In this paper I discuss a recent theory on functions called Organizational Account. This theory seeks to provide a new definition of function that overcomes the distinction between etiological and dispositional accounts and that could be used in biology as well as in technology. I present a definition of function that I think captures the intuitions of Organizational Accounts and consider several objections.

This paper sets out a view about the explanatory role of representational content and advocates one approach to naturalising content – to giving a naturalistic account of what makes an entity a representation and in virtue of what it has the content it does. It argues for pluralism about the metaphysics of content and suggests that a good strategy is to ask the content question with respect to a variety of predictively successful information processing models in experimental psychology and cognitive (...) neuroscience; and hence that data from psychology and cognitive neuroscience should play a greater role in theorising about the nature of content. Finally, the contours of the view are illustrated by drawing out and defending a surprising consequence: that individuation of vehicles of content is partly externalist. (shrink)

A common misunderstanding of the selected effects theory of function is that natural selection operating over an evolutionary time scale is the only functionbestowing process in the natural world. This construal of the selected effects theory conflicts with the existence and ubiquity of neurobiological functions that are evolutionary novel, such as structures underlying reading ability. This conflict has suggested to some that, while the selected effects theory may be relevant to some areas of evolutionary biology, its relevance to neuroscience is (...) marginal. This line of reasoning, however, neglects the fact that synapses, entire neurons, and potentially groups of neurons can undergo a type of selection analogous to natural selection operating over an evolutionary time scale. In the following, I argue that neural selection should be construed, by the selected effect theorist, as a distinct type of function-bestowing process in addition to natural selection. After explicating a generalized selected effects theory of function and distinguishing it from similar attempts to extend the selected effects theory, I do four things. First, I show how it allows one to identify neural selection as a distinct function-bestowing process, in contrast to other forms of neural structure formation such as neural construction. Second, I defend the view from one major criticism, and in so doing I clarify the content of the view. Third, I examine drug addiction to show the potential relevance of neural selection to neuroscientific and psychological research. Finally, I endorse a modest pluralism of function concepts within biology. (shrink)

According to David Chalmers, the hard problem of consciousness consists of explaining how and why qualitative experience arises from physical states. Moreover, Chalmers argues that materialist and reductive explanations of mentality are incapable of addressing the hard problem. In this chapter, I suggest that Chalmers’ hard problem can be usefully distinguished into a ‘how question’ and ‘why question,’ and I argue that evolutionary biology has the resources to address the question of why qualitative experience arises from brain states. From this (...) perspective, I discuss the different kinds of evolutionary explanations (e.g., adaptationist, exaptationist, spandrel) that can explain the origins of the qualitative aspects of various conscious states. This argument is intended to clarify which parts of Chalmers’ hard problem are amenable to scientific analysis. (shrink)

This paper applies the theory of teleosemantics to the issue of moral content. Two versions of teleosemantics are distinguished: input-based and output-based. It is argued that applying either to the case of moral judgements generates the conclusion that such judgements have both descriptive (belief-like) and directive (desire-like) content, intimately entwined. This conclusion directly validates neither descriptivism nor expressivism, but the application of teleosemantics to moral content does leave the descriptivist with explanatory challenges which the expressivist does not face. Since teleosemantics (...) ties content to function, the paper also offers an account of the evolutionary function of moral judgements. (shrink)

John is currently thinking that the sun is bright. Consider his occurrent belief or judgement that the sun is bright. Its content is that the sun is bright. This is a truth- evaluable content (which shall be our main concern) because it is capable of being true or false. In virtue of what natural, scientifically accessible facts does John’s judgement have this content? To give the correct answer to that question, and to explain why John’s judgement and other contentful mental (...) states have the contents they do in virtue of such facts, would be to naturalize mental content. (shrink)

Despite the voluminous literature on biological functions produced over the last 40 years, few philosophers have studied the concept of function as it is used in neuroscience. Recently, Craver (forthcoming; also see Craver 2001) defended the causal role theory against the selected effects theory as the most appropriate theory of function for neuroscience. The following argues that though neuroscientists do study causal role functions, the scope of that theory is not as universal as claimed. Despite the strong prima facie superiority (...) of the causal role theory, the selected effects theory (when properly developed) can handle many cases from neuroscience with equal facility. It argues this by presenting a new theory of function that generalizes the notion of a ‘selection process’ to include processes such as neural selection, antibody selection, and some forms of learning—that is, to include structures that have been differentially retained as well as those that have been differentially reproduced. This view, called the generalized selected effects theory of function, will be defended from criticism and distinguished from similar views in the literature. (shrink)

Does connectionism spell doom for folk psychology? I examine the proposal that cognitive representational states such as beliefs can play no role if connectionist models - - interpreted as radical new cognitive theories -- take hold and replace other cognitive theories. Though I accept that connectionist theories are radical theories that shed light on cognition, I reject the conclusion that neural networks do not represent. Indeed, I argue that neural networks may actually give us a better working notion of cognitive (...) representational states such as beliefs, and in so doing give us a better understanding of how these states might be instantiated in neural wetware. (shrink)

Descartes developed an elaborate theory of animal physiology that he used to explain functionally organized, situationally adapted behavior in both human and nonhuman animals. Although he restricted true mentality to the human soul, I argue that he developed a purely mechanistic (or material) ‘psychology’ of sensory, motor, and low-level cognitive functions. In effect, he sought to mechanize the offices of the Aristotelian sensitive soul. He described the basic mechanisms in the Treatise on man, which he summarized in the Discourse. However, (...) the Passions of the soul contains his most ambitious claims for purely material brain processes. These claims arise in abstract discussions of the functions of the passions and in illustrations of those functions. Accordingly, after providing an intellectual context for Descartes’s theory of the passions, especially by comparison with that of Tho- mas Aquinas, I examine its ‘machine psychology’, including the role of habituation and association. I contend that Descartes put forth what may reasonably be called a ‘psychology’ of the unensouled animal body and, correspondingly, of the human body when the soul does not intervene. He thus conceptually distinguished a mechanistically explicable sensory and motor psychology, common to nonhuman and human animals, from true mentality involving higher cognition and volition and requiring (in his view) an immaterial mind. (shrink)

Philosophers have often argued that ascriptions of content are appropriate only to the personal level states of folk psychology. Against this, this paper defends the view that the familiar propositional attitudes and states defined over them are part of a larger set of cognitive proceses that do not make constitutive reference to concept possession. It does this by showing that states with nonconceptual content exist both in perceptual experience and in subpersonal information-processing systems. What makes these states content-involving is their (...) satisfaction of certain basic conditions deriving from a general account of representation-driven behaviour that is neutral on the question of concept possession. It is also argued that creatures can be in states with nonconceptual content even though they possess no conceptual abilities at all. (shrink)

The No-Miracles Argument (NMA) is often used to support scientific realism. We can formulate this argument as an inference to the best explanation this accusation of circularity by appealing to reliabilism, an externalist epistemology. In this paper I argue that this retreat fails. Reliabilism suffers from a potentially devastating difficulty known as the Generality Problem and attempts to solve this problem require adopting both epistemic and metaphysical assumptions regarding local scientific theories. Although the externalist can happily adopt the former, if (...) he adopts the latter then the Generality Problem arises again, but now at the level of scientific methodology. Answering this new version of the Generality Problem is impossible for the scientific realist without making the important further assumption that there exists the possibility of a unique rule of Doing this however would make the NMA viciously premise circular. (shrink)

Arguably no concept is more fundamental to science than that of causality, for investigations into cases of existence, persistence, and change in the natural world are largely investigations into the causes of these phenomena. Yet the metaphysics and epistemology of causality remain unclear. For example, the ontological categories of the causal relata have been taken to be objects (Hume 1739), events (Davidson 1967), properties (Armstrong 1978), processes (Salmon 1984), variables (Hitchcock 1993), and facts (Mellor 1995). (For convenience, causes and effects (...) will usually be understood as events in what follows.) Complicating matters, causal relations may be singular (Socrates’s drinking hemlock caused Socrates’s death) or general (Drinking hemlock causes death); hence the relata might be tokens (e.g., instances of properties) or types (e.g., types of events) of the category in question. Other questions up for grabs are: Are singular causes metaphysically and/or epistemologically prior to general causes or vice versa (or neither)? What grounds the intuitive asymmetry of the causal relation? Are macro-causal relations reducible to micro-causal relations? And perhaps most importantly: Are causal facts (e.g., the holding of causal relations) reducible to non-causal facts (e.g., the holding of certain spatiotemporal relations)? (shrink)

Colors are of philosophical interest for two kinds of reason. One is that colors comprise such a large and important portion of our social, personal and epistemological lives and so a philosophical account of our concepts of color is highly desirable. The second reason is that trying to fit colors into accounts of metaphysics, epistemology and science leads to philosophical problems that are intriguing and hard to resolve. Not surprisingly, these two kinds of reasons are related. The fact that colors (...) are so significant in their own right, makes more pressing the philosophical problems of fitting them into more general metaphysical and epistemological frameworks. (shrink)

Several philosophers have argued that natural selection will favor reliable belief formation; others have been more skeptical. These traditional approaches to the evolution of rationality have been either too sketchy or else have assumed that phenotypic plasticity can be equated with having a mind. Here I develop a new model to explore the functional utility of belief and desire formation mechanisms, and defend the claim that natural selection favors reliable inference methods in a broad, but not universal, range of circumstances.

John Maynard Smith has defended against philosophical criticism the view that developmental biology is the study of the expression of information encoded in the genes by natural selection. However, like other naturalistic concepts of information, this ‘teleosemantic’ information applies to many non-genetic factors in development. Maynard Smith also fails to show that developmental biology is concerned with teleosemantic information. Some other ways to support Maynard Smith’s conclusion are considered. It is argued that on any definition of information the view that (...) development is the expression of genetic information is misleading. Some reasons for the popularity of that view are suggested. (shrink)

Ruth Millikan’s teleological theory of mental content is complex and often misunderstood. This paper motivates and clarifies some of the complexities of the theory, and shows that paying careful attention to its details yields answers to a number of common objections to teleological theories, in particular, the problem of novel mental states, the problem of functionally false beliefs, and problems about indeterminacy or multiplicity of function.

This paper argues that it is possible for suffering to occur in the absence of phenomenal consciousness – in the absence of a certain sort of experiential subjectivity, that is. (Phenomenal consciousness is the property that some mental states possess, when it is like something to undergo them, or when they have subjective feels, or possess qualia.) So even if theories of phenomenal consciousness that would withhold such consciousness from most species of non-human animal are correct, this neednt mean that (...) those animals dont suffer, and arent appropriate objects of sympathy and concern. (shrink)

According to higher-order thought accounts of phenomenal consciousness it is unlikely that many non-human animals undergo phenomenally conscious experiences. Many people believe that this result would have deep and far-reaching consequences. More specifically, they believe that the absence of phenomenal consciousness from the rest of the animal kingdom must mark a radical and theoretically significant divide between ourselves and other animals, with important implications for comparative psychology. I shall argue that this belief is mistaken. Since phenomenal consciousness might be almost (...) epiphenomenal in its functioning within human cognition, its absence in animals may signify only relatively trivial differences in cognitive architecture. Our temptation to think otherwise arises partly as a side-effect of imaginative identification with animal experiences, and partly from mistaken beliefs concerning the aspects of common-sense psychology that carry the main explanatory burden, whether applied to humans or to non-human animals. (shrink)

The present paper discusses Kitcher’s framework for studying conceptual change and progress. Kitcher’s core notion of reference potential is hard to apply to concrete cases. In addition, an account of conceptual change as change in reference potential misses some important aspects of conceptual change and conceptual progress. I propose an alternative framework that focuses on the inferences and explanations supported by scientific concepts. The application of my approach to the history of the gene concept offers a better account of the (...) conceptual progress that occurred in the transition from the Mendelian to the molecular gene than Kitcher’s theory. (shrink)

An argument is offered against three naturalistic theories of intentional content: causal-covariation theories, teleological theories, and certain versions of conceptual role semantics. The strategy involves focusing on a normative problem regarding the practice of associating content expressions (e.g., that-clauses) with internal entities (states, symbol structures, etc.). The problem can be expressed thus: Which content expressions are the right ones to associate with internal entities? I argue, first, that an empirical solution to this problem—what I call the Normative Problem—will follow naturally (...) from a descriptive-explanatory account of the practice of associating content expressions with internal entities; and second, that the empirical solution will be accepted and adopted within cognitive science. Naturalistic theories of content also entail solutions to the Normative Problem, and such theories are shown to be false by showing that their solutions to the Normative Problem are inconsistent with the empirical solution coming out of cognitive science. (shrink)

Reductive, naturalistic psychosemantic theories do not have a good track record when it comes to accommodating the representation of kinds. In this paper, I will suggest a particular teleosemantic strategy to solve this problem, grounded in the neurocomputational details of the cerebral cortex. It is a strategy with some parallels to one that Ruth Millikan has suggested, but to which insufficient attention has been paid. This lack of attention is perhaps due to a lack of appreciation for the severity of (...) the problem, so I begin by explaining why the situation is indeed a dire one. One of the main tasks for a naturalistic psychosemantic theory is to describe how the extensions of mental representations are determined. (Such a theory may also attempt to account for other aspects of the “meaning” of mental representations, if there are any.) Some mental representations, e.g. the concept of water, denote kinds (I shall be assuming this is non-negotiable). How is this possible? Unfortunately, I haven’t the space to canvass all the theories out there and show that each one fails to accommodate the representation of kinds, but I will point out the major types of problems that arise for the kinds of theories that, judging by the literature, are considered viable contenders.1 In general, the theories either attempt and fail to account for the representation of kinds, or they fall back on something like an intention to refer to a kind – not exactly the most auspicious move for a reductive theory. There are a number of problems that prevent non-teleosemantic theories from explaining how it is possible to represent kinds. A concept of a kind K must.. (shrink)

I present an account of mental representation based upon the ‘SINBAD’ theory of the cerebral cortex. If the SINBAD theory is correct, then networks of pyramidal cells in the cerebral cortex are appropriately described as representing, or more specifically, as modelling the world. I propose that SINBAD representation reveals the nature of the kind of mental representation found in human and animal minds, since the cortex is heavily implicated in these kinds of minds. Finally, I show how SINBAD neurosemantics can (...) provide accounts of misrepresentation, equivocal representation, twin cases, and Frege cases. (shrink)

CRS says that the meanings of expressions of a language or other symbol system or the contents of mental states are determined and explained by the way symbols are used in thinking. According to CRS one.

The aim of this paper is to defend the teleological theory of representation against an objection by Jerry Fodor. I shall argue that previous attempts to answer this objection fail to recognize the importance of belief-desire structure for the teleological theory of representation.

Ruth Millikan and others advocate theories which attempt to naturalize wide mental content (e.g. beliefs.

The propositional attitudes are attitudes such as believing and desiring, taken toward propositions such as the proposition that snow flurries are expected, or that the Prime Minister likes poutine. Collectively, our views about the propositional attitudes make up much of folk psychology, our everyday theory of how the mind works.

I examine the way in which Daniel Dennett (1987, 1995) uses his 'intentional' and 'design' stances to make the claim that intentionality is derived from design. I suggest that Dennett is best understood as attempting to supply an objective, nonintentional, naturalistic rationale for our use of intentional concepts. However, I demonstrate that his overall picture presupposes prior application of the intentional stance in a preconditional, ineliminable,'sense-giving' role. Construed as such, Dennett's account is almost identical to the account of biological teleology (...) offered by Kant in The Critique of Judgement, with the consequence that Dennett's naturalism is untenable. My conclusions lead to doubts concerning the legitimacy of any account attempting to naturalise intentionality by extracting normativity from biology and also point to a novel account of biological function. (shrink)

A comprehensive introduction to the Language of Though Hypothesis (LOTH) accessible to general audiences. LOTH is an empirical thesis about thought and thinking. For their explication, it postulates a physically realized system of representations that have a combinatorial syntax (and semantics) such that operations on representations are causally sensitive only to the syntactic properties of representations. According to LOTH, thought is, roughly, the tokening of a representation that has a syntactic (constituent) structure with an appropriate semantics. Thinking thus consists in (...) syntactic operations defined over representations. Most of the arguments for LOTH derive their strength from their ability to explain certain empirical phenomena like productivity, systematicity of thought and thinking. (shrink)

Relying on a range of now-familiar thought-experiments, it has seemed to many philosophers that phenomenal consciousness is beyond the scope of reductive explanation. (Phenomenal consciousness is a form of state-consciousness, which contrasts with creature-consciousness, or perceptual-consciousness. The different forms of state-consciousness include various kinds of access-consciousness, both first-order and higher-order--see Rosenthal, 1986; Block, 1995; Lycan, 1996; Carruthers, 2000. Phenomenal consciousness is the property that mental states have when it is like something to possess them, or when they have subjectively-accessible feels; (...) or as some would say, when they have qualia (see fn.1 below).) Others have thought that we can undermine the credibility of those thought-experiments by allowing that we possess purely recognitional concepts for the properties of our conscious mental states. This paper is concerned to explain, and then to meet, the challenge of showing how purely recognitional concepts are possible if there are no such things as qualia--in the strong sense of intrinsic (non-relational, non-intentional) properties of experience. It argues that an appeal to higher-order experiences is necessary to meet this challenge, and then deploys a novel form of higher-order thought theory to explain how such experiences are generated. (shrink)

Are there different constraints on theories of conscious experience as against theories of conscious propositional thought? Is what is problematic or puzzling about each of these phenomena of the same, or of different, types? And to what extent is it plausible to think that either or both conscious experience and conscious thought involve some sort of selfreference? In pursuing these questions I shall also explore the prospects for a defensible form of eliminativism concerning conscious thinking, one that would leave the (...) reality of conscious experience untouched. In the end, I shall argue that while there might be no such thing as conscious judging or conscious wanting, there is (or may well be) such a thing as conscious generic thinking. (shrink)

This chapter contains sections titled: Highlights of Past Literature Current Work Future Work.

Many philosophers assert that psychological verbs generate opaque contexts and that the object of a psychological verb cannot be replaced with a co‐referring expression salva veritate as the objects of non‐psychological verbs can be. I argue that the logical and linguistic concerns which govern this assertion do not transfer to observational and experimental situations because the criteria that we use in order to verify that an observed subject has one hypothesized desire rather than another provide inconclusive evidence when we don't (...) allow for all regular substitutions in psychological contexts. This becomes more obvious when we contextualize intentional behavior within the appropriate framework by recognizing that, in order to make sense of any desire attribution, we must understand the subject experiencing the desire to be pursuing each desired situation as a means to a further overarching goal. I conclude that the object of desire should always be read de re. (shrink)

Anthropomorphism is the methodology of attributing human-like mental states to animals. Zoomorphism is the converse of this: it is the attribution of animal-like mental states to humans. Zoomorphism proceeds by first understanding what kind of mental states animals have and then attributing these mental states to humans. Zoomorphism has been widely used as scientific methodology especially in cognitive neuroscience. But it has not been taken seriously as a philosophical explanatory paradigm: as a way of explaining the building blocks of the (...) human mind. The philosophical explanatory paradigm of zoomorphism may not explain all aspects of human behavior, but if we accept the zoomorphic way of thinking about the human mind, we should only posit new, different kinds of mental states if the zoomorphic attribution of animal mental states fails to explain our behavior. (shrink)

This dissertation focuses on teleology and functions in biology. More precisely, it focuses on the scientific legitimacy of teleofunctional attributions and explanations in biology. It belongs to a multi-faceted debate that can be traced back to at least the 1970s. One aspect of the debate concerns the naturalization of functions. Most authors try to reduce, translate or explain functions and teleology in terms of efficient causes so that they find their place in the framework of the natural sciences. Our approach (...) here is radically different, as we question the premise that teleological explanations are disguised causal explanations. On the contrary, we defend that they are acceptable in natural sciences and in biology in particular. We challenge the idea that teleological explanations are immature causal explanations, as well as the idea that teleology and functions are some sort of intentional explanations. We therefore reject the accusations of anthropomorphism, vitalism and finalism. On the contrary, we defend that teleology, causality and intentionality correspond to different, autonomous and complementary modes of representation of the outside world. -/- ———[FRANÇAIS]——— -/- Ce travail de thèse porte sur la téléologie et les fonctions en biologie. Plus précisément, il porte sur la légitimité scientifique des attributions et des explications téléofonctionnelles en biologie. Il s’inscrit dans le cadre d’un débat à plusieurs facettes que l’on peut faire remonter au moins jusqu’aux années 1970 et qui est encore très actif aujourd’hui. L’un des aspects du débat porte sur la naturalisation des fonctions, c’est-à-dire sur la manière de les réduire, de les traduire ou de les expliciter en termes de causes efficientes de sorte qu’elles trouvent leur place dans le cadre des sciences de la nature. Notre approche ici est radicalement différente, car nous remettons en question la prémisse selon laquelle les explications téléologiques seraient des explications causales déguisées. Nous défendons au contraire qu’elles sont acceptables en tant que telles aussi bien de façon générale que dans le domaine scientifique et en particulier en biologie. De façon générale, nous remettons en question l’idée selon laquelle la pensée téléologique serait une pensée causale immature, ainsi que sa dépendance présumée vis-à-vis de la psychologie, c’est-à-dire de l’intentionnalité. Nous rejetons donc les accusations d’anthropomorphisme, de vitalisme et de finalisme formulées contre elle. Nous défendons au contraire que la téléologie, la causalité et l’intentionnalité correspondent à des modes différents, autonomes et complémentaires de représentation du monde extérieur. (shrink)

The concern of this paper is not with the truth of any particular realist or anti-realist view, but rather with determining what it is to be a realist or anti-realist in the first place. While much skepticism has been voiced in recent years about the viability of such a project, my goal is to articulate interesting and informative conditions whereby any view in any domain of experience can count as either a realist or an anti-realist position.

Significant variations in the way objects appear across different viewing conditions pose a challenge to the view that they have some true, determinate color. This view would seem to require that we break the symmetry between multiple appearances in favor of a single variant. A wide range of philosophical and non-philosophical writers have held that the symmetry can be broken by appealing to daylight viewing conditions—that the appearances of objects in daylight have a stronger, and perhaps unique, claim to reveal (...) their true colors. In this note we argue that, whatever else its merits, this appeal to daylight is not a satisfactory answer to the problem posed by perceptual variation. (shrink)

This book contains a representationalist theory of self-consciousness and of the phenomenal first-person perspective. It draws on empirical data from the cognitive and neurosciences.

In a recent paper, Gregory defends the claim that a normative reason is a good basis for Φ-ing. He claims that a “basis” is what is commonly known as a motivating reason. By “good” Gregory means good in its attributive sense, as something which is good as a kind. In this paper I argue that it is not plausible that normative reasons are motivating reasons that are good as an instance of their kind. I argue that in order to assess (...) this claim, pace Gregory, we need to know what it is for a motivating reason to be good as a kind. I canvas some potential answers to this question provided by Gregory, first that motivating reasons are things that play a role in a causal structure, and second that motivating reasons are what is believed to be a normative reason. I argue that since neither of these is plausibly good as a kind, we should reject RGB. (shrink)

The present paper looks at one of the most thorough articles on the intelligence of GPT, research conducted by engineers at Microsoft. Although there is a great deal of value in their work, I will argue that, for familiar philosophical reasons, their methodology, ‘Black-box Interpretability’ is wrongheaded. But there is a better way. There is an exciting and emerging discipline of ‘Inner Interpretability’ (also sometimes called ‘White-box Interpretability’) that aims to uncover the internal activations and weights of models in order (...) to understand what they represent and the algorithms they implement. In my view, a crucial mistake in Black-box Interpretability is the failure to appreciate that how processes are carried out matters when it comes to intelligence and understanding. I can’t pretend to have a full story that provides both necessary and sufficient conditions for being intelligent, but I do think that Inner Interpretability dovetails nicely with plausible philosophical views of what intelligence requires. So the conclusion is modest, but the important point in my view is seeing how to get the research on the right track. Towards the end of the paper, I will show how some of the philosophical concepts can be used to further refine how Inner Interpretability is approached, so the paper helps draw out a profitable, future two-way exchange between Philosophers and Computer Scientists. (shrink)

Some emotional representations seem to be unreliable. For instance, we are often afraid when there is no danger present. If emotions such as fear are so unreliable, what function do they have in our representational system? This is a problem for representationalist theories of emotion. I will argue that seemingly unreliable emotional representations are reliable after all. While many mental states strike an optimal balance between minimizing inaccurate representations and maximizing accurate representations, some emotional representations only aim at maximizing accuracy. (...) They detect important phenomena such as danger based on little evidence, which will lead to a lot of false alarms. When it matters, however, these emotional representations will detect danger and other important phenomena. Often, one is better scared (and wrong) than sorry. (shrink)

Can humans and artificial intelligences share concepts and communicate? Making AI Intelligible shows that philosophical work on the metaphysics of meaning can help answer these questions. Herman Cappelen and Josh Dever use the externalist tradition in philosophy to create models of how AIs and humans can understand each other. In doing so, they illustrate ways in which that philosophical tradition can be improved. The questions addressed in the book are not only theoretically interesting, but the answers have pressing practical implications. (...) Many important decisions about human life are now influenced by AI. In giving that power to AI, we presuppose that AIs can track features of the world that we care about (for example, creditworthiness, recidivism, cancer, and combatants). If AIs can share our concepts, that will go some way towards justifying this reliance on AI. This ground-breaking study offers insight into how to take some first steps towards achieving Interpretable AI. (shrink)