Recent advances in natural language processing have given rise to a new kind of AI architecture: the language agent. By repeatedly calling an LLM to perform a variety of cognitive tasks, language agents are able to function autonomously to pursue goals specified in natural language and stored in a human-readable format. Because of their architecture, language agents exhibit behavior that is predictable according to the laws of folk psychology: they function as though they have desires and beliefs, and then make (...) and update plans to pursue their desires given their beliefs. We argue that the rise of language agents significantly reduces the probability of an existential catastrophe due to loss of control over an AGI. This is because the probability of such an existential catastrophe is proportional to the difficulty of aligning AGI systems, and language agents significantly reduce that difficulty. In particular, language agents help to resolve three important issues related to aligning AIs: reward misspecification, goal misgeneralization, and uninterpretability. (shrink)

Under what conditions would an artificially intelligent system have wellbeing? Despite its clear bearing on the ethics of human interactions with artificial systems, this question has received little direct attention. Because all major theories of wellbeing hold that an individual’s welfare level is partially determined by their mental life, we begin by considering whether artificial systems have mental states. We show that a wide range of theories of mental states, when combined with leading theories of wellbeing, predict that certain existing (...) artificial systems have wellbeing. Along the way, we argue that there are good reasons to believe that artificial systems can have wellbeing even if they are not phenomenally conscious. While we do not claim to demonstrate conclusively that AI systems have wellbeing, we argue that there is a significant probability that some AI systems have or will soon have wellbeing, and that this should lead us to reassess our relationship with the intelligent systems we create. (shrink)

Recent research has identified a tension between the Safety principle that knowledge is belief without risk of error, and the Closure principle that knowledge is preserved by competent deduction. Timothy Williamson reconciles Safety and Closure by proposing that when an agent deduces a conclusion from some premises, the agent’s method for believing the conclusion includes their method for believing each premise. We argue that this theory is untenable because it implies problematically easy epistemic access to one’s methods. Several possible solutions (...) are explored and rejected. (shrink)

Cognitive penetration of perception, broadly understood, is the influence that the cognitive system has on a perceptual system. The paper shows a form of cognitive penetration in the visual system which I call ‘architectural’. Architectural cognitive penetration is the process whereby the behaviour or the structure of the perceptual system is influenced by the cognitive system, which consequently may have an impact on the content of the perceptual experience. I scrutinize a study in perceptual learning that provides empirical evidence that (...) cognitive influences in the visual system produce neural reorganization in the primary visual cortex. The type of cognitive penetration can be synchronic and diachronic. (shrink)

Contextology is the science of the dynamics of the conversational context. Contextology formulates laws governing how the shared information states of interlocutors evolve in response to assertion. More precisely, the contextologist attempts to construct a function which, when provided with just a conversation’s pre-update context and the content of an assertion, delivers that conversation’s post-update context. Most contextologists have assumed that the function governing the evolution of the context is simple: the post-update context is just the pre-update context intersected with (...) the content of the assertion. We argue that this assumption is wrong: not only is it false, it is also incoherent given standard contextological assumptions. Moreover, it is impossible in principle to revise it to correctly describe the dynamics of context. We conclude that there can be no science of Contextology. The laws governing the evolution of the context in response to assertion must make essential reference to the private information states of interlocutors. (shrink)

You omega know something when you know it, and know that you know it, and know that you know that you know it, and so on. This paper first argues that omega knowledge matters, in the sense that it is required for rational assertion, action, inquiry, and belief. The paper argues that existing accounts of omega knowledge face major challenges. One account is skeptical, claiming that we have no omega knowledge of any ordinary claims about the world. Another account embraces (...) the KK thesis, and identifies knowledge with omega knowledge. This position faces counterexamples, and struggles to make sense of inexact knowledge. The paper then develops a new account of knowledge, by proposing the principle of Reflective Luminosity: if you know that you know something, then you omega know it. I argue that Reflective Luminosity allows for omega knowledge while avoiding the problems for KK. (shrink)

Generics are sentences such as Birds fly, which express generalizations. They are prevalent in speech, and as far as is known, no human language lacks generics. Yet, it is very far from clear what they mean. After all, not all birds fly—penguins don’t! -/- There are two general views about the meaning of generics in the literature, and each view encompasses many specific theories. According to the inductivist view, a generic states that a sufficient number of individuals satisfy a certain (...) property—in the example above, it says that sufficiently many birds fly. This view faces the complicated problem of spelling out exactly how many is “sufficiently many” in a way that correctly captures the intuitive truth conditions of generics. -/- An alternative, the rules and regulations view, despairs from this project and proposes instead that generics directly express rules in the world. Rules are taken to be abstract objects, which are not related to the properties of specific individuals. This view faces the difficult problem of explaining how people come to know of such rules when judging the truth of falsity of generics, and accounting for the strong intuition that a sentence such as Birds fly talks about birds, not abstract objects. -/- What seems to be beyond dispute is that generics, even if they do not express rules, are lawlike: they state non-accidental generalizations. Many scholars have taken this fact to indicate that generics are parametric on possible worlds: they refer to worlds other than the actual world. This, again, raises the problem of how people come to know about what happens in these other worlds. However, a rigorous application of standard tests for intensionality shows that generics are not, in fact, parametric on possible worlds, but only on time. This unusual property may explain much of the mystery surrounding generics. -/- Another mysterious property of generics is that although there is no language without them, there is no linguistic construction that is devoted to the expression of genericity. Rather, generics can be expressed in a variety of ways, each of which can also express nongenerics. Yet, each manifestation of generics differs subtly (or sometimes not so subtly) in its meaning from the others. -/- Even when these and other puzzles of genericity are solved, one mystery would remain: Why are generics, which are so easy to produce and understand in conversation, so difficult to analyze? (shrink)

You omega know p when you possess every iteration of knowledge of p. This book argues that omega knowledge plays a central role in philosophy. In particular, the book argues that omega knowledge is necessary for permissible assertion, action, inquiry, and belief. Although omega knowledge plays this important role, existing theories of omega knowledge are unsatisfying. One theory, KK, identifies knowledge with omega knowledge. This theory struggles to accommodate cases of inexact knowledge. The other main theory is skeptical, claiming that (...) we do not omega know any ordinary claims about the world. This book develops and critically compares three new theories of omega knowledge. (shrink)

The notion of causation that Mary Shepherd develops in her 1824 An Essay Upon the Relation of Cause and Effect (ERCE) has a number of surprising features that have only recently begun to be studied by scholars. This relation is synchronic, rather than diachronic (ERCE 49-50); it always involves a “mixture” of pre-existing objects (ERCE 46-7); and the effect must be “a new nature, capable of exhibiting qualities varying from those of either of the objects unconjoined” (ERCE 63). In this (...) essay I argue for an emergentist interpretation of Shepherd’s causal theory. On the reading I defend, all effects have qualities that metaphysically emerge from the complex interactions of their constituents. This reading explains the structure of Shepherd’s causal relation and clarifies the central aims of her philosophical project. In response to the problems raised by the science of her time, Shepherd developed a theory of emergence and published it during the period when the concept was first being shaped and adopted by prominent philosophers. Her work thus merits a place in the history of emergentist ideas. (shrink)

The observational-theoretical distinction has played a central role in the philosophy of science from logical empiricism onwards. Developments within the discipline have shown that such a distinction hides two non-identical distinctions: observational vs. non-observational and theoretical vs. non-theoretical. Likewise, metatheoretical structuralism proposed a more sophisticated treatment of theoricity in terms of the operational dependence or independence of concepts from the theories in which they appear. Despite this remarkable sophistication, it is still generally accepted that the distinction between theoretical and non-theoretical (...) concepts coincides with the explanatory vs. non-explanatory and testing vs. non-testing distinctions. Ginnobili and Carman argued for the independence between theoricity and explanation. In this paper we will focus on testing and argue for its independence from both theoricity and explanation. To do so, we propose an account of theory testing based on the framework of metatheoretical structuralism and apply it to natural selection theory and cladistics. (shrink)

In ‘Sly Pete’ or ‘standoff’ cases, reasonable speakers accept incompatible conditionals, and communicate them successfully to a trusting hearer. This paper uses the framework of dynamic semantics to offer a new model of the conversational dynamics at play in standoffs, and to articulate several puzzles posed by such cases. The paper resolves these puzzles by embracing a dynamic semantics for conditionals, according to which indicative conditionals require that their antecedents are possible in their local context, and update this body of (...) information by eliminating the possibilities where the antecedent is true and the consequent is false. In this way, the dynamic analysis draws on insights from the material conditional and contextualist analyses, while explaining how standoffs are genuine disagreements. (shrink)

The Great Divide in metaphysical debates about laws of nature is between Humeans, who think that laws merely describe the distribution of matter, and non-Humeans, who think that laws govern it. The metaphysics can place demands on the proper formulations of physical theories. It is sometimes assumed that the governing view requires a fundamental / intrinsic direction of time: to govern, laws must be dynamical, producing later states of the world from earlier ones, in accord with the fundamental direction of (...) time in the universe. In this paper, we propose a minimal primitivism about laws of nature (MinP) according to which there is no such requirement. On our view, laws govern by constraining the physical possibilities. Our view captures the essence of the governing view without taking on extraneous commitments about the direction of time or dynamic production. Moreover, as a version of primitivism, our view requires no reduction / analysis of laws in terms of universals, powers, or dispositions. Our view accommodates several potential candidates for fundamental laws, including the principle of least action, the Past Hypothesis, the Einstein equation of general relativity, and even controversial examples found in the Wheeler-Feynman theory of electrodynamics and retrocausal theories of quantum mechanics. By understanding governing as constraining, non-Humeans who accept MinP have the same freedom to contemplate a wide variety of candidate fundamental laws as Humeans do. (shrink)

This paper develops a question-sensitive theory of intention. We show that this theory explains some puzzling closure properties of intention. In particular, it can be used to explain why one is rationally required to intend the means to one’s ends, even though one is not rationally required to intend all the foreseen consequences of one’s intended actions. It also explains why rational intention is not always closed under logical implication, and why one can only intend outcomes that one believes to (...) be under one’s control. (shrink)

In this paper, we present a way to translate the metainferences of a mixed metainferential system into formulae of an extended-language system, called its associated σ-system. To do this, the σ-system will contain new operators (one for each standard), called the σ operators, which represent the notions of "belonging to a (given) standard". We first prove, in a model-theoretic way, that these translations preserve (in)validity. That is, that a metainference is valid in the base system if and only if its (...) translation is a tautology of its corresponding σ-system. We then use these results to obtain other key advantages. Most interestingly, we provide a recipe for building unlabeled sequent calculi for σ-systems. We then exemplify this with a σ-system useful for logics of the ST family, and prove soundness and completeness for it, which indirectly gives us a calculus for the metainferences of all those mixed systems. Finally, we respond to some possible objections and show how our σ-framework can shed light on the “obeying” discussion within mixed metainferential contexts. (shrink)

How do the young learn names for feelings? After criticizing Wittgensteinian explanations, I formulate and defend an explanation very different from Wittgensteinians embrace.

Formal models of appearance and reality have proved fruitful for investigating structural properties of perceptual knowledge. This paper applies the same approach to epistemic justification. Our central goal is to give a simple account of The Preface, in which justified belief fails to agglomerate. Following recent work by a number of authors, we understand knowledge in terms of normality. An agent knows p iff p is true throughout all relevant normal worlds. To model The Preface, we appeal to the normality (...) of error. Sometimes, it is more normal for reality and appearance to diverge than to match. We show that this simple idea has dramatic consequences for the theory of knowledge and justification. Among other things, we argue that a proper treatment of The Preface requires a departure from the internalist idea that epistemic justification supervenes on the appearances and the widespread idea that one knows most when free from error. (shrink)

It is generally assumed that existing artificial systems are not phenomenally conscious, and that the construction of phenomenally conscious artificial systems would require significant technological progress if it is possible at all. We challenge this assumption by arguing that if Global Workspace Theory (GWT) — a leading scientific theory of phenomenal consciousness — is correct, then instances of one widely implemented AI architecture, the artificial language agent, might easily be made phenomenally conscious if they are not already. Along the way, (...) we articulate an explicit methodology for thinking about how to apply scientific theories of consciousness to artificial systems and employ this methodology to arrive at a set of necessary and sufficient conditions for phenomenal consciousness according to GWT. (shrink)

This paper develops an information-sensitive theory of the semantics and probability of conditionals and statements involving epistemic modals. The theory validates a number of principles linking probability and modality, including the principle that the probability of a conditional If A, then C equals the probability of C, updated with A. The theory avoids so-called triviality results, which are standardly taken to show that principles of this sort cannot be validated. To achieve this, we deny that rational agents update their credences (...) via conditionalization. We offer a new rule of update, Hyperconditionalization, which agrees with Conditionalization whenever nonmodal statements are at stake but differs for modal and conditional sentences. (shrink)

This paper explores the principle that knowledge is fragile, in that whenever S knows that S doesn’t know that S knows that p, S thereby fails to know p. Fragility is motivated by the infelicity of dubious assertions, utterances which assert p while acknowledging higher-order ignorance whether p. Fragility is interestingly weaker than KK, the principle that if S knows p, then S knows that S knows p. Existing theories of knowledge which deny KK by accepting a Margin for Error (...) principle can be conservatively extended with Fragility. (shrink)

Since the release of ChatGPT, there has been a lot of debate about whether AI systems pose an existential risk to humanity. This paper develops a general framework for thinking about the existential risk of AI systems. We analyze a two-premise argument that AI systems pose a threat to humanity. Premise one: AI systems will become extremely powerful. Premise two: if AI systems become extremely powerful, they will destroy humanity. We use these two premises to construct a taxonomy of ‘survival (...) stories’, in which humanity survives into the far future. In each survival story, one of the two premises fails. Either scientific barriers prevent AI systems from becoming extremely powerful; or humanity bans research into AI systems, thereby preventing them from becoming extremely powerful; or extremely powerful AI systems do not destroy humanity, because their goals prevent them from doing so; or extremely powerful AI systems do not destroy humanity, because we can reliably detect and disable systems that have the goal of doing so. We argue that different survival stories face different challenges. We also argue that different survival stories motivate different responses to the threats from AI. Finally, we use our taxonomy to produce rough estimates of ‘P(doom)’, the probability that humanity will be destroyed by AI. (shrink)

AI companies are racing to create artificial general intelligence, or “AGI.” If they succeed, the result will be human-level AI systems that can independently pursue high-level goals by formulating and executing long-term plans in the real world. Leading AI researchers agree that some of these systems will likely be “misaligned”–pursuing goals that humans do not desire. This goal mismatch will put misaligned AIs and humans into strategic competition with one another. As with present-day strategic competition between nations with incompatible goals, (...) the result could be violent and catastrophic conflict. Existing legal institutions are unprepared for the AGI world. New foundations for AGI governance are needed, and the time to begin laying them is now, before the critical moment arrives. -/- This Article begins to lay those new legal foundations. It is the first to think systematically about the dynamics of strategic competition between humans and misaligned AGI. The Article begins by showing, using formal game-theoretic models, that, by default, humans and AIs will be trapped in a prisoner’s dilemma. Both parties’ dominant strategy will be to permanently disempower or destroy the other, even though the costs of such conflict would be high. -/- The Article then argues that a surprising legal intervention could transform the game theoretic equilibrium and avoid conflict: AI rights. Not just any AI rights would promote human safety. Granting AIs the right not to be needlessly harmed–as humans have granted to certain non-human animals–would, for example, have little effect. Instead, to promote human safety, AIs should be given those basic private law rights–to make contracts, hold property, and bring tort claims–that law already extends to non-human corporations. Granting AIs these economic rights would enable long-run, small-scale, mutually-beneficial transactions between humans and AIs. This would, we show, facilitate a peaceful strategic equilibrium between humans and AIs for the same reasons economic interdependence tends to promote peace in international relations. Namely, the gains from trade far exceed those from war. Throughout, we argue that human safety, rather than AI welfare, provides the right framework for developing AI rights. This Article explores both the promise and the limits of AI rights as a legal tool for promoting human safety in an AGI world. (shrink)

This paper focuses on negative exemplarity-related emotions (NEREs) and on their educational implications. In this paper, we will first argue for the nonexpendability of negative emotions broadly conceived (section 2) by defending their instrumental and intrinsic role in a good and flourishing life. In section 3, we will make the claim more specific by focusing on the narrower domain of NEREs and argue for their moral and educational significance by evaluating whether they fit the arguments provided in the previous section. (...) In section 4, we will propose three educational strategies to foster NEREs’ positive moral role. In conclusion, we will point out that an exemplarist approach to character education would greatly benefit from a more fine-grained account of the emotions involved in the educational process and from a broader perspective on which of these emotions should be taken as valuable for educational purposes. (shrink)

What is it to believe something might be the case? We develop a puzzle that creates difficulties for standard answers to this question. We go on to propose our own solution, which integrates a Bayesian approach to belief with a dynamic semantics for epistemic modals. After showing how our account solves the puzzle, we explore a surprising consequence: virtually all of our beliefs about what might be the case provide counterexamples to the view that rational belief is closed under logical (...) implication. (shrink)

There is a large literature exploring how accuracy constrains rational degrees of belief. This paper turns to the unexplored question of how accuracy constrains knowledge. We begin by introducing a simple hypothesis: increases in the accuracy of an agent’s evidence never lead to decreases in what the agent knows. We explore various precise formulations of this principle, consider arguments in its favour, and explain how it interacts with different conceptions of evidence and accuracy. As we show, the principle has some (...) noteworthy consequences for the wider theory of knowledge. First, it implies that an agent cannot be justified in believing a set of mutually inconsistent claims. Second, it implies the existence of a kind of epistemic blindspot: it is not possible to know that one’s evidence is misleading. (shrink)

Philosophy and Phenomenological Research, EarlyView.

We often claim to know what might be—or probably is—the case. Modal knowledge along these lines creates a puzzle for information-sensitive semantics for epistemic modals. This paper develops a solution. We start with the idea that knowledge requires safe belief: a belief amounts to knowledge only if it could not easily have been held falsely. We then develop an interpretation of the modal operator in safety that allows it to non-trivially embed information-sensitive contents. The resulting theory avoids various paradoxes that (...) arise from other accounts of modal knowledge. It also delivers plausible predictions about modal Gettier cases. (shrink)

Once upon a time, Aesop says, there was a donkey who wanted to be a pet dog. The pet dog was given many treats by the master and the household servants, and the donkey was envious of him. Hence, the donkey began emulating the pet dog. What happened next? The story ends up with the donkey beaten senseless, chased off to the stables, exhausted and barely alive. Who is to blame for the poor donkey’s unfortunate fate? Well, there could be (...) disagreement upon this, but we think emulation is to blame. And it’s on the kinds of envy-related emulation that we focus in this chapter. More analytically, we aim at vindicating the role of envy for moral exemplars within an exemplarist character educational framework. In the first section, we recall the central tenets of an exemplarist account of moral progress, and highlight how negative emotions, in general, have suffered a bad press within character education, with exemplarism being no exception. Then we provide a brief outline of standard strategies of defending envy by appealing to useful taxonomies of envy (e.g., Taylor 1988; Protasi 2016; Fussi 2018). After that, we put forward our 'Donkey Objection' by recalling Aesop’s fable on "foolish imitation", so as to show that when envy triggers mere emulation, it can bear devastating effects such as conformism and a lack of self-worth and personal integrity. In response to this objection, we bring into play a distinction between two rival forms of imitation—emulation and inspiration—and we coin the label of "inspired envy" for those forms of imitation by inspiration triggered by envy that lead to self-improvement avoiding morally detrimental consequences. (shrink)

En un libro reciente McShea y Brandon defienden que la diversidad y la complejidad de la vida se explican, principalmente, por la acción de un principio que llaman “la ley evolutiva de fuerzas cero” o “ZFEL”. Tal principio actuaría de un modo implícito por detrás de muchas explicaciones de la biología, pero nunca habría sido explicitado. Asumiendo que esta idea es interesante, y que los autores en cuestión tienen razón, discutiremos el modo metateórico en que presentan dicho principio, como siendo (...) parte de la teoría de la probabilidad. Esto permite a los autores afirmar que la teoría de la probabilidad brindaría la base reductiva para toda la biología evolutiva (dado que consideran que otros principios, como el de selección natural, también serían parte de la teoría de la probabilidad). Defenderemos que, efectivamente, ZFEL no es propio de la biología únicamente, pero no por formar parte de la teoría de la probabilidad, sino por tratarse de una versión específica del principio de causa común. -/- In a recent book, McShea and Brandon argue that the observed diversity and complexity of life are explainable by a principle they call the “zero-force evolutionary law” or “ZFEL”. Although this principle would be implicit in many explanations given by biologists, it would have never been made explicit. Assuming that this idea is interesting, and that the authors are right, we will discuss the metatheoretical way in which they present said principle, as being a part of probability theory. This allows the authors to claim that probability theory provides the reductive basis for all evolutionary biology. We will defend, in accordance with them, that ZFEL is not a solely biological principle, but not because it is a part of probability theory, but rather because it is a specific version of the principle of common cause. (shrink)

Schlenker (Semant Pragmat 2(3):1–78, 2009; Philos Stud 151(1):115–142, 2010a; Mind 119(474):377–391, 2010b) provides an algorithm for deriving the presupposition projection properties of an expression from that expression’s classical semantics. In this paper, we consider the predictions of Schlenker’s algorithm as applied to attitude verbs. More specifically, we compare Schlenker’s theory with a prominent view which maintains that attitudes exhibit belief projection, so that presupposition triggers in their scope imply that the attitude holder believes the presupposition (Karttunen in Theor Linguist 34(1):181, (...) 1974; Heim in J Semant 9(3):183–221, 1992; Sudo in The art and craft of semantics: a festschrift for Irene Heim, MIT Press, 2014). We show that Schlenker’s theory does not predict belief projection, and discuss several consequences of this result. (shrink)

This paper models knowledge in cases where an agent has multiple experiences over time. Using this model, we introduce a series of observations that undermine the pretheoretic idea that the evidential significance of experience depends on the extent to which that experience matches the world. On the basis of these observations, we model knowledge in terms of what is likely given the agent’s experience. An agent knows p when p is implied by her epistemic possibilities. A world is epistemically possible (...) when its probability given the agent’s experiences is not significantly lower than the probability of the actual world given that experience. (shrink)

LLMs have dramatically improved in capabilities in recent years. This raises the question of whether LLMs could become genuine agents with beliefs and desires. This paper demonstrates an in principle limit to LLM agency, based on their architecture. LLMs are next word predictors: given a string of text, they calculate the probability that various words can come next. LLMs produce outputs that reflect these probabilities. I show that next word predictors are exploitable. If LLMs are prompted to make probabilistic predictions (...) about the world, these predictions are guaranteed to be incoherent, and so Dutch bookable. If LLMs are prompted to make choices over actions, their preferences are guaranteed to be intransitive, and so money pumpable. In short, the problem is that selecting an action based on its potential value is structurally different then selecting the description of an action that is most likely given a prompt: probability cannot be forced into the shape of expected value. The in principle exploitability of LLMs raises doubts about how agential they can become. This exploitability also offers an opportunity for humanity to safely control such AI systems. (shrink)

This paper examines the question of whether Large Language Models (LLMs) like ChatGPT possess minds, focusing specifically on whether they have a genuine folk psychology encompassing beliefs, desires, and intentions. We approach this question by investigating two key aspects: internal representations and dispositions to act. First, we survey various philosophical theories of representation, including informational, causal, structural, and teleosemantic accounts, arguing that LLMs satisfy key conditions proposed by each. We draw on recent interpretability research in machine learning to support these (...) claims. Second, we explore whether LLMs exhibit robust dispositions to perform actions, a necessary component of folk psychology. We consider two prominent philosophical traditions, interpretationism and representationalism, to assess LLM action dispositions. While we find evidence suggesting LLMs may satisfy some criteria for having a mind, particularly in game-theoretic environments, we conclude that the data remains inconclusive. Additionally, we reply to several skeptical challenges to LLM folk psychology, including issues of sensory grounding, the "stochastic parrots" argument, and concerns about memorization. Our paper has three main upshots. First, LLMs do have robust internal representations. Second, there is an open question to answer about whether LLMs have robust action dispositions. Third, existing skeptical challenges to LLM representation do not survive philosophical scrutiny. (shrink)

That all pleasure is good and all pain bad in itself is an eternally true ethical principle. The common claim that some pleasure is not good, or some pain not bad, is mistaken. Strict particularism (ethical decisions must be made case by case; there are no sound universal normative principles) and relativism (all good and bad are relative to society) are among the ethical theories we may refute through an appeal to pleasure and pain. Daniel Dennett, Philippa Foot, R M (...) Hare, Gilbert Harman, Immanuel Kant, J. L. Mackie, and Jean-Paul Sartre are among the many philosophers addressed. (shrink)

This paper develops a semantic solution to the puzzle of Free Choice permission. The paper begins with a battery of impossibility results showing that Free Choice is in tension with a variety of classical principles, including Disjunction Introduction and the Law of Excluded Middle. Most interestingly, Free Choice appears incompatible with a principle concerning the behavior of Free Choice under negation, Double Prohibition, which says that Mary can’t have soup or salad implies Mary can’t have soup and Mary can’t have (...) salad. Alonso-Ovalle 2006 and others have appealed to Double Prohibition to motivate pragmatic accounts of Free Choice. Aher 2012, Aloni 2018, and others have developed semantic accounts of Free Choice that also explain Double Prohibition. -/- This paper offers a new semantic analysis of Free Choice designed to handle the full range of impossibility results involved in Free Choice. The paper develops the hypothesis that Free Choice is a homogeneity effect. The claim possibly A or B is defined only when A and B are homogenous with respect to their modal status, either both possible or both impossible. Paired with a notion of entailment that is sensitive to definedness conditions, this theory validates Free Choice while retaining a wide variety of classical principles except for the transitivity of entailment. The homogeneity hypothesis is implemented in two different ways, homogeneous alternative semantics and homogeneous dynamic semantics, with interestingly different consequences. (shrink)

This paper offers the first careful analysis of the possibility that AI and humanity will go to war. The paper focuses on the case of artificial general intelligence, AI with broadly human capabilities. The paper uses a bargaining model of war to apply standard causes of war to the special case of AI/human conflict. The paper argues that information failures and commitment problems are especially likely in AI/human conflict. Information failures would be driven by the difficulty of measuring AI capabilities, (...) by the uninterpretability of AI systems, and by differences in how AIs and humans analyze information. Commitment problems would make it difficult for AIs and humans to strike credible bargains. Commitment problems could arise from power shifts, rapid and discontinuous increases in AI capabilities. Commitment problems could also arise from missing focal points, where AIs and humans fail to effectively coordinate on policies to limit war. In the face of this heightened chance of war, the paper proposes several interventions. War can be made less likely by improving the measurement of AI capabilities, capping improvements in AI capabilities, designing AI systems to be similar to humans, and by allowing AI systems to participate in democratic political institutions. (shrink)

Many defend the thesis that when someone knows p, they couldn’t easily have been wrong about p. But the notion of easy possibility in play is relatively undertheorized. One structural idea in the literature, the principle of Counterfactual Closure (CC), connects easy possibility with counterfactuals: if it easily could have happened that p, and if p were the case, then q would be the case, it follows that it easily could have happened that q. We first argue that while CC (...) is false, there is a true restriction of it to cases involving counterfactual dependence on a coin flip. The failure of CC falsifies a model where the easy possibilities are counterfactually similar to actuality. Next, we show that extant normality models, where the easy possibilities are the sufficiently normal ones, are incompatible with the restricted CC thesis involving coin flips. Next, we develop a new kind of normality theory that can accommodate the restricted version of CC. This new theory introduces a principle of Counterfactual Contamination, which says roughly that any world is fairly abnormal if at that world very abnormal events counterfactually depend on a coin flip. Finally, we explain why coin flips and other related events have a special status. A central take home lesson is that the correct principle in the vicinity of Safety is importantly normality-theoretic rather than (as it is usually conceived) similarity-theoretic. (shrink)

Triviality results threaten plausible principles governing our credence in epistemic modal claims. This paper develops a new account of modal credence which avoids triviality. On the resulting theory, probabilities are assigned not to sets of worlds, but rather to sets of information state-world pairs. The theory avoids triviality by giving up the principle that rational credence is closed under conditionalization. A rational agent can become irrational by conditionalizing on new evidence. In place of conditionalization, the paper develops a new account (...) of updating: conditionalization with normalization. (shrink)

In this article, we provide three generators of propositional formulae for arbitrary languages, which uniformly sample three different formulae spaces. They take the same three parameters as input, namely, a desired depth, a set of atomics and a set of logical constants (with specified arities). The first generator returns formulae of exactly the given depth, using all or some of the propositional letters. The second does the same but samples up-to the given depth. The third generator outputs formulae with exactly (...) the desired depth and all the atomics in the set. To make the generators uniform (i.e. to make them return every formula in their space with the same probability), we will prove various cardinality results about those spaces. (shrink)

In recent years, a number of theorists have claimed that beliefs about probability are transparent. To believe probably p is simply to have a high credence that p. In this paper, I prove a variety of triviality results for theses like the above. I show that such claims are inconsistent with the thesis that probabilistic modal sentences have propositions or sets of worlds as their meaning. Then I consider the extent to which a dynamic semantics for probabilistic modals can capture (...) theses connecting belief, certainty, credence, and probability. I show that although a dynamic semantics for probabilistic modals does allow one to validate such theses, it can only do so at a cost. I prove that such theses can only be valid if probabilistic modals do not satisfy the axioms of the probability calculus. (shrink)

According to one tradition, uttering an indicative conditional involves performing a special sort of speech act: a conditional assertion. We introduce a formal framework that models this speech act. Using this framework, we show that any theory of conditional assertion validates several inferences in the logic of conditionals, including the False Antecedent inference. Next, we determine the space of truth-conditional semantics for conditionals consistent with conditional assertion. The truth value of any such conditional is settled whenever the antecedent is false, (...) and whenever the antecedent is true and the consequent is false. Then, we consider the space of dynamic meanings consistent with the theory of conditional assertion. We develop a new family of dynamic conditional-assertion operators that combine a traditional test operator with an update operation. (shrink)

Against Hume and Epicurus I argue that our selection of pleasure, pain and other objects as our ultimate ends is guided by reason. There are two parts to the explanation of our attraction to pleasure, our aversion to pain, and our consequent preference of pleasure to pain: 1. Pleasure presents us with reason to seek it, pain presents us reason to avoid it, and 2. Being intelligent, human beings (and to a degree, many animals) are disposed to be guided by (...) reason, and hence by what there is reason to choose, seek, and prefer, when they act. (shrink)

Resumen -/- El objetivo de este trabajo consiste en analizar las relaciones entre los modelos de optimalidad y la selección natural. Defenderemos que esas relaciones pueden dividirse en dos tipos, en tanto hay dos tipos de explicaciones seleccionistas, que llamaremos “históricas” y “ahistóricas”. Las explicaciones históricas revelan como una población dada adquiere un rasgo que es adaptativo en ese ambiente e involucran muchas generaciones, variación, etc. Las explicaciones ahistóricas, explican por qué, en determinado momento, ciertos tipos de organismos tienen un (...) mayor éxito reproductivo que otros. Mostraremos que los modelos de optimalidad pueden jugar un rol en la determinación del explanandum de las explicaciones histórica seleccionistas, esto es, que ayudan a reconocer qué rasgos son adaptativos. Por otra parte, mostramos que los modelos de optimalidad nos permiten determinar a veces la parte del explanans de las explicaciones ahistóricas (particularmente, el concepto de fitness). -/- Abstract -/- The goal of this paper is to analyze the relations between optimality models and natural selection. We contend that these relationships can be divided into two kinds, as there are two kinds of natural selection explanations, which we call “historical” and “ahistorical”. Historical explanations reveal how a given population acquires a trait which is adaptive in its environment, and involves many generations, variations, etc. Ahistorical ones, explain why, at a given moment, certain kinds of organisms have a greater reproductive success than others. We show that optimality models can play a role in determining the explanandum of historical selectionist explanations, that is, they help us to recognize which traits are adaptive. And, on the other hand, that optimality models sometimes allow us to determine part of the explanans of ahistorical explanations (particularly, the concept of fitness). (shrink)

A mental state is luminous if, whenever an agent is in that state, they are in a position to know that they are. Following Timothy Williamson’s Knowledge and Its Limits, a wave of recent work has explored whether there are any non-trivial luminous mental states. A version of Williamson’s anti-luminosity appeals to a safety- theoretic principle connecting knowledge and confidence: if an agent knows p, then p is true in any nearby scenario where she has a similar level of confidence (...) in p. However, the relevant notion of confidence is relatively underexplored. This paper develops a precise theory of confidence: an agent’s degree of confidence in p is the objective chance they will rely on p in practical reasoning. This theory of confidence is then used to critically evaluate the anti-luminosity argument, leading to the surprising conclusion that although there are strong reasons for thinking that luminosity does not obtain, they are quite different from those the existing literature has considered. In particular, we show that once the notion of confidence is properly understood, the failure of luminosity follows from the assumption that knowledge requires high confidence, and does not require any kind of safety principle as a premise. (shrink)

That pain and suffering are unwanted is no truism. Like the sadist, the masochist wants pain. Like sadism, masochism entails an irrational, abnormal attitude toward pain. I explain this abnormality.

By what types of properties do we specify twinges, toothaches, and other kinds of mental states? Wittgenstein considers two methods. Procedure one, direct, private acquaintance: A person connects a word to the sensation it specifies through noticing what that sensation is like in his own experience. Procedure two, outward signs: A person pins his use of a word to outward, pre-verbal signs of the sensation. I identify and explain a third procedure and show we in fact specify many kinds of (...) mental states in this way. (shrink)

Functionalists think an event's causes and effects, its 'causal role', determines whether it is a mental state and, if so, which kind. Functionalists see this causal role principle as supporting their orthodox materialism, their commitment to the neuroscientist's ontology. I examine and refute the functionalist's causal principle and the orthodox materialism that attends that principle.

“Happiness” is an evaluative, not a value-neutral psychological, concept.