J. Adam Carter

Action theory offers well-developed treatments of tool use and of delegation, but agentic AI belongs to neither category. The user specifies an end; the system autonomously selects the means. What, then, secures the connection between the user’s intention and outcome that distinguishes intentional action from lucky coincidence when things go right? I examine five candidate approaches – Davidsonian minimalism, principal–agent decomposition, strong practical-knowledge views, permissive intention-plus-success accounts, and extended-agency frameworks – and argue that each draws the line in the wrong place, variously under-crediting supervised use, over-demanding means-level transparency, erasing the competence/luck distinction, or inheriting the bloat and glue problems that plague extended-mind theories. The positive proposal then relocates non-deviance from route-identity to governance-stability. On the know-how account defended here, a user intentionally ϕ-s through agentic AI when her success manifests the exercise of supervisory know-how – viz., the competence to define an “acceptable corridor” of outcomes and means, to monitor for departures from that corridor, and to intervene or abort when drift threatens. This framework tolerates the opacity and route-variability characteristic of agentic AI, explains graded attributions across interaction profiles (in/on/out-of-the-loop), and remains neutral on whether the AI itself qualifies as an agent. It thereby vindicates, under specifiable conditions, the ordinary human claim “I ϕ-d through an AI agent” as tracking creditworthy governance.

This chapter investigates the prospects of a knowledge-first approach to disagreement. This approach takes knowledge to be the central value of the epistemic domain, and norms governing moves in this domain – such as belief in the face of disagreement – to drop right out of this value. On our account, in a case in which A and B disagree about whether p – where, after the discovery of the disagreement, A has a doxastic attitude D with content p and B has a doxastic attitude D* with content not-p – A prima facie should conciliate in virtue of her disagreement with B if and only if A’s doxastic attitude thus adopted would thereby be closer to knowledge than D, or else hold steadfast.

I reply here to five excellent commentaries on my book, Autonomous Knowledge: Radical Enhancement, Autonomy, and the Future of Knowing (Oxford University Press, 2022). In what follows, I address objections and constructive proposals from Gloria Andrada, Kevin McCain, Jesús Vega-Encabo, Duncan Pritchard, and Nikolaj Jang Lee Linding Pedersen & Peter J. Graham. Topics range from the application of autonomy to know-how and cognitive development, the resilience of evidentialism and virtue epistemology against nonautonomous enhancement cases, the distinction between positive and negative epistemic autonomy, and the axiological foundations of autonomous belief and self-constitution.

A key project in mainstream epistemology investigates the sense in which beliefs are vulnerable to knowledge-undermining luck and/or risk. This chapter will explore a related but largely overlooked question of how and to what extent our grasping connections between propositions is vulnerable to understanding- undermining luck and risk. The result will be a better view of how our attempts to understand the world are vulnerable when they are, and how to better mitigate against such vulnerabilities.

Information we use to structure our lives is increasingly stored digitally, rather than in biomemory. (Just think: if your online calendar went down, would you know where you are supposed to be and at what time next week?) Likewise, with breakthroughs such as those from Google DeepMind and OpenAI, discoveries at the frontiers of knowledge are increasingly due to machine learning (often, applied to massive datasets, extracted from a fast-growing datasphere) rather than to brainbound cognition. It’s hard to deny that knowledge retention and production are becoming increasingly – in various ways – digitised. Digital Knowledge: A Philosophical Investigation is the first book to squarely and rigorously investigate digital knowledge: what it is, how to make sense of it in connection with received theories of knowledge, and where it is going. Key questions J. Adam Carter examines along the way are the following: How is mere digital information converted into reliable digital knowledge? To what extent can digital knowledge be vindicated against sceptical challenges, and in what ways might digital knowledge stand distinctively subject to defeat? What is the epistemically optimal way for us to decide which tasks to outsource entirely to intelligent machines, and to what extent is further outsourcing appropriate (or not) to verify the results of that same outsourced cognition? Are there any ways in which the expansion of the datasphere threatens to make knowledge less, rather than more, easy to come by? If so, are there any promising ways to safeguard, epistemically, against such threats? Using fascinating examples throughout, such as the recent chess match between Stockfish and Google’s AlphaZero, smartphones and personalisation, Digital Knowledge: A Philosophical Investigation is ideal for researchers investigating this fascinating area of research at the intersection of traditional mainstream epistemology, the philosophy of cognitive science, the philosophy of technology, and computer science.

Intentional action is, in some sense, non-accidental. One prima facie promising way to account for this platitude is through Anscombe’s Practical Knowledge Principle (PKP), which holds that intentionally doing something requires knowing that you are doing it intentionally. While (PKP) offers strong anti-luck credentials, it has the problematic implication that intentional action becomes luminous. This chapter critiques some existing attempts to weaken (PKP) and introduces an alternative rooted in performance-theoretic virtue epistemology. The proposed framework distinguishes between two grades of intentional action, each with different levels of protection against luck in action. Both involve knowledge of what we are doing, but in different ways: the first grade requires externalist knowledge secured by apt practical belief, while the second – reflective or R-intentional action – demands also second-order knowledge of one’s abilities and their reliability in the relevant performance conditions. This two-tiered, virtue theoretic approach, which gives knowledge of abilities a central role at the second order, is shown to offer several explanatory advantages in action theory.

What is it to trust well? How do we do it? If we think of trust as a kind of aimed performance, capable not only of success but also of competence and aptness, we can put our understanding of what it is to trust well on an entirely new footing. This book takes this project up, and in doing so, it uses the core ‘trust as performance’ idea—which is developed and refined in substantive detail—in the service of explaining a range of philosophically important phenomena related to trust, including its nature and varieties, the evaluative norms that govern good trusting and distrusting (both implicit and deliberative), how trust relates to vulnerability, risk, negligence, and monitoring, as well as to trustworthiness and, more generally, to our practices of cooperation. The result, a telic theory of trust, opens up entirely new option space and a research agenda in the philosophy of trust that is methodologically in the spirit of virtue epistemology, but which takes on its own distinctive shape.

This accessible Element defends version of virtue epistemology shown to have all-things-considered advantages over other views on the market. The view is unorthodox, in that it incorporates Sosa's animal/reflective knowledge distinction, which has thus far had few takers. The author shows why embracing a multi-tiered framework is not a liability within virtue epistemology but instead affords it an edge not attainable otherwise. The particular account of knowledge goes beyond Sosa's own view by introducing and incorporating several theoretical innovations (regarding both basing and risk, as well as the introduction of multiple species of reflective knowledge) which are aimed at revamping how we think about 'high-grade' knowledge, how we attain it, and what it demands of us. The result is a new and improved stratified virtue epistemology that can hold up against scrutiny.

Trust is a central theme within social epistemology, and for good reason: trust is critical to successful communication and knowledge exchange. Doing social epistemology well requires, accordingly, that we understand how to minimize the various ways that bad trusting, and untrustworthiness, wreck social-epistemic exchanges (and, conversely: how good trusting, and trustworthiness, can help to facilitate them). This chapter critically discusses the significance of trust and its theoretical cognates—distrust, trustworthiness, and distrustworthiness—in social epistemology. Special focus is given to the following issues: (i) knowledge on trust; (ii) the entitlement to expect to be presumed trustworthy; (iii) the normativity of trusting; and the role of defective trust and distrust in cases of (iv) epistemic injustice; and (v) the uptake and spread of conspiracy theories.

A central conclusion developed and defended throughout the book is that epistemic autonomy is necessary for knowledge (both knowledge-that and knowledge-how) and in ways that epistemologists have not yet fully appreciated. The book is divided into five chapters. Chapter 1 motivates (using a series of twists on Lehrer’s TrueTemp case) the claim that propositional knowledge requires autonomous belief. Chapters 2 and 3 flesh out this proposal in two ways, by defending a specific form of history-sensitive externalism with respect to propositional knowledge-apt autonomous belief (Chapter 2) and by showing how the idea that knowledge requires autonomous belief—understood along the externalist lines proposed—corresponds with an entirely new class of knowledge defeaters (Chapter 3). Chapter 4 extends the proposal to (both intellectualist and anti-intellectualist) knowledge-how and performance enhancement, and in a way that combines insights from virtue epistemology with research on freedom, responsibility, and manipulation. Chapter 5 concludes with a new twist on the Value of Knowledge debate, by vindicating the value of epistemically autonomous knowledge over that which falls short, including (mere) heteronomous but otherwise epistemically impeccable justified true belief.

This paper has two aims. The first is critical: it argues that our mainstream epistemology of disagreement does not have the resources to explain what goes wrong in cases of group-level epistemic injustice. The second is positive: we argue that a functionalist account of group belief and group justification delivers an account of the epistemic peerhood relation between groups that (1) accommodates minority and oppressed groups, and (2) diagnoses the epistemic injustice cases correctly as cases of unwarranted belief on the part of the oppressor group.

The topic of this volume—theepistemology of group disagreement—aims to face the complex topic of group disagreement head on; it represents the first-ever volume of papers dedicated exclusively to group disagreement and to the epistemological puzzles such disagreements raise. The volume consists of 12 new essays by leading epistemologists working in the area, and it spans a range of different key themes related to group disagreement, some established themes and others entirely new. In what follows, we offer brief summaries of these 12 chapters, drawing some connections between them where appropriate.

We investigate to what extent it is epistemically advantageous and disadvantageous that groups whose members disagree over some issue use deliberation in comparison to voting as a way to reach collective agreements. Extant approaches in the literature to this ‘deliberation versus voting’ comparison typically assume there is some univocal answer as to which group strategy is best, epistemically. We think this assumption is mistaken. We approach the deliberation versus voting question from a pluralist perspective, in that we hold that a group’s collective endeavor to solve an internal dispute can be aimed at different, albeit not necessarily incompatible, epistemic goals, namely the goals of truth, evidence, understanding, and epistemic justice. Different answers to our guiding question, we show, correspond to different epistemic goals. We conclude by exploring several ways to mitigate the potential epistemic disadvantages of solving intragroup disagreement by means of deliberation in relation to each epistemic goal.

What is knowledge? Why is it valuable? How much of it do we have (if any at all), and what ways of thinking are good ways to use to get more of it? These are just a few questions that are asked in epistemology, roughly, the philosophical theory of knowledge. This is Epistemology is a comprehensive introduction to the philosophical study of the nature, origin, and scope of human knowledge. Exploring both classic debates and contemporary issues in epistemology, this rigorous yet accessible textbook provides readers with the foundation necessary to start doing epistemology. Organized around 11 key subtopics, and assuming no prior knowledge of the subject, this volume exposes readers to diverse, often contentious perspectives—guiding readers through crucial debates including Hume’s problem of induction, Descartes’ engagement with radical skepticism, rationalist and empiricist evaluations of a priori justification, and many more. The authors avoid complex technical terms and jargon in favor of an easy-to-follow, informal writing style with engaging chapters designed to stimulate student interest and encourage class discussion. Throughout the text, a wealth of up-to-date references and links to online resources are provided to enable further investigation of an array of epistemological topics. A balanced and authoritative addition to the acclaimed This is Philosophy series, This is Epistemology is a perfect primary textbook for philosophy undergraduates, and a valuable resource for general readers with interest in this important branch of philosophy.

Group polarization—the tendency of groups to incline toward more extreme positions than initially held by their individual members—has been rigorously studied by social psychologists, though in a way that has overlooked important philosophical questions. This is the first book-length treatment of group polarization from a philosophical perspective. The phenomenon of group polarization raises several important metaphysical and epistemological questions. From a metaphysical point of view, can group polarization, understood as an epistemic feature of a group, be reduced to epistemic features of its individual members? Relatedly, from an epistemological point of view, is group polarization best understood as a kind of cognitive bias or rather in terms of intellectual vice? This book compares four models that combine potential answers to the metaphysical and epistemological questions. The models considered are: group polarization as (i) a collective bias; (ii) a summation of individual epistemic vices; (iii) a summation of individual biases; and (iv) a collective epistemic vice. Ultimately, the authors defend a collective vice model of group polarization over the competing alternatives. The Philosophy of Group Polarization will be of interest to students and researchers working in epistemology, particularly those working on social epistemology, collective epistemology, social ontology, virtue epistemology, and distributed cognition. It will also be of interest to those working on issues in political epistemology, applied epistemology, and on topics at the intersection of epistemology and ethics.

Recent literature suggests that intellectual humility is valuable to its possessor not only morally, but also epistemically-viz., from a point of view where (put roughly) epistemic aims such as true belief, knowledge and understanding are what matters. Perhaps unsurprisingly, epistemologists working on intellectual humility have focused almost exclusively on its ramifications for how we go about forming, maintaining and evaluating our own beliefs, and by extension, ourselves as inquirers. Less explored by contrast is how intellectual humility might have implications for how we should conduct our practice of asserting. The present entry aims to rectify this oversight by connecting these two topics in a way that sharpens how it is that intellectual humility places several distinctive kinds of demands on assertion, and more generally, on how we communicate what we believe and know.

While fallibilism has been the dominant view in epistemology in recent times, the field has witnessed the rise of a new form of infallibilism. In a recent book, Jessica Brown has taken on the task of mounting a systematic defence of fallibilism against this new infallibilism. She argues that new infallibilism incurs several problematic commitments that fallibilism can avoid. In addition, the key data points that infallibilists have adduced in support of their view can be accommodated by fallibilism, giving fallibilism the upper hand. This paper develops a rejoinder on behalf of new infallibilism. It explores ways in which new infallibilists can avoid the problematic commitments Brown identifies and provides reason to think that some of the data points supporting new infallibilism cannot be as readily handled by fallibilism as Brown would have us think.