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)

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

Solutions to word problems are moderated by the semantic alignment of real-world relations with mathematical operations. Categorical relations between entities are aligned with addition, whereas certain functional relations between entities are aligned with division. Similarly, discreteness vs. continuity of quantities is aligned with different formats for rational numbers. These alignments have been found both in textbooks and in the performance of college students in the USA and in South Korea. The current study examined evidence for alignments in Russia. Textbook (...) analyses revealed semantic alignments for arithmetic word problems, but not for rational numbers. Nonetheless, Russian college students showed semantic alignments both for arithmetic operations and for rational numbers. Since Russian students exhibit semantic alignments for rational numbers in the absence of exposure to examples in school, such alignments likely reflect intuitive understanding of mathematical representations of real-world situations. (shrink)

In this paper I explore a “variation” on the “theme” of intuition in the evolution of modern metaphysics. My aim is not to criticize A. W. Moore’s account of intuition as one of two ways by which Bergson makes sense of things (the other way is analysis). Instead I will suggest the significance in extending Bergson’s metaphysics to mystical life as “the ‘very life of things’ into which intuition installs itself.” When the metaphysical drama, in The Evolution of Modern Metaphysics, (...) reaches chapter 16, “Bergson: Metaphysics as Pure Creativity,” Moore expresses astonishment that Bergson could have thought philosophers have ever agreed on aligning “analysis” in science with the impossibility of non-perspectival sense-making and “intuition” in metaphysics with the possibility of absolute (non-perspectival) knowledge. Using a method of intuition, not of analysis, as non-perspectival sense-making is the opposite of what Moore himself finds in other philosophical contributions to modern metaphysics as “a most general attempt to make sense of things.” He takes an influential example: Bernard Williams associates analysis, not intuition, with the possibility of non-perspectival sense-making and absolute knowledge. My response defends Bergsonian intuition in giving it a positive—and, why not, non-perspectival?—role in metaphysics as mystical; that is, as unique and inexpressible life. Moore describes intuition in Bergson as both the faculty and the method for the evolution of new concepts and new ways of making sense of things. I will stress that Bergsonian intuition is “an effort to place oneself into a movement, such as that of philosophy itself,” expressing “what is ‘living in philosophers’ rather than what is ‘fixed and dead in theses.’ ” This mystical life pushes out the limits set up by Kant for metaphysics (and science) by allowing intuition (with analysis) to reach for absolute, non-perspectival knowledge. (shrink)

This paper explores the relationship between intuition and flow from a neurodynamics perspective. Flow and intuition represent two cognitive phenomena rooted in nonconscious information processing; however, there are clear differences in both their phenomenal characteristics and, more broadly, their contribution to action and cognition. We propose, extrapolating from dual processing theory, that intuition serves as a rapid, nonconscious decision-making process, while flow facilitates this process in action, achieving optimal cognitive control and performance without [conscious] deliberation. By exploring these points of (...) convergence between flow and intuition, we also attempt to reconcile the apparent paradox of the presence of enhanced intuition in flow, which is also a state of heightened cognitive control. To do so, we utilize a revised dual-processing framework, which allows us to productively align and differentiate flow and intuition (including intuition in flow). Furthermore, we draw on recent work examining flow from an active inference perspective. Our account not only heightens understanding of human cognition and consciousness, but also raises new questions for future research, aiming to deepen our comprehension of how flow and intuition can be harnessed to elevate human performance and wellbeing. (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)

New technologies not only contribute greatly to society and the economy; they also involve fundamental societal shifts, challenging our values and ideas about ourselves and the world. With a view to aligning technological change and innovation with ethical values, the concept of responsible innovation advocates the inclusion of a variety of stakeholders, in particular from society. In shifting moral responsibility towards the producers of innovations, responsible innovation rejects the standard normative economic view that the ethical evaluation of innovations is a (...) matter of individual consumers’ market-based choices. However, in this article we argue that responsible innovation should not abandon all normative consideration of the individual outright, to which end we present an alternative normative economic approach based on preference learning. We show how this approach can provide an enhanced understanding of responsible innovation by clarifying the redistribution of moral responsibility and casting individuals in the normative role of co-innovators, rather than mere consumers. We argue that responsible innovation should enable individuals to form preferences and evaluate innovations, so as to align innovation with ethical demands. Finally, we show how our proposed approach can be put into practice in so-called laboratories in real-world contexts, using methods from the field of design. In short, drawing on normative economics, this article aims to establish a new understanding of responsible innovation that is conceptually sound and can form the basis for novel innovation practices. (shrink)

Moral and political philosophers commonly appeal to moral “intuitions” at crucial points in their reasoning. This chapter considers recent challenges to this practice—here referred to as “the Method”—based in empirical studies of moral intuitions. It contends that such studies do not justify radical or revisionary conclusions about the Method. A method is aimed at achieving certain goals. The key issue is the nature of the goals in relation to which the Method is to be evaluated. This chapter argues (...) that the relevant goal is not the “realist goal” of discovering the truth about moral and political matters. The central point is that, the chapter argues, the systematic philosophical study of moral and political questions would be worthwhile even if it turned out that moral realism cannot be vindicated or that the Method cannot be vindicated in relation to the realist goal. If this is correct, then the goal relative to which it is crucial to vindicate the Method is not the realist goal. A Rawlsian view is more plausible, according to which the relevant goal is to “characterize our moral sensibility” as it would be in “reflective equilibrium.” It turns out, however, that this Rawlsian view has some, perhaps unwelcome, deflationary implications. (shrink)

This paper criticizes Analytic philosophy with its reliance on intuitions in pursuit of conceptual analysis. Rejecting naturalism as an alternative philosophical method, I offer in its place a pragmatic and revisionary conception of philosophical method. I explain the method of Analytic philosophy and show why reliance on intuitions is essential to that method, which is unable to provide substantive answers to philosophical problems. I further show that reflective equilibrium or wide analysis requires some criterion of intuition choice and (...) that this criterion can be applied directly to definitions themselves. (shrink)

Network analysis is a promising step forward in efforts to align psychological assessment with explanatory theory in psychological science. The implications of Cramer et al.'s analysis are quite general. Networks analysis may illuminate functional relations not only among observable behaviors that comprise psychological disorders, but among cognitive and affective processes that causally contribute to everyday experience and action.

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)

Pamela Sue Anderson urges feminist philosophers to embrace Michèle Le Doeuff’s revaluation of women in philosophy through according “fair value” to intuition as an intellectual faculty, a view of intuition articulated by Henri Bergson. She asks whether women who follow Bergson could be given fair value along with intuition. She turns from Le Doeuff’s writings on intuition to writings by Bergson and by Beauvoir, but periodically returns to Le Doeuff herself. In the end, a picture of freedom, friendship and feminism (...) emerges from readings of all three. This is a portrait of confident and capable interactions in creativity and dynamic projects, which transform our becoming within life, on the assumption that the love of friendship is between like-minded, embodied and interrelated selves. She explores whether we transform our lives in freedom and in love between friends. Although attracted to the human – and humane – solidarity in freedom of “great souls,” as in Beauvoir’s women of action, she instead aligns herself with Le Doeuff’s critical caution against naturalizing a timelessly abstract female soul for contemporary feminist philosophers. She concludes her proposed orientation with a Le Doeuffian feminist image of living life freely for and with friends. (shrink)

Gerald Harrison has argued that the readiness with which we have and agree to moral intuitions about the value of disembodied persons shows that persons are essentially non-material, for if we were essentially material we would not so easily be able to ascribe moral value to an impossible non-material person. To support this point, he advances a somewhat novel metaphor of intuitions as a "call" to a help desk which can answer our queries about counter-factual scenarios. I first (...) point out that the help desk metaphor is not only compatible with, but actually suggestive of, the possibility of systematic error on the part of our intuitions. But more crucially, rapid acquisition of and widespread agreement on even plausible intuitions about counter-factual scenarios does nothing to show that the counter-factual scenarios are possible, let alone true, giving several other counter-examples to this idea. I conclude with the suggestion that imagining such counter-factual scenarios should not be seen as a mode of accessing a fixed source of truths in a "help desk" manual, but as a constructive way of understanding the relationship between concepts, and hence ultimately as a mode of writing small parts of this heretofore unwritten text. (shrink)

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

This article responds to recent empirical studies by De Brigard and Weijers on intuitions about Nozick's experience machine thought experiment. It argues that, contra De Brigard and Weijers, our intuitions about the experience machine do undermine hedonism about well-being and what's good for us. It furthers this argument by conducting new empirical studies into our intuitions about the experience machine.

Putting forward a new case for ethical intuitionism, Trevor Curnow finds its roots in the wisdom traditions of antiquity, while also drawing on Eastern philosophy and modern psychology.

The chapter begins by exploring a philosophical case study of the use of intuitions — viz., the debate regarding the problem of radical scepticism, paying particular attention to key figures within this debate such as Barry Stroud, John Austin, and Ludwig Wittgenstein. It contends that this debate demonstrates something interesting about the nature of intuitions and the role that they can play in philosophical inquiry. In particular, the chapter argues that we need to think of the philosophical use (...) of intuitions as at least sometimes involving a significant level of expertise. The chapter closes by considering the relevance of this point about philosophical intuitions to the negative programme in experimental philosophy. (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)

Experimental restrictionists have challenged philosophers’ reliance on intuitions about thought experiment cases based on experimental findings. According to the expertise defense, only the intuitions of philosophical experts count—yet the bulk of experimental philosophy consists in studies with lay people. In this paper, we argue that direct strategies for assessing the expertise defense are preferable to indirect strategies. A direct argument in support of the expertise defense would have to show: first, that there is a significant difference between expert (...) and lay intuitions; second, that expert intuitions are superior to lay intuitions; and third, that expert intuitions accord with the relevant philosophical consensus. At present, there is only little experimental evidence that bears on these issues. To advance the debate, we conducted two new experiments on intuitions about knowledge with experts and lay people. Our results suggest that the intuitions of epistemological experts are superior in some respects, but they also pose an unexpected challenge to the expertise defense. Most strikingly, we found that even epistemological experts tend to ascribe knowledge in fake-barn-style cases. This suggests that philosophy, as a discipline, might fail to adequately map the intuitions of its expert practitioners onto a disciplinary consensus. (shrink)

Speakers often overspecify by encoding more information than is necessary when referring to an object (e.g., “the blue mug” for the only mug in a group of objects). We investigated the role of a partner's linguistic behavior (whether or not they overspecify) on a speaker's own tendency to overspecify. We used a director–matcher task in which speakers interacted with a partner who either consistently overspecified or minimally specified in the color/size dimension (Experiments 1, 2, and 3), as well as with (...) a partner who switched behaviors midway through interaction (Experiments 4 and 5). We found that speakers aligned with their partner's linguistic behavior to produce overspecific or minimally specific descriptions, and we saw little evidence that the alignment was enhanced by lexical or semantic repetition across prime and target trials. Time‐course analyses showed that alignment increased over the course of the interaction, and speakers appeared to track a change in the partner's linguistic behavior, altering their reference strategy to continue matching that of their partner's. These results demonstrate the persistent influence of a partner's behavior on speakers across the duration of an interaction. (shrink)

In recent years a growing number of philosophers writing about the methodology of philosophy have defended the surprising claim that philosophers do not use intuitions as evidence. In this paper I defend the contrary view that philosophers do use intuitions as evidence. I argue that this thesis is the best explanation of several salient facts about philosophical practice. First, philosophers tend to believe propositions which they find intuitive. Second, philosophers offer error theories for intuitions that conflict with (...) their theories. Finally, philosophers are more confident in rejecting theories to the extent that they have several counter examples involving diverse cases. I argue that these facts are better explained by philosophers' using intuitions as evidence than by any plausible contrary explanations. I further argue that aspects of philosophical practice that my thesis may initially seem ill-suited to explain are in fact unsurprising whether or not my thesis is true. (shrink)

Volume 25, Issue 3, March 2025, Page 35-37.

According to the prevailing paradigm in social-cognitive neuroscience, the mental states of individuals become shared when they adapt to each other in the pursuit of a shared goal. We challenge this view by proposing an alternative approach to the cognitive foundations of social interactions. The central claim of this paper is that social cognition concerns the graded and dynamic process of alignment of individual minds, even in the absence of a shared goal. When individuals reciprocally exchange information about each (...) other's minds processes of alignment unfold over time and across space, creating a social interaction. Not all cases of joint action involve such reciprocal exchange of information. To understand the nature of social interactions, then, we propose that attention should be focused on the manner in which people align words and thoughts, bodily postures and movements, in order to take one another into account and to make full use of socially relevant information. (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)

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)

Confronts conflicting intuitions about the character of probabilistic causality. These intuitions were exposed with the publication of the preceding essay, and the critics’ responses to it. Using several important additional examples, this essay addresses the responses of I.J. Good to the criticisms raised in the preceding chapter. It exhibits complexities that arise when we try to accommodate sophisticated intuitions about probabilistic causality in an explicitly articulated theory.

The “received wisdom” in contemporary analytic philosophy is that intuition talk is a fairly recent phenomenon, dating back to the 1960s. In this paper, we set out to test two interpretations of this “received wisdom.” The first is that intuition talk is just talk, without any methodological significance. The second is that intuition talk is methodologically significant; it shows that analytic philosophers appeal to intuition. We present empirical and contextual evidence, systematically mined from the JSTOR corpus and HathiTrust’s Digital Library, (...) which provide some empirical support for the second rather than the first hypothesis. Our data also suggest that appealing to intuition is a much older philosophical methodology than the “received wisdom” alleges. We then discuss the implications of our findings for the contemporary debate over philosophical methodology. (shrink)

This book is an intellectual history of intuition.

This paper considers challenges resulting from the use of advanced artificial judicial intelligence (AAJI). We argue that these challenges should be considered through the lens of value alignment. Instead of discussing why specific goals and values, such as fairness and nondiscrimination, ought to be implemented, we consider the question of how AAJI can be aligned with goals and values more generally, in order to be reliably integrated into legal and judicial systems. This value alignment framing draws on AI (...) safety and alignment literature to introduce two otherwise neglected considerations for AAJI safety: specification and assurance. We outline diverse research directions and suggest the adoption of assurance and specification mechanisms as the use of AI in the judiciary progresses. While we focus on specification and assurance to illustrate the value of the AI safety and alignment literature, we encourage researchers in law and philosophy to consider what other lessons may be drawn. (shrink)

In epistemology, fake-barn thought experiments are often taken to be intuitively clear cases in which a justified true belief does not qualify as knowledge. We report a study designed to determine whether non-philosophers share this intuition. The data suggest that while participants are less inclined to attribute knowledge in fake-barn cases than in unproblematic cases of knowledge, they nonetheless do attribute knowledge to protagonists in fake-barn cases. Moreover, the intuition that fake-barn cases do count as knowledge is negatively correlated with (...) age; older participants are less likely than younger participants to attribute knowledge in fake-barn cases. We also found that increasing the number of defeaters (fakes) does not decrease the inclination to attribute knowledge. (shrink)

Kant denies that Reason is intuitive, but demands that we must - in some way - 'make' Reason intuitive, and follow its guidance, particularly in matters of morality. In this book, a group of scholars attempt to analyze and explore this central paradox within Kantian thought. Each essay explores the question from a different perspective - from political philosophy, ethics and religion to science and aesthetics. The essays thus also reformulate the core question in different forms, for example, how are (...) we to realize the moral good in personal character, political arrangements, or religious institutions? (shrink)

Some approaches to the assessment of moral intuitions are discussed. The controlled ethical trial isolates a moral issue from confounding factors and thereby clarifies what a person's intuition actually is. Casuistic reasoning from situations, where intuitions are clear, suggests or modifies principles, which can then help to make decisions in situations where intuitions are unclear. When intuitions are defended by a supporting principle, that principle can be tested by finding extreme cases, in which it is counterintuitive (...) to follow the principle. An approach to the resolution of conflict between valid moral principles, specifically the utilitarian and justice principles, is considered. It is argued that even those who justify intuitions by a priori principles are often obliged to modify or support their principles by resort to the consideration of consequences. (shrink)

Elijah Chudnoff elaborates and defends a view of intuition according to which intuition purports to, and reveals, how matters stand in abstract reality by making us aware of that reality through the intellect. He explores the experience of having an intuition; justification for beliefs that derives from intuition; and contact with abstract reality.

Human beings are internally inconsistent in various ways. One way to develop this thought involves using the language of value alignment: the values we hold are not always aligned with our behavior, and are not always aligned with each other. Because of this self-misalignment, there is room for potential projects of human enhancement that involve achieving a greater degree of value alignment than we presently have. Relatedly, discussions of AI ethics sometimes focus on what is known as the (...) value alignment problem, the challenge of how to build AI that acts in accordance with our human values. We argue that there is an especially close connection between solving the value alignment problem in AI ethics and using AI to pursue certain forms of human enhancement. But in addition, we also argue that there are important limits to what kinds of human enhancement can be pursued in this way, because some forms of human enhancement—namely moral revolutions—involve a kind of value misalignment rather than alignment. (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)

Linguists often advert to what are sometimes called linguistic intuitions. These intuitions and the uses to which they are put give rise to a variety of philosophically interesting questions: What are linguistic intuitions – for example, what kind of attitude or mental state is involved? Why do they have evidential force and how might this force be underwritten by their causal etiology? What light might their causal etiology shed on questions of cognitive architecture – for example, as (...) a case study of how consciously inaccessible subpersonal processes give rise to conscious states, or as a candidate example of cognitive penetrability? What methodological issues arise concerning how linguistic intuitions are gathered and interpreted – for example, might some subjects' intuitions be more reliable than others? And what bearing might all this have on philosophers' own appeals to intuitions? This paper surveys and critically discusses leading answers to these questions. In particular, we defend a ‘mentalist’ conception of linguistics and the role of linguistic intuitions therein. (shrink)

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

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)

In a series of pre-registered studies, we explored (a) the difference between people’s intuitions about indeterministic scenarios and their intuitions about deterministic scenarios, (b) the difference between people’s intuitions about indeterministic scenarios and their intuitions about neurodeterministic scenarios (that is, scenarios where the determinism is described at the neurological level), (c) the difference between people’s intuitions about neutral scenarios (e.g., walking a dog in the park) and their intuitions about negatively valenced scenarios (e.g., murdering (...) a stranger), and (d) the difference between people’s intuitions about free will and responsibility in response to first-person scenarios and third-person scenarios. We predicted that once we focused participants’ attention on the two different abilities to do otherwise available to agents in indeterministic and deterministic scenarios, their intuitions would support natural incompatibilism—the view that laypersons judge that free will and moral responsibility are incompatible with determinism. This prediction was borne out by our findings. (shrink)