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)

Was ist Intuition? Gibt es intuitive Erkenntnis? Intuition beschäftigt Philosophie, Psychologie und Alltagsdenken. Einschätzungen reichen dabei von "höchste Erkenntnisart" bis "höchst unzuverlässig." Cyrill Mamin zeichnet zentrale Bestimmungen der Intuition in Philosophie und Psychologie nach. Wesentliche Fragen sind dabei: Wie ist es, eine Intuition zu haben? Wie kommt eine Intuition zustande? Auf dieser Grundlage bestimmt Mamin Intuition als massgeblich nicht-propositionale Erkenntnisart, welche unsere intuitiven Überzeugungen rechtfertigen kann. Im Zentrum steht ein neuartiges Modell der intuitiven Rechtfertigung, das psychologische mit erkenntnistheoretischen Elementen verbindet. (...) Dadurch lässt sich Intuition im Verhältnis zu anderen mentalen Akten (u.a. Wahrnehmung, Imagination, Delusion) näher bestimmen sowie ein kritischer Blick auf die philosophische Intuitionsdebatte werfen. (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)

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)

The empirical turn has created an undercurrent of scrutiny regarding the relevance of disciplines such as philosophy and theology due to assumptions about the limitations of their epistemology. This article seeks to recognize that disciplines that are lauded as most relevant due to their reliance on empiricism as their main form of epistemology often rely upon intuition for making decisions in the research process. After delineating this process using Anthropological research as an example, I draw a parallel between descriptions of (...) how intuition can be understood and used as a means of knowing in the work of Kant and several theologians with descriptions of how intuition is relied upon and necessarily emerges as a critical epistemology in the more traditionally empirically grounded discipline Anthropology. This parallel is offered as the launching place for connections between these disciplines through further examination of the use of intuition as an epistemology and hopes to equate the epistemo- logical integrity of disciplines such as philosophy and theology that admit to the use of intuition with those that are considered empiri- cal which rely upon intuition yet may not admit to its use overtly. (shrink)

ABSTRACT Because he claims that intuition can give us insight into “life” apart from space, if not time, Bergson seems to transgress Kant's limits on possible knowledge. This article argues, however, that there is a “critical” way to read Bergson that allows him to evade accusations of epistemologically and politically problematic vitalism. When compared with the archaeological and genealogical treatment of “life” found in Michel Foucault's work, Bergson's effort to save humans from the destructive effects of intellect converges in interesting (...) ways with Foucault's displacement of life as a foundational philosophical or scientific term. (shrink)

Open peer commentary on the article “Subsystem Formation Driven by Double Contingency” by Bernd Porr & Paolo Di Prodi. Upshot: There is merit to the continuous-signal-space homeostatic viewpoint on subsystem formation presented by Bernd Porr and Paolo Di Prodi; many of their ideas also align well with a heterostatic constructivist perspective, and specifically developments in the field of reinforcement learning. This commentary therefore aims to identify and clarify some of the linkages made by the authors, and highlight ways in which (...) these interdisciplinary connections may be leveraged to enable future progress. (shrink)

This paper examines a well-known non-identity case of a mother who chooses to conceive a blind child instead of a sighted one. While some people accept the non-identity argument and claim that we should reject the intuition that the mother’s act is morally wrong, others hold onto that intuition and try to find a fault in the non-identity argument. This paper proposes a somewhat middle approach. It is argued that the conclusion of the non-identity argument is not necessarily in conflict (...) with our intuitive response to this case. (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)

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)

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

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.

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)

The aim of this article is to show that intuition plays no role in mathematics. That intuition plays a role in mathematics is mainly associated to the view that the method of mathematics is the axiomatic method. It is assumed that axioms are directly (Gödel) or indirectly (Hilbert) justified by intuition. This article argues that all attempts to justify axioms in terms of intuition fail. As an alternative, the article supports the view that the method of mathematics is the analytic (...) method, a method originally used by the mathematician Hippocrates of Chios and the physician Hippocrates of Cos, and first explicitly formulated by Plato. The article examines the main features of the analytic method, and argues that, while intuition plays an essential role in the axiomatic method, it plays no role in the analytic method, either in the discovery or in the justification of hypotheses. That the method of mathematics is the analytic method involves that mathematical knowledge is not absolutely certain but only plausible, but the article argues that this is the best we can achieve. (shrink)

We review the hypothesis that the brain uses a generative model to explain the causes of sensory inputs, using prediction schemes that operate based upon assimilation of time-series sensory data. We put this hypothesis in the context of psychopathology, in particular, schizophrenia's positive symptoms. Building upon work of Helmholtz and upon theories in computational cognitive processing, we hypothesize that delusions in schizophrenia can be explained in terms of false inference. An impairment in inferring appropriate information from the sensory input reflects (...) upon the ability to assess the environment and predict outcomes. Although the inference mechanism likely involves both conscious and unconscious processes, we hypothesize that the trigger of delusions may lie within the unconscious neural pathways. A collection of computational predictive codes have been proposed for modeling perception. We discuss two examples, which may be eligible as substrates for intuitive coding. We argue that failure of the psychotic patient to choose the correct computational scheme, or the optimal range of parameters, may readily lead to an altered reconstruction of the object and false inference, feeding into the delusion mechanism. We finally propose using these models in conjunction with cognitive and imaging data, in order to obtain more testable predictions. (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)

The need to align multiple experimental procedures and produce converging results so as to demonstrate that the phenomenon under investigation is real and not an artifact is a commonplace both in scientific practice and discussions of scientific methodology (Campbell and Stanley 1963; Wimsatt 1981). Although sometimes this is the purpose of aligning techniques, often there is a different purpose—multiple techniques are sought to supply different perspectives on the phenomena under investigation that need to be integrated to answer the questions scientists (...) are asking. After introducing this function, I will illustrate it by considering three of the major techniques in cognitive neuroscience for linking cognitive function with neural structure. (shrink)

In general, intuition and demonstration are explained in terms of the class of relations of ideas that remain the same as long as the ideas remain the same. The main negative point is that our concept of a deductively valid argument, even one with necessarily true premises, has little to do with Hume's conception of demonstration. Following Descartes and Locke, the emphasis is on content and certainty, not necessity and formal validity. Two ideas are intuitively related if the relation between (...) them is immediately conceived. Two ideas are demonstratively related if the relation between them is conceived, not immediately, but via other intermediate ideas. The link between each pair of adjacent ideas in the resulting chain must be intuitive. With this background, some of Hume's more infamous claims are explained: we know in advance that two ideas cannot be demonstratively related if we can conceive one without the other; the causal maxim is neither intuitively nor demonstratively known; the only relation capable of sustaining demonstrations is that of quantity and number. (shrink)

Note, by Sir D. Ross.--Reason and intuition.--The kinds of belief.--Religious belief.--Conflicts of belief.--The eclipse of cause.--Materialism in politics.--On the need for a social philosophy.--Can philosophy determine what is ethically and socially valuable?--The philosophy of democracy.--The principles and limitations of state action.--Leisure.--Locke's contribution to political theory.--Jeremy Bentham.--The empiricism of J. S. Mill.--Is a science of theology possible?--Will and action in ethics.

This paper is a response to Nenad Miščević’s “Reply to Michael Devitt”, the latest in an exchange on the source of linguistic intuitions. Miščević defends a modified version (“MoVoC”) of the received view that these intuitions are the product of a linguistic competence. I have earlier rejected all versions of the received view urging instead that intuitions are, like perceptual judgments, empirical theory-laden central-processor responses to phenomena. (1) I emphasize here, against Miščević, that this claim about a (...) speaker’s intuitions about strings is not to be conflated with a claim about her understanding of strings. (2) I develop my claim, addressed by Miščević, that MoVoC is implausible in three ways. But these are not the main problems for MoVoC. For further discussion of those, see Jutronić’s paper in this volume. (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)

Pickering & Garrod's (P&G's) mechanistic account of dialogue assumes that linguistic alignment between interlocutors takes place automatically, without using cognitive resources. However, even the most basic processes of speech perception depend on resource use. The lack of invariant mapping between input patterns and interpretations in dialogue, as in speech perception, may require controlled, rather than automatic, processing.

We describe an approach to textual inference that improves alignments at both the typed dependency level and at a deeper semantic level. We present a machine learning approach to alignment scoring, a stochastic search procedure, and a new tool that finds deeper semantic alignments, allowing rapid development of semantic features over the aligned graphs. Further, we describe a complementary semantic component based on natural logic, which shows an added gain of 3.13% accuracy on the RTE3 test set.

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)