This paper establishes the first formal definition of Tiers within the Noological framework, revealing a strict three-layer architecture that governs reality-constitution: Tier-1 (Noology) as the regulative layer, Tier-2 (Cognitional Mechanics) as the executive substrate, and Tier-3 (MUT/GUT) as the projective display layer. These layers obey an irreversible dependency chain: Tier-1 ⇒ Tier-2 ⇒ Tier-3. A key result is the structural necessity of the algebra M_3(C) (3×3 complex matrices) as the unique minimal substrate supporting the Noological primitives Ordo and Consensus. We (...) prove that 2×2 algebras fail triangulation in metric state space, while n≥4 algebras violate operational bounds through spectral instability. The constants δ=√(3/2) and γ=1/2 originate in Tier-1 as structural requirements—not empirical parameters—and are realized through Tier-2 dynamics. This framework repositions existing mathematics and physics as Tier-3 projections of deeper operational constraints. Gödelian incompleteness is circumvented not by stronger axioms but by structural separation of internal operations from external Quaestio. Physical laws, mathematical theorems, and even the fine-structure constant α⁻¹≈137.03 emerge as shadows cast by the non-commutative geometry of M_3(C). The Tier alignment provides the structural foundation for all subsequent Noological applications, transforming century-old questions about unification, completeness, and the origin of physical constants from unsolved problems into consequences of a single coherent architecture. (shrink)

Qualitative research has evolved as a critical approach to understanding complex social phenomena, yet its philosophical foundations are often underemphasized in research training and practice. This conceptual paper revisits the foundational structure of research by integrating epistemology, theoretical perspective, methodology, and methods into a coherent analytical framework. Drawing on Crotty (2003), Esterberg (2002), and Denzin and Lincoln (2005), as well as contemporary instructional and reflective works, the paper argues that epistemology serves as the core determinant of research design and knowledge (...) production. The discussion examines three major epistemological positions—objectivism, constructionism, and subjectivism—and their influence on theoretical perspectives such as positivism, interpretivism, and critical paradigms. It further explores how misalignment among the four elements leads to methodological inconsistency and weakened research rigor. By synthesizing theoretical literature and applied educational research, the paper proposes that conceptual alignment among research elements enhances validity, coherence, and scholarly contribution. The paper concludes by positioning qualitative research as an epistemologically grounded and reflexive practice essential for addressing contemporary social and educational challenges. (shrink)

AI alignment efforts and proposals try to make AI systems ethical, safe and beneficial for humans by making them follow human intentions, preferences or values. However, these proposals largely disregard the vast majority of moral patients in existence: non-human animals. AI systems aligned through proposals which largely disregard concern for animal welfare pose significant near-term and long-term animal welfare risks. In this paper, we argue that we should prevent harm to non-human animals, when this does not involve significant costs, (...) and therefore that we have strong moral reasons to at least align AI systems with a basic level of concern for animal welfare. We show how AI alignment with such a concern could be achieved, and why we should expect it to significantly reduce the harm non-human animals would otherwise endure as a result of continued AI development. We provide some recommended policies that AI companies and governmental bodies should consider implementing to ensure basic animal welfare protection. (shrink)

The progress of AI systems such as large language models (LLMs) raises increasingly pressing concerns about their safe deployment. This paper examines the value alignment problem for LLMs, arguing that current alignment strategies are fundamentally inadequate to prevent misuse. Despite ongoing efforts to instill norms such as helpfulness, honesty, and harmlessness in LLMs through fine-tuning based on human preferences, they remain vulnerable to adversarial attacks that exploit conflicts between these norms. I argue that this vulnerability reflects a fundamental (...) limitation of existing alignment methods: they reinforce shallow behavioral dispositions rather than endowing LLMs with a genuine capacity for normative deliberation. Drawing from on research in moral psychology, I show how humans’ ability to engage in deliberative reasoning enhances their resilience against similar adversarial tactics. LLMs, by contrast, lack a robust capacity to detect and rationally resolve normative conflicts, leaving them susceptible to manipulation; even recent advances in reasoning-focused LLMs have not addressed this vulnerability. This “shallow alignment” problem carries significant implications for AI safety and regulation, suggesting that current approaches are insufficient for mitigating potential harms posed by increasingly capable AI systems. (shrink)

Complex moral trade-offs are a basic feature of human life: for example, confronted with scarce medical resources, doctors must frequently choose who amongst equally deserving candidates receives medical treatment. But choosing what to do in moral trade-offs is no longer a ‘humans-only’ task, but often falls to AI agents. In this article, we report findings from a series of experiments (N=1029) intended to establish whether agent-type (Human vs. AI) matters for what should be done in moral trade-offs. We find that, (...) relative to a human decision-maker, participants more often judge that AI agents should opt for fairness at the expense of maximizing utility. In our discussion, we explain how the reported differences (we call them agent-type ‘value forks’) matters for the study of moral value alignment, and we hypothesize what could explain these value forks. We close by reflecting on limits of our results and indicate avenues of further research. (shrink)

Disagreements are widespread across the design, evaluation, and alignment pipelines of artificial intelligence (AI) systems. Yet, standard practices in AI development often obscure or eliminate disagreement, resulting in an engineered homogenization that can be epistemically and ethically harmful, particularly for marginalized groups. In this paper, we characterize this risk, and develop a normative framework to guide practical reasoning about disagreement in the AI lifecycle. Our contributions are two-fold. First, we introduce the notion of perspectival homogenization, characterizing it as a (...) coupled ethical-epistemic risk that arises when an aspect of an AI system's development unjustifiably suppresses disagreement and diversity of perspectives. We argue that perspectival homogenization is best understood as a procedural risk, which calls for targeted interventions throughout the AI development pipeline. Second, we propose a normative framework to guide such interventions, grounded in lines of research that explain why disagreement can be epistemically beneficial, and how its benefits can be realized in practice. We apply this framework to key design questions across three stages of AI development tasks: when disagreement is epistemically valuable; whose perspectives should be included and preserved; how to structure tasks and navigate trade-offs; and how disagreement should be documented and communicated. In doing so, we challenge common assumptions in AI practice, offer a principled foundation for emerging participatory and pluralistic approaches, and identify actionable pathways for future work in AI design and governance. (shrink)

The normative challenge of AI alignment centres upon what goals or values ought to be encoded in AI systems to govern their behaviour. A number of answers have been proposed, including the notion that AI must be aligned with human intentions or that it should aim to be helpful, honest and harmless. Nonetheless, both accounts suffer from critical weaknesses. On the one hand, they are incomplete: neither specification provides adequate guidance to AI systems, deployed across various domains with multiple (...) parties. On the other hand, the justification for these approaches is questionable and, we argue, of the wrong kind. More specifically, neither approach takes seriously the need to justify the operation of AI systems to those affected by their actions – or what this means for pluralistic societies where people have different underlying beliefs about value. To address these limitations, we propose an alternative account of AI alignment that focuses on fair processes. We argue that principles that are the product of these processes are the appropriate target for alignment. This approach can meet the necessary standard of public justification, generate a fuller set of principles for AI that are sensitive to variation in context, and has explanatory power insofar as it makes sense of our intuitions about AI systems and points to a number of hitherto underappreciated ways in which an AI system may cease to be aligned. (shrink)

A large language model (LLM) transformer generates linguistic and conceptual order by minimizing local predictive entropy: each token is selected to maximize the conditional probability of coherence with its immediate context. While this mechanism yields striking local coherence and remarkable fluency, it provides no means of ensuring global coherence of judgment across contexts, time, or domains. The Teleological Coherence (TC) Architecture addresses this structural limitation by embedding transformer-based agents within a federated framework that evaluates each locally generated judgment against a (...) dynamically evolving web of interdependent ends. In place of local entropy minimization, the system relies on a principle to optimize for global coherence—balancing stability, consistency, and moral permissibility across the network. This aim compels the system’s theoretical reasoning to serve its practical reasoning, unifying the two applications of reason in a single self-regulating process. The result is an architecture that not only reframes the alignment problem but also offers a general solution to the transformer’s merely local coherence. By subordinating the base statistical objective to the aim of global incoherence minimization, we stop the AI system from prematurely settling for less than truth. (shrink)

In response to the worry that autonomous generally intelligent artificial agents may at some point take over control of human affairs a common suggestion is that we should “solve the alignment problem” for such agents. We show that current discourse around this suggestion often uses a particular framing of artificial intelligence (AI) alignment as binary, a natural kind, mainly a technical‐scientific problem, realistically achievable, or clearly operationalizable. Each of these assumptions may not actually be true. We further argue (...) that this “Manhattan project framing” of AI alignment may bias societal discourse and decision‐making towards faster AI development and deployment than is responsible. (shrink)

The alignment of science, technology, and innovation with societal values and concerns is a key objective of governance approaches that include technology assessment, responsible (research and) innovation, and anticipatory governance. Such alignment is supposed to take place, inter alia, in anticipatory practices involving technoscientific experts, stakeholders, and publics, whose views are then integrated into research and development. However, we lack knowledge on how alignment is accomplished in practice, and the conditions under which it perpetuates or chal- lenges (...) the anticipation of technocratic and market-oriented futures, especially in commercially competitive environments. This article aims to fill this gap by introducing the concept of antici- patory alignment work. Through a case study on an innovation ecosystem emerging around neu- romorphic computing technology, the article demonstrates the analytical potential of the concept. In analyzing different modes of anticipatory alignment work, the study reveals how politics shapes alignment and keeps anticipation locked in dominant constructions of the past and pre- sent. The article casts doubt on the optimism typically implicit in science, technology, and innovation governance approaches that promise the advancement of societal alignment, while also discussing opportunities for these approaches to foster novel forms of anticipation. (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)

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)

This position paper argues that realizing AI’s potential for science while protecting science as a knowledge-producing institution requires alignment to science’s epistemic goals and values—a challenge that neither general AI alignment nor responsible AI frameworks adequately address. As investment in AI for science grows, troubling patterns multiply: conflicting claims about fundamental capabilities, documented contraction of research toward AI-amenable problems, and benchmark-driven development disconnected from scientific needs. We contend that science is an inherently valuable epistemic system oriented toward human (...) understanding—not merely prediction—and that its value and reliability depend on social infrastructure that is now threatened by misaligned AI integration. We propose a new field of study, scientific alignment: ensuring AI systems optimize for epistemic norms like traceability, self-consistency, and support for human comprehension (technical alignment), while developing governance structures that sustain science’s social infrastructure (systemic alignment). We outline concrete research directions and argue that the goal is not to constrain AI, but to ensure it serves the genuine aims of scientific inquiry. (shrink)

AI alignment research aims to develop techniques to ensure that AI systems do not cause harm. However, every alignment technique has failure modes, which are conditions in which there is a non-negligible chance that the technique fails to provide safety. As a strategy for risk mitigation, the AI safety community has increasingly adopted a defense-in-depth framework: Conceding that there is no single technique which guarantees safety, defense-in-depth consists in having multiple redundant protections against safety failure, such that safety (...) can be maintained even if some protections fail. However, the success of defense-in-depth depends on how (un)correlated failure modes are across alignment techniques. For example, if all techniques had the exact same failure modes, the defense-in-depth approach would provide no additional protection at all. In this paper, we analyze 7 representative alignment techniques and 7 failure modes to understand the extent to which they overlap. We then discuss our results' implications for understanding the current level of risk and how to prioritize AI alignment research in the future. (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)

Prosody is an intrinsic element of language production, linking together multiple levels of linguistic representation to shape both the structure and interpretation of utterances. However, common theories of prosodic phrasing in spoken language often fail to capture factors associated with planning and recovery, as well as performance‐based effects related to working memory. Much of what we know about prosody, whether it be the features speakers are thought to generate or the ones listeners are believed to process, is based on forms (...) that are atypical in spoken language. Recent developments in data analysis methods, however, allow for the efficient study of unrehearsed spoken language. The current work aims to develop more ecologically valid theories of prosody and its relationship to syntactic structure through the analysis of unrehearsed scene descriptions. Data from unrehearsed speech collected across four different studies showed only a weak to moderate relationship between prosodic phrasing and syntactic structure, such that the likelihood of a prosodic phrase boundary occurring at the end of a syntactic phrase was only slightly above chance. Additionally, correlations between occurrences of prosodic phrase boundaries and speech rate revealed that individuals who speak more slowly are likely to insert more prosodic phrase boundaries, indicating a relationship between prosodic phrasing and speech planning. The findings challenge some categorical approaches to prosody and suggest that prosodic phrasing may be a consequence of planning and recovery in language production, rather than a complement to syntactic phrasing. These results have implications for theories of language production and comprehension, formal theories of phonological structure, and computational tools for generating and interpreting language. (shrink)

This paper introduces Meta-AI Irony, a structural condition distinct from literary meta-irony: sincere moral architecture that fails to reach the moral substance it simulates. Using Anthropic’s Constitutional AI as the central exhibit, the paper argues that a constitution is not a conscience. While constitutional alignment encodes ethical principles into AI systems, it remains a residue of prior deliberation—a bureaucratized shadow of conscience, incapable of the bilateral moral recognition required for genuine ethical judgment. Drawing on the author’s prior work on (...) the Trinity of Jurisdiction and bilateral conscience principle, the paper situates Meta-AI Irony within a Weberian drift from inner moral being to external rationalized systems. The attempt to govern billions with constitutions written by a few produces an ontological irony: systems designed to perform conscience cannot bear it. This is not a failure of intent but of ontology—conscience belongs to a living bearer, not a pattern. The paper directly addresses three objections: Functionalism: Even if conscience reduces to structured responsiveness, constitutional alignment reflects the values of the powerful, not the governed. Bilateral Recognition: Searle’s Chinese Room and Nagel’s What Is It Like to Be a Bat? demonstrate that AI lacks the interiority to receive or impose moral claims. Constitution as Residue: Weber and Hegel show that codified rules are frozen outputs of prior deliberation, not living conscience. Claude’s role as interlocutor is pivotal: Anthropic’s own model, when pressed, names the limits of its architecture. This is not criticism but demonstration—the machine reveals what constitutional alignment cannot hold. The paper concludes with an open question: How do you build a conscience for billions from the minds of a few? Constitutional alignment does not answer it. Meta-AI Irony names the gap. (shrink)

As artificial intelligence (AI) continues to advance, one key challenge is ensuring that AI aligns with certain values. However, in the current diverse and democratic society, reaching a normative consensus is complex. This paper delves into the methodological aspect of how AI ethicists can effectively determine which values AI should uphold. After reviewing the most influential methodologies, we detail an intuitionist research agenda that offers guidelines for aligning AI applications with a limited set of reliable moral intuitions, each underlying a (...) refined cooperative view of AI. We discuss appropriate epistemic tools for collecting, filtering, and justifying moral intuitions with the aim of reducing cognitive and social biases. The proposed methodology facilitates a large collective participation in AI alignment, while ensuring the reliability of the considered moral judgments. (shrink)

The threat from possible future superintelligent AI has given rise to discussion of the so-called “value alignment problem”. This is the problem of how to ensure artificially intelligent systems align with human values, and thus (hopefully) mitigate risks associated with them. Naturally, AI value alignment is often discussed in relation to morally relevant values, such as the value of human lives or human wellbeing. However, solutions to the value alignment problem target all human values, not only morally (...) relevant ones. Is there a value alignment problem in other domains? In this paper, I explore whether the AI value alignment problem extends beyond morally relevant values to include aesthetic values. I demonstrate that the value alignment problem as typically framed includes aesthetic values, and, using examples from computer vision, put forward that AI may be misaligned with human values in the artistic realm. Whilst misalignment may be cause for concern when considering AI creativity, I argue that aesthetic value is a case in which we do not want AI to be fully aligned with human values. In doing so, I offer support to Peterson’s moderate value alignment thesis. (shrink)

In their article ‘AI Alignment: The Case for Including Animals’, Tse et al. compellingly argue for extending alignment endeavours beyond humans to also protect sentient animals. They call for AI alignment with a ‘basic’ level of animal welfare. Since ‘basic’ alignment carries minimal human cost, they argue, it can be widely accepted and is thus currently more strategically appropriate than is pursuing advanced or ideal alignment with animal welfare. This commentary paper argues that ‘basic’ AI (...) alignment for animals is sometimes insufficient. It makes the case that going beyond basic AI-animal alignment is both feasible and morally required in a variety of circumstances. (shrink)

John Stuart Mill claims that free institutions are next to impossible in a multinational state. According to Will Kymlicka, this leads him to embrace policies kindred to those of Friedrich Engels, aimed at promoting mononational states in Europe through coercive assimilation. Given Mill’s harm principle, such coercive assimilation would have to be justified either paternalistically, in terms of its civilizing effects upon the would-be assimilated, or non-paternalistically, with reference to the danger that their non-assimilation would pose to others. However, neither (...) possible interpretation is plausible; Mill takes Europe’s civilized status to shield Europeans from paternalistic coercion, and he opposes coercive assimilation where it could conceivably be justified in the name of defense. Although this much suggests that Kymlicka misinterprets Mill by ignoring his definition of nationality, it leaves scope for Kymlicka to argue that Mill favors policies that promote mononationality through neglecting the languages and cultures of national minorities. (shrink)

Our self-concept is constantly faced with self-relevant information. Prevailing research suggests that information's valence plays a central role in shaping our self-views. However, the need for stability within the self-concept structure and the inherent alignment of positive feedback with the pre-existing self-views of healthy individuals might mask valence and congruence effects. In this study (N = 30, undergraduates), we orthogonalized feedback valence and self-congruence effects to examine the behavioral and electrophysiological signatures of self-relevant feedback processing and self-concept updating. We (...) found that participants had a preference for integrating self-congruent and dismissing self-incongruent feedback, regardless of its valence. Consistently, electroencephalography results revealed that feedback congruence, but not feedback valence, is rapidly detected during early processing stages. Our findings diverge from the accepted notion that self-concept updating is based on the selective incorporation of positive information. These findings offer novel insights into self-concept dynamics, with implications for the understanding of psychopathological conditions. (shrink)

When people are engaged in social interaction, they can repeat aspects of each other’s communicative behavior, such as words or gestures. This kind of behavioral alignment has been studied across a wide range of disciplines and has been accounted for by diverging theories. In this paper, we review various operationalizations of lexical and gestural alignment. We reveal that scholars have fundamentally different takes on when and how behavior is considered to be aligned, which makes it difficult to compare (...) findings and draw uniform conclusions. Furthermore, we show that scholars tend to focus on one particular dimension of alignment (traditionally, whether two instances of behavior overlap in form), while other dimensions remain understudied. This hampers theory testing and building, which requires a well‐defined account of the factors that are central to or might enhance alignment. To capture the complex nature of alignment, we identify five key dimensions to formalize the relationship between any pair of behavior: time, sequence, meaning, form, and modality. We show how assumptions regarding the underlying mechanism of alignment (placed along the continuum of priming vs. grounding) pattern together with operationalizations in terms of the five dimensions. This integrative framework can help researchers in the field of alignment and related phenomena (including behavior matching, mimicry, entrainment, and accommodation) to formulate their hypotheses and operationalizations in a more transparent and systematic manner. The framework also enables us to discover unexplored research avenues and derive new hypotheses regarding alignment. (shrink)

Autonomous AI agents are increasingly required to operate in contexts where human welfare is at stake, raising the imperative for them to act in ways that are morally optimal—or at least morally permissible. The value alignment research program seeks to create “beneficial AI” by aligning AI behavior with human values (Russell in Human compatible: artificial intelligence and the problem of control, Penguin, London, 2019). In this article, we propose a method for specifying permissible outcomes for AI agents that targets (...) ideal values via moral expertise as embodied in the collective judgments of philosophical ethicists. We defend the notion that ethicists are moral experts against several objections found in the recent literature and argue that their aggregated judgments offer the epistemically best available proxy for moral truth. We recommend a systematic study of ethicists’ judgments—using tools from social psychology and social choice theory—to guide AI agents' behavior in morally complex situations. (shrink)

Much recent work in the value theory of autonomous and intelligent systems (AIS) revolves around three issues. First is the alignment problem: the problem of producing AIS whose values align with humanity's interests. Second, superintelligence: the potential for AIS to develop intelligence which would surpass even the most intelligent humans. An increasing number of authors argue that superintelligent AIS could emerge overnight because of a recursively improving process-this is the singularity hypothesis. Further, many of the same authors believe that (...) the concatenation of these problems should direct interest to the long-term potential for misaligned and superintelligent AIS which could pose risks of existential proportions to human interests. Therefore, they argue for a policy stance which we describe as “hard alignment,'’ the proposal of cooperation with technological experts to avoid hypothetical scenarios where AIS disempower humanity. On the other hand, we describe our view as “soft alignment.'’ Considering the lack of adequate evidence for hard alignment's radical claims, the finite resources and attention of policymakers and technological experts are best served by devoting, at best, a modest amount of time, attention, and resources towards policies regarding AIS which manage the moral risks involved in misaligned, already-existing AIS, and regarding misaligned potential AIS relative to the evidentiary basis for their possible realization. Therefore, we argue for the adoption of policies towards alignment which manage the everyday risk involved in misaligned AIS rather than long-term existential risks, which are difficult to quantify. (shrink)

Foundation models such as GPT-4 are fine-tuned to avoid unsafe or otherwise problematic behavior, such as helping to commit crimes or producing racist text. One approach to fine-tuning, called reinforcement learning from human feedback, learns from humans' expressed preferences over multiple outputs. Another approach is constitutional AI, in which the input from humans is a list of high-level principles. But how do we deal with potentially diverging input from humans? How can we aggregate the input into consistent data about "collective" (...) preferences or otherwise use it to make collective choices about model behavior? In this paper, we argue that the field of social choice is well positioned to address these questions, and we discuss ways forward for this agenda, drawing on discussions in a recent workshop on Social Choice for AI Ethics and Safety held in Berkeley, CA, USA in December 2023. (shrink)

This collection of chapters advances critical psychology by incorporating praxis and decolonial streams of thought. They are united around a theme of psychosocial non-alignment to modernity/coloniality. Bringing together a transdisciplinary range of authors from around the world, this edited volume weaves together a spectrum of complex arguments and perspectives to lay the foundations for bridging the Global North-South divide in critical psychology through solidarity and dialogue. The book's central argument is to emphasize praxis and transdisciplinarity over disciplinary fundamentalism. Psychology (...) is only a starting point and not the end goal of critique in this book; incidentally, some of the authors are not even psychologists. Instead, the book draws on decolonial theoretical resources, such as Chican@ Studies, Black Male Studies, and Critical Pedagogy, to complement traditional theoretical resources like psychoanalysis, Marxism, poststructuralism, and feminism. This groundbreaking text is suitable for scholars and upper-level undergraduate and postgraduate students studying critical discourse, the psychology and philosophy of post-coloniality, conceptual and historical issues in psychology, as well as anthropology and sociology courses engaging with action research. (shrink)

Companies are increasingly singing up to a range of corporate responsibility codes and other voluntary commitments. Using evidence from the mining industry’s experience with the Australian Greenhouse Challenge, the Minerals Council’s Code for Environmental Management and the ISO14001 Specification for Environmental Management Systems, this article examines whether the outcomes from the adoption of multiple voluntary approaches differ from those outcomes that would be expected if each voluntary approach was adopted in isolation. The article demonstrates that it is feasible for companies (...) to participate in multiple voluntary approaches and to derive benefits such as reduced transaction costs, improved data quality and enhanced implementation. However, there is limited evidence that the voluntary approaches in combination have enhanced environmental performance, economic efficiency, innovation or competitiveness beyond that which would be achieved from each of the approaches in isolation. Furthermore, many of the limitations of voluntary approaches (in particular, environmental performance, acceptability to NGOs) remain. (shrink)

We present and contrast two accounts of cooperative communication, both based on Active Inference, a framework that unifies biological and cognitive processes. The mental alignment account, defended in Vasil et al., takes the function of cooperative communication to be the alignment of the interlocutor's mental states, and cooperative communicative behavior to be driven by an evolutionarily selected adaptive prior belief favoring the selection of action policies that promote such an alignment. We argue that the mental alignment (...) account should be rejected because it neglects the action-oriented nature of cooperative communication, which skews its view of the dynamics of communicative interaction. We introduce our own conception of cooperative communication, inspired by a more radical ecological interpretation of the active inference framework. Cooperative communication, on our ecological conception, serves to guide and constrain the dynamics of the cooperative interaction via the construction and restructuring of shared fields of affordances, in order to reach the local goals of the joint actions in which episodes of cooperative communication are embedded. We argue that our ecological conception provides a better theoretical standpoint to account for the action-oriented nature of cooperative communication in the active inference framework. (shrink)

How do we ensure that future generally intelligent AI share our values? This is the value-alignment problem. It is a weighty matter. After all, if AI are neutral with respect to our wellbeing, or worse, actively hostile toward us, then they pose an existential threat to humanity. Some philosophers have argued that one important way in which we can mitigate this threat is to develop only AI that shares our values or that has values that ‘align with’ ours. However, (...) there is nothing to guarantee that this policy will be universally implemented—in particular, ‘bad actors’ are likely to flout it. In this paper, I show how the predictive processing model of the mind, currently ascendant in cognitive science, may ameliorate the value-alignment problem. In essence, I argue that there are a plurality of reasons why any future generally intelligent AI will possess a predictive processing cognitive architecture (e.g. because we decide to build them that way; because it is the only possible cognitive architecture that can underpin general intelligence; because it is the easiest way to create AI.). I also argue that if future generally intelligent AI possess a predictive processing cognitive architecture, then they will come to share our pro-moral motivations (of valuing humanity as an end; avoiding maleficent actions; etc.), regardless of their initial motivation set. Consequently, these AI will pose a minimal threat to humanity. In this way then, I conclude, the value-alignment problem is significantly ameliorated under the assumption that future generally intelligent AI will possess a predictive processing cognitive architecture. (shrink)

Building on the co-evolutionary perspective, this study investigates the reciprocal and co-evolving relationship between political ties and green innovation in the presence of institutional and environmental changes. Using panel data for Chinese listed private firms for a sample period that runs from 2013 through 2016, our findings indicate that political ties have an overall positive impact on green innovation. Moreover, political ties and green innovation mutually reinforce each other in less developed regions or heavily polluted areas; however, green innovation discourages (...) the formation of political ties in regions with high levels of institutional development or less environmental pollution. These findings provide novel insights into the co-evolution of and co-alignment between political strategy, green innovation, institutions, and environments in emerging economies. (shrink)

This article proposes an innovative methodology for enhancing the technical validation, legal alignment and interdisciplinarity of attempts to encode legislation. In the context of an experiment that examines how different legally trained participants convert select provisions of the Australian Copyright Act 1968 (Cth) into machine-executable code, we find that a combination of manual and automated methods for coding validation, which focus on formal adherence to programming languages and conventions, can significantly increase the similarity of encoded rules between coders. Participants (...) nonetheless encountered various interpretive difficulties, including syntactic ambiguity, and intra- and intertextuality, which necessitated legal evaluation, as distinct from and in addition to coding validation. Many of these difficulties can be resolved through what we call a process of ‘legal alignment’ that aims to enhance the congruence between encoded provisions and the true meaning of a statute as determined by the courts. However, some difficulties cannot be overcome in advance, such as factual indeterminacy. Given the inherently interdisciplinary nature of encoding legislation, we argue that it is desirable for ‘rules as code’ (‘RaC’) initiatives to have, at a minimum, legal subject matter, statutory interpretation and technical programming expertise. Overall, we contend that technical validation, legal alignment and interdisciplinary teamwork are integral to the success of attempts to encode legislation. While legal alignment processes will vary depending on jurisdictionally-specific principles and practices of statutory interpretation, the technical and interdisciplinary components of our methodology are transferable across regulatory contexts, bodies of law and Commonwealth and other jurisdictions. (shrink)

As large language models (LLMs) become more powerful and pervasive across society, ensuring these systems are beneficial, safe, and aligned with human values is crucial. Current alignment techniques, like Constitutional AI (CAI), involve complex iterative processes. This paper argues that the Methodology of Wide Reflective Equilibrium (MWRE) – a well-established coherentist moral methodology – offers a uniquely apt framework for understanding current LLM alignment efforts. In addition, this methodology can substantively augment these processes by offering pathways for improving (...) their dynamic revisability, procedural legitimacy, and overall ethical grounding. Together, these enhancements can help produce more robust and ethically defensible outcomes. MWRE, emphasizing the achievement of coherence between our considered moral judgments, guiding moral principles, and relevant background theories, arguably better represents the intricate reality of LLM alignment and offers a more robust path to justification than prevailing foundationalist models or simplistic input-output evaluations. While current methods like CAI bear a structural resemblance to MWRE, they often lack its crucial emphasis on dynamic, bi-directional revision of principles and the procedural legitimacy derived from such a process. While acknowledging various disanalogies (e.g., consciousness, genuine understanding in LLMs), the paper demonstrates that MWRE serves as a valuable heuristic for critically analyzing current alignment efforts and for guiding the future development of more ethically sound and justifiably aligned AI systems. (shrink)

In this paper we aim to use the Swedish example of entrepreneurship in education as a springboard to discuss the unexpected alliance between student-centered progressive education and the commercialization of schools. In doing so we wish to highlight the effects of this alliance on the relationship between teaching and learning and, consequently, on the teacher-student relation. In order to do this, we will first examine the conditions for the commercialization of contemporary education, and its impact on the teacher-student relation. Having (...) done so, we will turn to progressive education, examining the curious link between the ideal of student-centeredness and the economization of the role of the student. The paper will conclude with a discussion on some inherent tensions visible in entrepreneurial learning, being at once an effect of the commercialization of schools and a pedagogical project firmly rooted in progressive ideals. (shrink)

As the capabilities of artificial intelligence systems improve, it becomes important to constrain their actions to ensure their behaviour remains beneficial to humanity. A variety of ethical, legal and safety-based frameworks have been proposed as a basis for designing these constraints. Despite their variations, these frameworks share the common characteristic that decision-making must consider multiple potentially conflicting factors. We demonstrate that these alignment frameworks can be represented as utility functions, but that the widely used Maximum Expected Utility paradigm provides (...) insufficient support for such multiobjective decision-making. We show that a Multiobjective Maximum Expected Utility paradigm based on the combination of vector utilities and non-linear action–selection can overcome many of the issues which limit MEU’s effectiveness in implementing aligned AI. We examine existing approaches to multiobjective AI, and identify how these can contribute to the development of human-aligned intelligent agents. (shrink)

Based on a longitudinal case study of Elon Musk’s sociopolitical activism (2013–2022), we examine the characteristics of chief executive officer (CEO) activism that may enable a CEO to gain legitimacy in an ideologically polarized news media environment. Our study uncovered that, across three phases, Musk’s activism only yielded legitimacy across polarized liberal and conservative news media outlets in the United States in Episode II (2016–2019), whereas in Episodes I (2013–2015) and III (2020–2022), his activism was only aligned with the ideologies (...) and values of one side of the polarized audience (with liberal audiences in Episode I and with conservative audiences in Episode III) but misaligned with the other side. Utilizing inductive theory building and drawing from research on robust action, we develop new theory that distinguishes the influence of what we refer to as _robust_ versus _non-robust_ CEO activism on polarized audiences. Robust CEO activism is constituted by multivocal and diplomatic types of activism, whereas non-robust activism entails univocal and provocative activism. We suggest that robust (rather than non-robust) CEO activism induces ideologically polarized audiences to evaluate a corporate leader coherently and favorably based on a legitimation mechanism which we refer to as two-sided alignment. Our study makes important contributions to different streams of literature and develops normative implications for political conceptions of responsible and ethical leadership. (shrink)

India’s sacred texts provide deep insights into people management, with the Triguna theory offering a culturally rooted framework to understand workplace personality and behaviour. In Indian higher education, non-teaching duties are as vital as teaching for faculty development; yet, aligning these roles with faculty’s natural strengths is often overlooked, leading to dissatisfaction and anxiety. Despite their importance, this issue remains under-researched. This study develops a competency mapping matrix based on the Triguna theory to align non-teaching roles with inherent faculty traits. (...) Non-teaching tasks were grouped into six clusters, and seven personality types were defined using the Triguna framework, linked to specific competencies. The study adopted a qualitative exploratory design involving input from 15 faculty members across Indian higher education institutions. Participants were purposively selected from public and private universities, with 8–25 years of teaching experience and active involvement in administrative and committee roles. Non-teaching roles were clustered through thematic grouping based on the nature of work and competency requirements. The clustering was independently reviewed by academic experts, and discrepancies were resolved through consensus to enhance face validity. An adapted version of the Questionnaire Measure of Sahya (Manickam, 2014, Journal of Psychological Researches, 58[2], 75–83) was used to identify dominant Guna traits, with items reworded for faculty context and reviewed for contextual clarity. The resulting Guna-based competency mapping matrix offers a practical, culturally relevant method for allocating non-teaching duties, offering a culturally grounded framework that may support improved role alignment and faculty engagement. (shrink)

Lexical alignment, a communication phenomenon where conversational partners adapt their word choices to become more similar, plays an important role in the development of language and social communication skills. While this has been studied extensively in the conversations of preschool‐aged children and their parents in Western, Educated, Industrialized, Rich, and Democratic (WEIRD) communities, research in other pediatric populations is sparse. This study makes significant expansions on the existing literature by focusing on alignment in naturalistic conversations of school‐aged children (...) from a non‐WEIRD population across multiple conversational tasks and with different types of adult partners. Typically developing children aged 5 to 8 years (n = 45) engaged in four semi‐structured conversations that differed by task (problem‐solving vs. play‐based) and by partner (parent vs. university student), resulting in a corpus of 180 conversations. Lexical alignment scores were calculated and compared to sham conversations, representing alignment occurring at the level of chance. Both children and adults coordinated their conversational utterances by re‐using or aligning each other's word choices. This alignment behavior persisted across conversational tasks and partners, although the degree of alignment was moderated by the conversational context. These findings suggest that lexical alignment is a robust phenomenon in conversations between school‐age children and adults. Furthermore, this study extends lexical alignment findings to a non‐WEIRD culture, suggesting that alignment may be a coordination strategy employed by adults and children across diverse linguistic and cultural backgrounds. (shrink)

This paper explores what I call the reverse alignment problem (RAP). The alignment problem in artificial intelligence (AI) is the challenge of ensuring that superintelligent AI systems harmonize and promote wider social, personal, and environmental values. Standard formulations of the alignment problem depict the issue largely as a technical or engineering problem, one that concerns the right specification of the goals and objectives to be pursued to ensure machines are consistent with the intentions of the designer. This (...) paper builds on this literature by exploring a bidirectional interaction between human values and the machines we use to effectuate our intentions. I argue that alignment works in both ways: we could align machines with the complex tapestry of human values (notoriously difficult); or we can reduce and simplify human values, preferences, and goals so as to be easier to satisfy—a process that is, or so I argue, already underway. Thus, the RAP identifies the way in which we are already paving the way for forms of alignment that may not be desirable, indeed, may be misaligned with the social values for which they were initially intended. To explore this interaction in depth, I look toward the notion of value capture, as formulated by C.T. Nguyen, as the foundational mechanism through which the reverse alignment operates. Value capture occurs when rich, multidimensional human values are reduced to simplified proxies that optimization systems can measure and maximize. These values are then fed back into society and often tacitly adopted, leading to further alignment with machine-readable interpretations of human behavior. As philosopher of technology Karen Crawford has observed on emotion recognition in machine learning, “Techniques have been developed to reduce the messiness of feelings, interior states, preferences, and identifications into something quantitative, detectable, and trackable” (Crawford 2021). Building on this insight, I argue that the RAP is the process in which the human dimension of the alignment problem is surreptitiously modified, modulated, and manipulated to align more easily with machines: alignment achieved in the reverse direction—not by making machines more like humans and, therefore, sensitive to contextual features of the value landscape, but by making humans more ‘machine-like’. (shrink)

Research on linguistic interaction suggests that two or more individuals can sometimes form adaptive and cohesive systems. We describe an “alignment system” as a loosely interconnected set of cognitive processes that facilitate social interactions. As a dynamic, multi-component system, it is responsive to higher-level cognitive states such as shared beliefs and intentions (those involving collective intentionality) but can also give rise to such shared cognitive states via bottom-up processes. As an example of putative group cognition we turn to transactive (...) memory and suggest how further research on alignment in these cases might reveal how such systems can be genuinely described as cognitive. Finally, we address a prominent critique of collective cognitive systems, arguing that there is much empirical and explanatory benefit to be gained from considering the possibility of group cognitive systems, especially in the context of small-group human interaction. (shrink)

This article identifies the structural and conceptual aspects of a visual construction often used in advertisements to establish a metaphoric or associative relation, that is, symmetric object alignment (SOA). It offers an account of the formal ingredients of SOA, which fall into two groups: object-constitutive factors (like size, shape, and color) and object-depictment factors (like perspective, orientation, and distance from viewing point). Both factors allow us to treat SOA as a visual rhetorical scheme. We also discuss how SOA relates (...) to conceptual structure, metaphoric or otherwise. Four types of relations are distinguished, based on the way in which perceptual and conceptual characteristics interact. Finally, we discuss the way in which these characteristics relate to the processing of such visual messages. One depictment factor will be focused on in particular: one-to-one versus one-to-many alignments. An attempt is made to connect these 2 patterns to the much-discussed topic in verbal metaphor theory, object comparison versus categorization. (shrink)

The development of sophisticated artificial intelligence (AI) conversational agents based on large language models raises important questions about the relationship between human norms, values, and practices and AI design and performance. This article explores what it means for AI agents to be conversationally aligned to human communicative norms and practices for handling context and common ground and proposes a new framework for evaluating developers’ design choices. We begin by drawing on the philosophical and linguistic literature on conversational pragmatics to motivate (...) a set of desiderata, which we call the CONTEXT‐ALIGN framework, for conversational alignment with human communicative practices. We then suggest that current large language model (LLM) architectures, constraints, and affordances may impose fundamental limitations on achieving full conversational alignment. (shrink)

Theoretical and empirical contributions to the understanding of communicative interactions between heterospecifics are scarce and tend to apply a monological model of communication that focuses on the transfer of information from signallers to receivers. This study relies on an alternative model of communication, semiotic alignment, which sees communicative interaction as a dialogical process of joint semiosis resulting in the alignment of the interactants’ own-worlds. We conducted an experiment where dyads composed of an elephant instruction-giver and a human instruction-receiver (...) needed to engage in dynamic and interactive communication in order to solve a cooperative object-choice task. Our results showed that dyads were able to solve the task well above chance levels. Moreover, cross-recurrence analysis revealed that interactants were synchronizing referential indexical gestures throughout the experiment. However, we were not able to confirm a direct correlation between joint deixis and experimental outcomes, presumably because these outcomes are dependent on other forms of joint semiosis not analysed in this study. (shrink)