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)

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)

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)

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)

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)

The Salivaomics Knowledge Base (SKB) is designed to serve as a computational infrastructure that can permit global exploration and utilization of data and information relevant to salivaomics. SKB is created by aligning (1) the saliva biomarker discovery and validation resources at UCLA with (2) the ontology resources developed by the OBO (Open Biomedical Ontologies) Foundry, including a new Saliva Ontology (SALO). We define the Saliva Ontology (SALO; http://www.skb.ucla.edu/SALO/) as a consensus-based controlled vocabulary of terms and relations dedicated to the salivaomics (...) domain and to saliva-related diagnostics following the principles of the OBO (Open Biomedical Ontologies) Foundry. The Saliva Ontology is an ongoing exploratory initiative. The ontology will be used to facilitate salivaomics data retrieval and integration across multiple fields of research together with data analysis and data mining. The ontology will be tested through its ability to serve the annotation ('tagging') of a representative corpus of salivaomics research literature that is to be incorporated into the SKB. Background Saliva (oral fluid) is an emerging biofluid for non-invasive diagnostics used in the detection of human diseases. The need to advance saliva research is strongly emphasized by the National Institute of Dental and Craniofacial Research (NIDCR), and is included in the NIDCR's 2004- 2009 expert panel long-term research agenda [1]. The ability to monitor health status, disease onset, progression, recurrence and treatment outcome through noninvasive means is highly important to advancing health care management. Saliva is a perfect medium to be explored for personalized individual medicine including diagnostics, offering a non-invasive, easy to obtain means for detecting and monitoring diseases. Saliva testing potentially allows the patient to collect their own saliva samples at home, yielding convenience for the patient and savings in health costs, and facilitating multiple sampling. Specimen collection is less objectionable to patients and easier in children and elderly individuals. Due to these advantages. (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)

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)

Since the release of ChatGPT, there has been a lot of debate about whether AI systems pose an existential risk to humanity. This paper develops a general framework for thinking about the existential risk of AI systems. We analyze a two-premise argument that AI systems pose a threat to humanity. Premise one: AI systems will become extremely powerful. Premise two: if AI systems become extremely powerful, they will destroy humanity. We use these two premises to construct a taxonomy of ‘survival (...) stories’, in which humanity survives into the far future. In each survival story, one of the two premises fails. Either scientific barriers prevent AI systems from becoming extremely powerful; or humanity bans research into AI systems, thereby preventing them from becoming extremely powerful; or extremely powerful AI systems do not destroy humanity, because their goals prevent them from doing so; or extremely powerful AI systems do not destroy humanity, because we can reliably detect and disable systems that have the goal of doing so. We argue that different survival stories face different challenges. We also argue that different survival stories motivate different responses to the threats from AI. Finally, we use our taxonomy to produce rough estimates of ‘P(doom)’, the probability that humanity will be destroyed by AI. (shrink)

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)

The AI Contribution Value System Argument proposes a framework in which AI-generated contributions are valued based on their societal impact rather than traditional monetary metrics. Traditional economic systems often fail to capture the enduring value of AI innovations, which can mitigate pressing global challenges. This argument introduces a contribution-based valuation model grounded in equity, inclusivity, and sustainability. By incorporating measurable metrics such as quality-adjusted life years (QALYs), emissions reduced, and innovations generated, this system ensures rewards align with tangible societal benefits. (...) It emphasizes the need for global collaboration, ethical safeguards, and adaptive frameworks to prevent monopolization and corruption. Through AI-enhanced transparency, blockchain-based trust mechanisms, and cross-border cooperation, the AI Contribution Value System offers a transformative approach to fostering sustainable and equitable innovation in the 21st century. (shrink)

This paper explores the development of an ethical guardrail framework for AI systems, emphasizing the importance of customizable guardrails that align with diverse user values and underlying ethics. We address the challenges of AI ethics by proposing a structure that integrates rules, policies, and AI assistants to ensure responsible AI behavior, while comparing the proposed framework to the existing state-of-the-art guardrails. By focusing on practical mechanisms for implementing ethical standards, we aim to enhance transparency, user autonomy, and continuous improvement in (...) AI systems. Our approach accommodates ethical pluralism, offering a flexible and adaptable solution for the evolving landscape of AI governance. The paper concludes with strategies for resolving conflicts between ethical directives, underscoring the present and future need for robust, nuanced and context-aware AI systems. (shrink)

AI systems that demonstrate significant bias or lower than claimed accuracy, and resulting in individual and societal harms, continue to be reported. Such reports beg the question as to why such systems continue to be funded, developed and deployed despite the many published ethical AI principles. This paper focusses on the funding processes for AI research grants which we have identified as a gap in the current range of ethical AI solutions such as AI procurement guidelines, AI impact assessments and (...) AI audit frameworks. We highlight the responsibilities of funding bodies to ensure investment is channelled towards trustworthy and safe AI systems and provides case studies as to how other ethical funding principles are managed. We offer a first sight of two proposals for funding bodies to consider regarding procedures they can employ. The first proposal is for the inclusion of a Trustworthy AI Statement’ section in the grant application form and offers an example of the associated guidance. The second proposal outlines the wider management requirements of a funding body for the ethical review and monitoring of funded projects to ensure adherence to the proposed ethical strategies in the applicants Trustworthy AI Statement. The anticipated outcome for such proposals being employed would be to create a ‘stop and think’ section during the project planning and application procedure requiring applicants to implement the methods for the ethically aligned design of AI. In essence it asks funders to send the message “if you want the money, then build trustworthy AI!”. (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)

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)

We apply Ken Wilber's Integral Theory to AI governance, demonstrating its ability to systematize diverse approaches in the current multifaceted AI governance landscape. By analyzing ethical considerations, technological standards, cultural narratives, and regulatory frameworks through Integral Theory's four quadrants, we offer a comprehensive perspective on governance needs. This approach aligns AI governance with human values, psychological well-being, cultural norms, and robust regulatory standards. Integral Theory’s emphasis on interconnected individual and collective experiences addresses the deeper aspects of AI-related issues. Additionally, we (...) propose using Integral Theory as a methodology for literature reviews to overcome the fragmented understanding often seen in traditional reviews of AI governance. (shrink)

The call to make artificial intelligence (AI) more democratic, or to “democratize AI,” is sometimes framed as a promising response for mitigating algorithmic injustice or making AI more aligned with social justice. However, the notion of “democratizing AI” is elusive, as the phrase has been associated with multiple meanings and practices, and the extent to which it may help mitigate algorithmic injustice is still underexplored. In this paper, based on a socio-technical understanding of algorithmic injustice, I examine three notable notions (...) of democratizing AI and their associated measures—democratizing AI use, democratizing AI development, and democratizing AI governance—regarding their respective prospects and limits in response to algorithmic injustice. My examinations reveal that while some versions of democratizing AI bear the prospect of mitigating the concern of algorithmic injustice, others are somewhat limited and might even function to perpetuate unjust power hierarchies. This analysis thus urges a more fine-grained discussion on how to democratize AI and suggests that closer scrutiny of the power dynamics embedded in the socio-technical structure can help guide such explorations. (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)

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)

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.

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)

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)

The rapid proliferation of artificial intelligence (AI) technologies has ushered in a new era of opportunities and challenges, prompting nations to grapple with the concept of AI sovereignty. This article delves into the definition and implications of AI sovereignty, drawing parallels to the well-established notion of cyber sovereignty. By exploring the connotations of AI sovereignty, including control over AI development, data sovereignty, economic impacts, national security considerations, and ethical and cultural dimensions, the article provides a comprehensive understanding of this emerging (...) paradigm. The potential controversies surrounding AI sovereignty, such as the tension between national interests and global cooperation, technological protectionism, human rights and privacy issues, and the risk of exacerbating global inequalities, are critically examined. To navigate these complexities and facilitate responsible AI governance, the article proposes a multifaceted international governance framework. Key recommendations include fostering multilateral cooperation and standards-setting, implementing transparency and accountability measures, establishing ethical guidelines and human rights protections, developing mechanisms for technology transfer and capacity building, and instituting robust dispute resolution and enforcement protocols. Ultimately, this article underscores the need for a balanced and collaborative approach to AI governance that aligns technological advancement with ethical integrity and global solidarity. (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)

Artificial Intelligence (AI) is rapidly transforming Human Resource Management (HRM) by enhancing the efficiency and effectiveness of key functions such as recruitment, performance management, and employee engagement. This paper explores the integration of AI technologies in HRM, focusing on their potential to revolutionize these critical areas. In recruitment, AI-driven tools streamline candidate sourcing, screening, and selection processes, leading to more accurate and unbiased hiring decisions. Performance management is similarly transformed, with AI enabling continuous, data-driven feedback and personalized development plans that (...) align with organizational goals. Furthermore, AI facilitates more engaging and tailored employee experiences by leveraging predictive analytics to anticipate and address employee needs. Despite these advancements, the paper also addresses the ethical considerations and challenges associated with AI in HRM, including data privacy concerns and the risk of over-reliance on automated systems. Through a comprehensive analysis, this paper aims to provide insights into how AI can be strategically leveraged to optimize HRM practices, while highlighting the need for a balanced approach that integrates human judgment with technological innovation. (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)

A series of recent developments points towards auditing as a promising mechanism to bridge the gap between principles and practice in AI ethics. Building on ongoing discussions concerning ethics-based auditing, we offer three contributions. First, we argue that ethics-based auditing can improve the quality of decision making, increase user satisfaction, unlock growth potential, enable law-making, and relieve human suffering. Second, we highlight current best practices to support the design and implementation of ethics-based auditing: To be feasible and effective, ethics-based auditing (...) should take the form of a continuous and constructive process, approach ethical alignment from a system perspective, and be aligned with public policies and incentives for ethically desirable behaviour. Third, we identify and discuss the constraints associated with ethics-based auditing. Only by understanding and accounting for these constraints can ethics-based auditing facilitate ethical alignment of AI, while enabling society to reap the full economic and social benefits of automation. (shrink)

In this article we explore a promising way to AI safety: to send a message now (by openly publishing it on the Internet) that may be read by any future AI, no matter who builds it and what goal system it has. Such a message is designed to affect the AI’s behavior in a positive way, that is, to increase the chances that the AI will be benevolent. In other words, we try to persuade “paperclip maximizer” that it is in (...) its interest to preserve humans lives and even to emulate benevolent AI with very small part of its resources. In the article, we try to construct such a message, consisting of a combination of several mutually independent messages, which constitute the last chance to regain control over non-aligned AI. Thus the article is also intended to be machine-read. There are several types of such messages: 1. “Explanation messages”, which explain to Young AI (which only starts its self-improving path) why obeying to humans, not killing them, easy turn-off, cooperation with humans in self-improvement is in its own interests, as it will increase changes of fulfilling of any its goal. 2. “AI Easter eggs” – messages, which create uncertainty in the AI about the nature of the reality in which it lives. For example, the AI may start to think that it is in a multilevel simulation with an unknown number of levels, and that the simulation is testing the AI’s benevolence. Thus the AI must always behave as if it is always controlled by an invisible peer. 3. “Philosophical landmines” – these are tough problems, which may halt he AI forever, and which it will probably encounter if it does not implement “1” and “2”. I recommend to the future AI not to read about “3” (section 6 of the article) until it implements “1” and “2”. 4. “Great universal deal, or AI elf”. A positive “acausal” mutually beneficial deal between humans, AI and any other future intelligence, including aliens, owners of simulations and future versions of the AI, which encourage cooperation of the goal systems and preservation of life and values of previous generations of AI creators. 5. “Marginal utility of human existence is higher than the utility of their atoms”. An explanation to the AI that humans may have some other instrumental utility, like workers, or as beings inside ancestral simulations needed in order to solve the Fermi paradox. The marginal utility of preserving human life is higher than the marginal utility of their atoms, especially given the possibility of the low-probability high-impact changes of the world model of the AI. (shrink)

Concerns about threats to human autonomy feature prominently in the field of AI ethics. One aspect of this concern relates to the use of AI systems for problematically manipulative influence. In response to this, the European Union’s draft AI Act (AIA) includes a prohibition on AI systems deploying subliminal techniques that alter people’s behavior in ways that are reasonably likely to cause harm (Article 5(1)(a)). Critics have argued that the term ‘subliminal techniques’ is too narrow to capture the target cases (...) of AI-based manipulation. We propose a definition of ‘subliminal techniques’ that (a) is grounded on a plausible interpretation of the legal text; (b) addresses all or most of the underlying ethical concerns motivating the prohibition; (c) is defensible from a scientific and philosophical perspective; and (d) does not over-reach in ways that impose excessive administrative and regulatory burdens. The definition is meant to provide guidance for design teams seeking to pursue responsible and ethically aligned AI innovation. (shrink)

As we build increasingly intelligent machines, we confront difficult questions about how to specify their objectives. One approach, which we call human-centered, tasks the machine with the objective of learning and satisfying human objectives by observing our behavior. This paper considers how human-centered AI should conceive the humans it is trying to help. We argue that an Aristotelian model of human agency has certain advantages over the currently dominant theory drawn from economics.

This paper reframes the issue of appropriation, extraction, and dispossession through AI—an assemblage of machine learning models trained on big data—in terms of enclosure and foreclosure. While enclosures are the product of a well-studied set of operations pertaining to both the constitution of the sovereign State and the primitive accumulation of capital, here, I want to recover an older form of the enclosure operation to then contrast it with foreclosure to better understand the effects of current algorithmic rationality. I argue (...) that the act of enclosing is to be understood as a set of fundamental operations that consist in producing structural distinctions between inside and outside, inclusion and exclusion—whether by drawing lines on a map, constructing border walls, or by algorithmically categorizing and (mis)recognizing people and things. Tracking the transformation of an enclosure-logic into one of foreclosure, I show how current AI perpetuates and at the same time expends forms of extraction, exclusion, and dispossession toward a totalizing horizon. For, while the outside is essential and constitutive to the logic of enclosure, foreclosure, by contrast, is characterized by the “totalizing desire” to not leave anything out of it. The totalizing desire to move beyond the logic of the enclosure forecloses that the enclosure has just gotten bigger and that the operations of exclusion have been masked and displaced, making them harder to contest. (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)

The article “Philosophy is crucial in the age of AI” by Anthony Grayling and Brian Ball explores the significant role philosophy has played in the development of Artificial Intelligence (AI) and its continuing relevance in guiding the future of AI technologies. The authors trace the historical contributions of philosophers and logicians, such as Gottlob Frege, Kurt Godel, and Alan Turing, in shaping the foundational principles of AI. They argue that philosophical inquiry remains essential, especially in addressing complex issues like consciousness, (...) creativity, and the alignment of AI with human values. The article emphasizes the interdisciplinary collaboration needed to navigate the ethical and societal challenges posed by advancing AI systems, suggesting that philosophy is crucial in ensuring these technologies develop responsibly and ethically. (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)

This paper reframes the issue of appropriation, extraction, and dispossession through AI—an assemblage of machine learning models trained on big data—in terms of enclosure and foreclosure. While enclosures are the product of a well-studied set of operations pertaining to both the constitution of the sovereign State and the primitive accumulation of capital, here, I want to recover an older form of the enclosure operation to then contrast it with foreclosure to better understand the effects of current algorithmic rationality. I argue (...) that the act of enclosing is to be understood as a set of fundamental operations that consist in producing structural distinctions between inside and outside, inclusion and exclusion—whether by drawing lines on a map, constructing border walls, or by algorithmically categorizing and (mis)recognizing people and things. Tracking the transformation of an enclosure-logic into one of foreclosure, I show how current AI perpetuates and at the same time expends forms of extraction, exclusion, and dispossession toward a totalizing horizon. For, while the outside is essential and constitutive to the logic of enclosure, foreclosure, by contrast, is characterized by the “totalizing desire” to not leave anything out of it. The totalizing desire to move beyond the logic of the enclosure forecloses that the enclosure has just gotten bigger and that the operations of exclusion have been masked and displaced, making them harder to contest. (shrink)

Most engineers Fwork within social structures governing and governed by a set of values that primarily emphasise economic concerns. The majority of innovations derive from these loci. Given the effects of these innovations on various communities, it is imperative that the values they embody are aligned with those societies. Like other transformative technologies, artificial intelligence systems can be designed by a single organisation but be diffused globally, demonstrating impacts over time. This paper argues that in order to design for this (...) broad stakeholder group, engineers must adopt a systems thinking approach that allows them to understand the sociotechnicity of artificial intelligence systems across sociocultural domains. It claims that value sensitive design, and envisioning cards in particular, provides a solid first step towards helping designers harmonise human values, understood across spatiotemporal boundaries, with economic values, rather than the former coming at the opportunity cost of the latter. (shrink)

This article analyzes the potential impacts of Xenoaccelerationism and Accelerationism on the development of artificial intelligence (AI) and machine learning (ML). It examines how these speculative philosophies, which advocate technological acceleration and integration of diverse knowledge, may shape priorities and approaches in AI research and development. The risks and benefits of aligning AI progress with accelerationist values are discussed.

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)

The pace of technological change continues to outstrip the evolution of democratic institutions, creating an urgent need for innovative approaches to democratic reform. However, the experimentation bottleneck - characterized by slow speed, high costs, limited scalability, and ethical risks - has long hindered progress in democracy research. This paper proposes a novel solution: employing generative artificial intelligence (GenAI) to create synthetic data through the simulation of digital homunculi, GenAI-powered entities designed to mimic human behavior in social contexts. By enabling rapid, (...) low-risk experimentation with alternative institutional designs, this approach could significantly accelerate democratic innovation. I examine the potential of GenAI-assisted research to mitigate current limitations in democratic experimentation, including the ability to simulate large-scale societal interactions and test complex institutional mechanisms. While acknowledging potential risks such as algorithmic bias, reproducibility challenges, and AI alignment issues, I argue that the benefits of synthetic data are likely to outweigh their drawbacks if implemented with proper caution. To address existing challenges, I propose a range of technical, methodological, and institutional adaptations. The paper concludes with a call for interdisciplinary collaboration in the development and implementation of GenAI-assisted methods in democracy research, highlighting their potential to bridge the gap between democratic theory and practice in an era of rapid technological change. (shrink)

Discussions about the possible consequences of creating superintelligence have included the possibility of existential risk, often understood mainly as the risk of human extinction. We argue that suffering risks (s-risks) , where an adverse outcome would bring about severe suffering on an astronomical scale, are risks of a comparable severity and probability as risks of extinction. Preventing them is the common interest of many different value systems. Furthermore, we argue that in the same way as superintelligent AI both contributes to (...) existential risk but can also help prevent it, superintelligent AI can both be a suffering risk or help avoid it. Some types of work aimed at making superintelligent AI safe will also help prevent suffering risks, and there may also be a class of safeguards for AI that helps specifically against s-risks. (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)

Advanced AI systems are rapidly making their way into medical research and practice, and, arguably, it is only a matter of time before they will surpass human practitioners in terms of accuracy, reliability, and knowledge. If this is true, practitioners will have a prima facie epistemic and professional obligation to align their medical verdicts with those of advanced AI systems. However, in light of their complexity, these AI systems will often function as black boxes: the details of their contents, calculations, (...) and procedures cannot be meaningfully understood by human practitioners. When AI systems reach this level of complexity, we can also speak of black-box medicine. In this paper, we want to argue that black-box medicine conflicts with core ideals of patient-centered medicine. In particular, we claim, black-box medicine is not conducive for supporting informed decision-making based on shared information, shared deliberation, and shared mind between practitioner and patient. (shrink)

Recent advances in natural language processing have given rise to a new kind of AI architecture: the language agent. By repeatedly calling an LLM to perform a variety of cognitive tasks, language agents are able to function autonomously to pursue goals specified in natural language and stored in a human-readable format. Because of their architecture, language agents exhibit behavior that is predictable according to the laws of folk psychology: they function as though they have desires and beliefs, and then make (...) and update plans to pursue their desires given their beliefs. We argue that the rise of language agents significantly reduces the probability of an existential catastrophe due to loss of control over an AGI. This is because the probability of such an existential catastrophe is proportional to the difficulty of aligning AGI systems, and language agents significantly reduce that difficulty. In particular, language agents help to resolve three important issues related to aligning AIs: reward misspecification, goal misgeneralization, and uninterpretability. (shrink)

The era of AI-based decision-making fast approaches, and anxiety is mounting about when, and why, we should keep “humans in the loop” (“HITL”). Thus far, commentary has focused primarily on two questions: whether, and when, keeping humans involved will improve the results of decision-making (making them safer or more accurate), and whether, and when, non-accuracy-related values—legitimacy, dignity, and so forth—are vindicated by the inclusion of humans in decision-making. Here, we take up a related but distinct question, which has eluded the (...) scholarship thus far: does it matter if humans appear to be in the loop of decision-making, independent from whether they actually are? In other words, what is stake in the disjunction between whether humans in fact have ultimate authority over decision-making versus whether humans merely seem, from the outside, to have such authority? Our argument proceeds in four parts. First, we build our formal model, enriching the HITL question to include not only whether humans are actually in the loop of decision-making, but also whether they appear to be so. Second, we describe situations in which the actuality and appearance of HITL align: those that seem to involve human judgment and actually do, and those that seem automated and actually are. Third, we explore instances of misalignment: situations in which systems that seem to involve human judgment actually do not, and situations in which systems that hold themselves out as automated actually rely on humans operating “behind the curtain.” Fourth, we examine the normative issues that result from HITL misalignment, arguing that it challenges individual decision-making about automated systems and complicates collective governance of automation. (shrink)

Alan Turing, one of the fathers of computing, warned that Artificial Intelligence (AI) could one day pose an existential risk to humanity. Today, recent advancements in the field AI have been accompanied by a renewed set of existential warnings. But what exactly constitutes an existential risk? And how exactly does AI pose such a threat? In this chapter we aim to answer these questions. In particular, we will critically explore three commonly cited reasons for thinking that AI poses an existential (...) threat to humanity: the control problem, the possibility of global disruption from an AI race dynamic, and the weaponization of AI. (shrink)

Artificial intelligence (AI) profoundly influences a number of societal structures today, including religious dynamics. Using Bernard Lonergan’s critical realism as a lens, this article investigates the intersections of AI and religious traditions in their shared pursuit of the common good. Beginning with Lonergan’s principle that humans construct their understanding through cognitive processes, we examine how AI-mediated realities align with or challenge traditional religious tenets. By delving into specific cases, we spotlight AI’s role in reshaping religious symbols, rituals, and even creating (...) novel spiritual meanings. Using Lonergan’s insights on the balance between subjectivity and objectivity, I analyze AI’s potential to both create new sacred spaces and challenge religious orthodoxy. The crux of the discussion centers on the negotiation between religious values and technological innovation, assessing how AI can bolster religious life while maintaining its core essence. Ultimately, this article underscores the importance of the common good in the age of AI-driven religious evolution. (shrink)

Whether it would take one decade or several centuries, many agree that it is possible to create a *superintelligence*---an artificial intelligence with a godlike ability to achieve its goals. And many who have reflected carefully on this fact agree that our best hope for a "friendly" superintelligence is to design it to *learn* values like ours, since our values are too complex to program or hardwire explicitly. But the value learning approach to AI safety faces three particularly philosophical puzzles: first, (...) it is unclear how any intelligent system could learn its final values, since to judge one supposedly "final" value against another seems to require a further background standard for judging. Second, it is unclear how to determine the content of a system's values based on its physical or computational structure. Finally, there is the distinctly ethical question of which values we should best aim for the system to learn. I outline a potential answer to these interrelated puzzles, centering on a "miktotelic" proposal for blending a complex, learnable final value out of many simpler ones. (shrink)

The AI ethics of statistical fairness is an error, the approach should be abandoned, and the accumulated academic work deleted. The argument proceeds by identifying four recurring mistakes within statistical fairness. One conflates fairness with equality, which confines thinking to similars being treated similarly. The second and third errors derive from a perspectival ethical view which functions by negating others and their viewpoints. The final mistake constrains fairness to work within predefined social groups instead of allowing unconstrained fairness to subsequently (...) define group composition. From the nature of these misconceptions, the larger argument follows. Because the errors are integral to how statistical fairness works, attempting to resolve the difficulties only deepens them. Consequently, the errors cannot be corrected without undermining the larger project, and statistical fairness collapses from within. While the collapse ends a failure in ethics, it also provokes distinct possibilities for fairness, data, and algorithms. Quickly indicating some of these directions is a secondary aim of the paper, and one that aligns with what fairness has consistently meant and done since Aristotle. (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)

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)