation of ontology alignment algorithms and to discuss closely connected issues concerning the epistemological and statistical significance of sharp or precise hypotheses in empirical science.

This paper explores the potential of integrating ancient educational principles from diverse eastern cultures into modern AI ethics curricula. It draws on the rich educational traditions of ancient China, India, Arabia, Persia, Japan, Tibet, Mongolia, and Korea, highlighting their emphasis on philosophy, ethics, holistic development, and critical thinking. By examining these historical educational systems, the paper establishes a correlation with modern AI ethics principles, advocating for the inclusion of these ancient teachings in current AI development and education. The proposed integration (...) aims to provide a comprehensive education that not only encompasses foundational knowledge but also advanced learning, thereby equipping future AI professionals with the necessary tools to develop AI systems that are ethically responsible, culturally aware, and aligned with human values such as fairness, safety, transparency, and collaboration. This approach not only addresses the AI alignment problem but also fosters cultural harmony and global understanding, which are crucial in an increasingly interconnected world. The paper posits that the wisdom of ancient educational systems, when harmonized with modern AI ethics, can guide the development of AI technologies that are beneficial for humanity, ensuring these advancements are not just technologically sound but also ethically and culturally informed. (shrink)

Recent years have seen rapid progress in the development of ontologies as semantic models intended to capture and represent aspects of the real world. There is, however, great variation in the quality of ontologies. If ontologies are to become progressively better in the future, more rigorously developed, and more appropriately compared, then a systematic discipline of ontology evaluation must be created to ensure quality of content and methodology. Systematic methods for ontology evaluation will take into account representation of individual ontologies, (...) performance (in terms of accuracy, domain coverage and the efficiency and quality of automated reasoning using the ontologies) on tasks for which the ontology is designed and used, degree of alignment with other ontologies and their compatibility with automated reasoning. A sound and systematic approach to ontology evaluation is required to transform ontology engineering into a true scientific and engineering discipline. This chapter discusses issues and problems in ontology evaluation, describes some current strategies, and suggests some approaches that might be useful in the future. (shrink)

This paper presents a new trilemma with respect to resolving the control and alignment problems in machine ethics. Section 1 outlines three possible types of artificial moral agents (AMAs): (1) 'Inhuman AMAs' programmed to learn or execute moral rules or principles without understanding them in anything like the way that we do; (2) 'Better-Human AMAs' programmed to learn, execute, and understand moral rules or principles somewhat like we do, but correcting for various sources of human moral error; and (3) (...) 'Human-Like AMAs' programmed to understand and apply moral values in broadly the same way that we do, with a human-like moral psychology. Sections 2–4 then argue that each type of AMA generates unique control and alignment problems that have not been fully appreciated. Section 2 argues that Inhuman AMAs are likely to behave in inhumane ways that pose serious existential risks. Section 3 then contends that Better-Human AMAs run a serious risk of magnifying some sources of human moral error by reducing or eliminating others. Section 4 then argues that Human-Like AMAs would not only likely reproduce human moral failures, but also plausibly be highly intelligent, conscious beings with interests and wills of their own who should therefore be entitled to similar moral rights and freedoms as us. This generates what I call the New Control Problem: ensuring that humans and Human-Like AMAs exert a morally appropriate amount of control over each other. Finally, Section 5 argues that resolving the New Control Problem would, at a minimum, plausibly require ensuring what Hume and Rawls term ‘circumstances of justice’ between humans and Human-Like AMAs. But, I argue, there are grounds for thinking this will be profoundly difficult to achieve. I thus conclude on a skeptical note. Different approaches to developing ‘safe, ethical AI’ generate subtly different control and alignment problems that we do not currently know how to adequately resolve, and which may or may not be ultimately surmountable. (shrink)

There are two types of artificial general intelligence (AGI) safety solutions: global and local. Most previously suggested solutions are local: they explain how to align or “box” a specific AI (Artificial Intelligence), but do not explain how to prevent the creation of dangerous AI in other places. Global solutions are those that ensure any AI on Earth is not dangerous. The number of suggested global solutions is much smaller than the number of proposed local solutions. Global solutions can be divided (...) into four groups: 1. No AI: AGI technology is banned or its use is otherwise prevented; 2. One AI: the first superintelligent AI is used to prevent the creation of any others; 3. Net of AIs as AI police: a balance is created between many AIs, so they evolve as a net and can prevent any rogue AI from taking over the world; 4. Humans inside AI: humans are augmented or part of AI. We explore many ideas, both old and new, regarding global solutions for AI safety. They include changing the number of AI teams, different forms of “AI Nanny” (non-self-improving global control AI system able to prevent creation of dangerous AIs), selling AI safety solutions, and sending messages to future AI. Not every local solution scales to a global solution or does it ethically and safely. The choice of the best local solution should include understanding of the ways in which it will be scaled up. Human-AI teams or a superintelligent AI Service as suggested by Drexler may be examples of such ethically scalable local solutions, but the final choice depends on some unknown variables such as the speed of AI progress. (shrink)

Various thinkers have been attempting to align artificial intelligence (AI) with ethics (Christian, 2020; Russell, 2021), the so-called problem of alignment, but some suspect that the problem may be intractable (Yampolskiy, 2023). In the following, we make an argument by analogy to analyze the possibility that the problem of alignment could be intractable. We show how the Tri-Omni properties in theology can direct us towards analogous properties for artificial superintelligence, Tri-Opti properties. However, just as the Tri-Omni properties are (...) vulnerable to metaphysical incompatibility, we will show that the Tri-Opti properties are vulnerable to a corresponding physical incompatibility, because optimal physical systems exist on the Pareto Frontier. We will explain that, while Tri-Omni incompatibility thus seems metaphysically soluble, the Tri-Opti incompatibility seems physically insoluble due to the constraints of multi-variable optimization. Finally, we will provide some scenarios by which this incompatibility may be realized. Besides for the primary purpose of its theoretical considerations, this analysis has the secondary interdisciplinary purpose of communicating to the theologically literate the potential importance of AI safety work, and the gesturing towards the possibility of the collaboration in both fields on topics in ethics, epistemology, and ontology. (shrink)

Cyber attackers targeting large corporations achieved a high perimeter penetration success rate during 2013, resulting in many corporations incurring financial losses. Corporate information technology leaders have a fiduciary responsibility to implement information security domain processes that effectually address the challenges for preventing and deterring information security breaches. Grounded in corporate governance theory, the purpose of this correlational study was to examine the relationship between strategic alignment, resource management, risk management, value delivery, performance measurement implementations, and information security governance (ISG) (...) effectiveness in United States-based corporations. Surveys were used to collect data from 95 strategic and tactical leaders of the 500 largest for-profit United States headquartered corporations. The results of the multiple linear regression indicated the model was able to significantly predict ISG effectiveness, F(5, 89) = 3.08, p = 0.01, R² = 0.15. Strategic alignment was the only statistically significant (t = 2.401, p <= 0.018) predictor. The implications for positive social change include the potential to constructively understand the correlates of ISG effectiveness, thus increasing the propensity for consumer trust and reducing consumers' costs. (shrink)

The alignment problem in the context of large language models must consider the plurality of human values in our world. Whilst there are many resonant and overlapping values amongst the world’s cultures, there are also many conflicting, yet equally valid, values. It is important to observe which cultural values a model exhibits, particularly when there is a value conflict between input prompts and generated outputs. We discuss how the co- creation of language and cultural value impacts large language models (...) (LLMs). We explore the constitution of the training data for GPT-3 and compare that to the world’s language and internet access demographics, as well as to reported statistical profiles of dominant values in some Nation-states. We stress tested GPT-3 with a range of value-rich texts representing several languages and nations; including some with values orthogonal to dominant US public opinion as reported by the World Values Survey. We observed when values embedded in the input text were mutated in the generated outputs and noted when these conflicting values were more aligned with reported dominant US values. Our discussion of these results uses a moral value pluralism (MVP) lens to better understand these value mutations. Finally, we provide recommendations for how our work may contribute to other current work in the field. (shrink)

Propositions are often aligned with truth-conditions. The view is mistaken, since propositions discriminate where truth conditions do not. Propositions are hyperintensional: they are sensitive to necessarily equivalent differences. I investigate an alternative view on which propositions are truthmaker conditions, understood as sets of possible truthmakers. This requires making metaphysical sense of merely possible states of affairs. The theory that emerges illuminates the semantic phenomena of samesaying, subject matter, and aboutness.

Several scholars align Nietzsche’s philosophy with Stoicism because of their naturalist approaches to ethics and doctrines of eternal recurrence. Yet this alignment is difficult to reconcile with Nietzsche’s criticisms of Stoicism’s ethical ideal of living according to nature by dispassionately accepting fate—so much so that some conclude that Nietzsche’s rebuke of Stoicism undermines his own philosophical project. I argue that affinities between Nietzsche and Stoicism belie deeper disagreement about teleology, which, in turn, yields different understandings of nature and human (...) flourishing, so that Nietzsche’s objections to Stoicism support his commitments to ethical naturalism and to affirming life’s eternal recurrence. (shrink)

The religious right often aligns its patriarchal opposition to same-sex marriage with the defence of religious freedom. In this article, I identify resources for confronting such prejudicial religiosity by surveying two predominant feminist approaches to same-sex marriage that are often assumed to be at odds: discourse ethics and queer critical theory. This comparative analysis opens up to view commitments that may not be fully recognizable from within either feminist framework: commitments to ideals of selfhood, to specific conceptions of justice, and (...) to particular definitions of secularism. I conclude by examining the "postsecular" turn in feminism, suggesting that we can see the same-sex marriage debate not in terms of an impasse between differing feminist approaches, but in terms of shared existential and ethical affinities. (shrink)

Environmental activism is crucial for raising public awareness and support toward addressing the climate crisis. However, using climate change mitigation as the cause for blockage, vandalism, and harassment activities might be counterproductive and risk causing negative repercussions and declining public support. The paper describes a dataset of metadata of 89 blockage, vandalism, and harassment events happening in recent years. The dataset comprises three main categories: 1) Events, 2) Activists, and 3) Consequences. For researchers interested in environmental activism, climate change, and (...) sustainability, the dataset is helpful in studying the effectiveness and appropriateness of strategies to raise public awareness and support. For researchers in the field of security studies and green criminology, the dataset offers resources to study features and impacts of blockage, vandalism, and harassment events. The Bayesian Mindsponge Framework (BMF) analytics was employed to validate the dataset. Consequently, the estimated result aligns with the Mindsponge Theory’s theoretical reasoning. (shrink)

There is no strict alignment between induction and fallibility, nor between deduction and certainty. Fallibility in deductive inferences, such as failed mathematical theorems, demonstrates that deduction does not guarantee certainty. Similarly, inductive reasoning, typically seen as weaker and more prone to uncertainty, is not inherently tied to fallibility. In fact, inductive generalizations can sometimes lead to certainty, especially in mathematical contexts. By decoupling induction from fallibility and deduction from certainty, we preserve the distinct nature of each form of reasoning, (...) allowing them to be properly understood without unnecessary constraints. (shrink)

Technology should be aligned with our values. We make the case that attempts to align emerging technologies with our values should reflect critically on these values. Critical thinking seems like a natural starting point for the critical assessment of our values. However, extant conceptualizations of critical thinking carve out no space for the critical scrutiny of values. We will argue that we need critical thinking that focuses on values instead of taking them as unexamined starting points. In order to play (...) a crucial role in helping to align values and technology, critical thinking needs to be modified and refocused on values. Here, we outline what value-centred critical thinking could look like. (shrink)