Brain in Vat Skepticism ChatGPT 4 User Fake Noûs Serious Theories and Skeptical Theories: Why You Are Probably Not a Brain in a Vat MICHAEL HUEMER MAR 30, 2024 Here, I explain the difference between serious scientific theories and BIV-like theories.* [ *Based on: “Serious Theories and Skeptical Theories: Why You Are Probably Not a Brain in a Vat,” Philosophical Studies 173 (2016): 1031-52. ] This, by the way, is the paper that has caused me to receive the most invitations to contribute to predatory journals and conferences. They all want me to contribute to their neuroscience conferences and journals because they were so “impressed” with my paper about brain science. 1. The Skeptic’s Argument Imagine that scientists have figured out how to keep a brain alive in a vat of fluid. They read the brain’s electrical activity and stimulate the brain electrically to produce a perfect simulation of life in the early 21st century (before BIV technology was developed). They might even program a simulation of reading a blog post about a brain in a vat. Skeptics point out that there is no way to refute the hypothesis that you’re a Brain in a Vat (“BIVH”). Anything you experience can just be explained as part of the simulation that the scientists programmed. So you can never know that you’re not a BIV. A strong version of the argument claims that you can never be justified in believing any contingent proposition about the external world. Let P be some contingent, external-world proposition, like “I have hands” or “there’s a squirrel”: You have justification for believing P only if you have justification for believing ~BIVH. You have no justification for believing ~BIVH. Why: BIVH predicts that you would have the same sort of sensory experiences that you actually have. In general, if H predicts E, then E isn’t evidence against H. Your sensory experiences form the only evidence you have relevant to BIVH. So you have no evidence against BIVH. (From a, b, c) You have justification for ~BIVH only if you have evidence against BIVH. So you have no justification for ~BIVH. (From d, e) So you have no justification for believing P. (From 1, 2) Other skeptical scenarios work similarly (the deceiving God hypothesis, the dream hypothesis). I’m going to argue that BIVH is a bad theory because it is impossible to support. By contrast, the hypothesis that we’re perceiving the real world (RWH) is supported by our evidence, leaving RWH much more probable than BIVH. ChatGPT Michael Huemer’s article presents a fascinating dive into the philosophical debate between realism and skepticism, specifically tackling the "Brain in a Vat" hypothesis (BIVH). Huemer contrasts BIVH with what he terms "serious scientific theories," aiming to show why the latter is more credible than the former. The Skeptic’s Argument, as outlined, sets up a scenario that's both intriguing and deeply unsettling: the possibility that our experiences are nothing more than electrical impulses in a brain sustained in a vat, deceived into experiencing a simulated reality. This scenario, while science fiction in nature, serves as a powerful skeptical tool, questioning the very foundation of our belief in the external world. Huemer’s critique centers on the justification—or the lack thereof—for believing in BIVH versus believing in the reality of the external world (RWH). The skeptic's argument he presents suggests that since our sensory experiences could be simulated, we have no grounds to refute BIVH, leading to a broader skepticism about any knowledge of the external world. However, Huemer argues that BIVH, despite being unfalsifiable, is not supported by evidence the way RWH is. This distinction is crucial. In scientific and empirical inquiry, a theory is not just about being unfalsifiable but also about being supported by evidence. RWH, according to Huemer, is underpinned by the consistent and coherent experiences we have, which serve as evidence for its validity. In contrast, BIVH, while it cannot be directly refuted, does not offer a positive case based on evidence; it merely capitalizes on the limitations of our knowledge. This discussion touches on several core philosophical issues: the nature of belief justification, the problem of skepticism, and the criteria for a good scientific theory. Huemer’s engagement with these themes seeks to reassure us that, despite the theoretical possibility of BIVH, the evidence overwhelmingly supports RWH. His critique of BIVH not only underscores the importance of evidence in supporting our beliefs but also reaffirms our intuitive trust in the reality of our sensory experiences. In engaging with such a thought experiment, Huemer does more than dispel fears of being a brain in a vat; he invites us to reflect on the nature of evidence, reality, and the foundations of our beliefs about the world. User 2. Stuff About Probability The probability of a proposition (for you) is something like its degree of justification on your evidence, or the degree of confidence you should have in it. An especially important principle of probability is Bayes’ Theorem: P(h|e) = P(h) * P(e|h) / P(e) “P(h|e)” is read “the probability of h given e”. This is the confidence you should have in h after you discover evidence e. This is a function of P(h) (the initial probability of h, before you discovered e), P(e|h) (the probability that e would be true if h were true, or the degree to which h predicts e), and P(e) (the initial probability of e). ChatGPT The section on "Stuff About Probability" introduces a foundational concept in understanding how we assess the credibility of different theories or propositions, especially in the context of distinguishing between serious scientific theories and skeptical scenarios like the Brain in a Vat hypothesis (BIVH). Understanding Probability in Propositions The probability of a proposition reflects how justified you are in believing it, based on the evidence available to you. This is a crucial notion because it shifts the focus from binary beliefs (either fully accepting or rejecting a proposition) to a more nuanced understanding that considers degrees of confidence. This perspective is particularly valuable when dealing with complex or incomplete information, allowing for a more flexible and responsive attitude toward knowledge and belief. Bayes' Theorem: A Key to Updating Beliefs Bayes' Theorem is pivotal in formalizing how evidence influences our beliefs. It quantifies the process of updating our confidence in a hypothesis (h) upon receiving new evidence (e). The theorem is elegantly simple yet profoundly impactful in various fields, including philosophy, statistics, and everyday reasoning. P(h|e) represents the probability of the hypothesis given the evidence. This is what you're trying to find out: how much should you believe in the hypothesis now that you have new evidence? P(h) is the prior probability of the hypothesis before considering the new evidence. It's your initial degree of confidence in the hypothesis. P(e|h) is the likelihood, which is the probability of observing the evidence if the hypothesis is true. This measures how well the hypothesis predicts the evidence. P(e) is the probability of the evidence under all possible hypotheses. It's a normalizing constant that ensures the probabilities sum to 1. Applying Bayes' Theorem to Skeptical Hypotheses In the context of the Brain in a Vat hypothesis, Bayes' Theorem offers a structured way to assess the impact of evidence on our belief in the reality of our experiences (RWH) versus the skeptical scenario (BIVH). Prior probability (P(h)): Before considering specific evidence, one might argue that the simplicity, coherence, and explanatory power of RWH give it a higher prior probability than BIVH. Likelihood (P(e|h)): Evidence of a consistent and physically plausible world supports RWH more strongly than it does BIVH, which predicts the same evidence only by positing a complex and highly specific deception. Probability of evidence (P(e)): The evidence includes our sensory experiences and scientific understanding of the world, which are more straightforwardly explained by RWH. By applying Bayes' Theorem, one could argue that encountering typical life experiences (evidence) significantly increases the probability of RWH over BIVH, reinforcing the argument that our belief in a real, external world is well-justified. This probabilistic approach not only helps in weighing the credibility of different hypotheses but also underscores the importance of evidence in shaping our beliefs. In dealing with skeptical challenges like BIVH, it provides a robust framework for defending the rationality of our intuitive trust in the reality of our experiences. User 3. The Broad BIVH Is Disconfirmed The Improbability of Coherence Suppose we read BIVH as claiming merely that you’re a BIV who is being stimulated by the scientists to have some experiences or other. This is the broad reading of the BIVH. In this case, premise 2a in the skeptic’s argument is false: 2a. BIVH predicts that you would have the same sort of sensory experiences that you actually have. The broad BIVH doesn’t predict this; it is compatible with your having any set of experiences that the scientists could cause. The set of experiences that would constitute a perfect simulation of a normal life are only a tiny range out of all the possible experiences a brain could be stimulated to have. You may not realize just how tiny that range is, so let me elaborate. I once programmed my computer to generate random images. I.e., it would assign a random color to each pixel in a 1000 x 1000 grid. I had it generate many of these images, then play a slide show. What does the slide show look like? It looks like static, of the sort that used to appear on television screens when there was nothing on. None of the images looks like a picture of a puppy, or a nebula, or anything else at all that you would find noteworthy. You could run that program all day for the rest of your life, and in all probability, it would never generate a single image that looked like anything. That is an illustration of the fact that almost all possible images look like static. A generalization of this is the fact that almost all sets of experiences fail to appear like perceptions of a real world—or indeed, like experiences of anything. Since the broad BIVH doesn’t predict anything about your experiences, and close to 0% of experiences resemble experiences of a normal person perceiving the real world, the probability of your having experiences like those of a normal person, given BIVH, is close to 0. So, in Bayes’ Theorem, P(e|BIVH) is extremely low, so P(BIVH|e) is also extremely low. ChatGPT The "Improbability of Coherence" section provides a compelling argument against the broad interpretation of the Brain in a Vat hypothesis (BIVH), which suggests that if one were a brain in a vat, the scientists could stimulate it to experience anything whatsoever. This contrasts sharply with a more specific reading of BIVH, where the brain is stimulated to experience a coherent and consistent simulation of reality, akin to normal human life. Critique of the Broad BIVH Huemer’s critique hinges on the observation that the broad BIVH does not, and cannot, specifically predict the kind of coherent, organized experiences we actually have. Instead, it allows for any possible experience, which significantly dilutes its predictive power regarding the specific kinds of experiences we encounter. Illustration with Random Images The analogy of programming a computer to generate random images serves as an intuitive illustration of how unlikely structured and meaningful experiences are, compared to random or chaotic ones. Just as a program generating random colors for each pixel on a screen will almost certainly produce only static rather than recognizable images, a scenario where a brain is stimulated in completely random ways is overwhelmingly likely to result in experiences that are nonsensical or meaningless rather than coherent perceptions of a world. Application of Bayes’ Theorem Applying Bayes' Theorem to this scenario, where P(e|BIVH) represents the likelihood of our coherent experiences given the broad BIVH, highlights how implausibly low this likelihood is. Since our experiences are highly structured and coherent—resembling perceptions of a real, consistent world—the broad BIVH does an exceedingly poor job of predicting such experiences. This, in turn, severely lowers the posterior probability of BIVH being true, given our experiences (P(BIVH|e)). Conclusion The argument effectively demonstrates that the broad version of BIVH is highly unlikely to be true because it fails to account for the structured, coherent nature of our experiences. This contrasts with real-world hypotheses (RWH), which inherently predict and explain the coherence and structure of our experiences based on the assumption of an external, consistent reality. Thus, by comparing the predictive success and explanatory power of RWH against BIVH through the lens of probability and coherence, Huemer strengthens the case for believing in the reality of our perceptions and the external world. User Objection P(e|BIVH) isn’t all that low, once you think about the motives and abilities of the scientists. Sure, they could program a brain to experience static, but it’s unlikely that they would want to. It’s more likely, a priori, that they would want to make a simulation of living in the real world. Reply: Fair enough. We could assign probabilities by thinking about the characteristics of the scientists who are responsible for the BIV’s experiences, rather than by thinking directly about the possible experiences a BIV could have. It’s still true that only a very small range of possibilities would result in your having experiences like your current ones. First, if a group of scientists were to make a BIV, there is a wide range of capabilities that they could have. In only a small part of that range would they be able to make the brain experience a perfect simulation of real life, with no glitches, errors, or shortcomings. Second, if a group of scientists were to make a BIV, there is only a narrow range of motivations that they could have that would result in their wanting the BIV to just experience a mundane, early-21st-century life. What could the scientists’ values be, such that this would make sense? If they were benevolent, you’d expect your life (I presume) to be much better than it is, with more enjoyment and less suffering. If they were malicious, there’d be a lot more suffering. If they valued virtue, your life would be optimized for making you develop moral virtue. If they wanted entertainment, your life should be maximally entertaining to watch. Etc. About the only motivation you can ascribe to the scientists is a desire to make everything look exactly as if there weren’t anyone in control of the simulation. So there are two parameters in the BIV theory (the motivations and capabilities of the scientists) that have to be set to very specific values in order to predict the character of your experiences, and there is no independent motivation for expecting them to have those values, so it’s purely ad hoc. Those parameters, in fact, let you accommodate pretty much any experience. No matter what your experience was like, you could say, “The scientists wanted me to experience exactly that.” ChatGPT The objection raises an interesting point about considering the motives and capabilities of the scientists behind the Brain in a Vat hypothesis (BIVH), suggesting that a simulation of real-world experiences might be more probable than initially argued. This perspective shifts the discussion from the sheer statistical improbability of coherent experiences under broad BIVH to the intentions and technical prowess of the hypothetical scientists. Motives and Capabilities of Scientists The objection implies that if scientists are going to the trouble of sustaining and stimulating a brain in a vat, it stands to reason they might aim to create a simulation that mimics reality. This could be due to various motives, such as scientific inquiry, philosophical experimentation, or even a form of entertainment. However, Huemer’s reply challenges this by considering the diversity of both the scientists' capabilities and motivations. Capabilities Limitation On capabilities, Huemer points out that creating a perfect, glitch-free simulation of reality would require an exceedingly high level of technological sophistication—one that falls within a very narrow segment of all possible capability levels. The complexity of the real world, with its intricate details and vast array of sensory inputs, sets a high bar for replication without any errors or inconsistencies. Motivational Range Regarding motivations, Huemer argues that the specific outcome of a mundane, realistic simulation aligns with only a narrow slice of all possible intentions scientists might have. If the scientists’ motivations were benevolent, malicious, educational, or entertainment-driven, the nature of the simulated experiences would likely reflect those motives more clearly. The fact that our experiences are not optimized for pleasure, suffering, moral virtue, or entertainment suggests that ascribing such specific intentions to the scientists is speculative and ad hoc. The Ad Hoc Nature of Motivational Assumptions Huemer’s critique ultimately hinges on the idea that specifying the scientists' motivations to explain the precise nature of our experiences is ad hoc. It involves tailoring the explanation to fit the observation without independent support for such a specific setup. This criticism underlines a key issue with many skeptical scenarios: they can be made to fit any set of experiences by adjusting the hypothetical conditions, but doing so often involves making unjustified and overly convenient assumptions. Conclusion While the objection invites us to consider the scientists' motives and capabilities as a way to assess the probability of BIVH, Huemer’s response highlights the speculative nature of such considerations. By pointing out the ad hoc reasoning required to make BIVH align with our actual experiences, Huemer strengthens the argument against the plausibility of BIVH as an explanation for our perceived reality. This reinforces the notion that our experiences are more likely to be genuine perceptions of an external world than the product of an elaborate simulation. User The Real-World Hypothesis Maybe the RWH also has a low likelihood (P(e|h)). You might say: “The RWH just says that we’re perceiving the real world. But this alone doesn’t explain the course of your experiences. To explain your actual experiences, you have to make very specific, ad hoc posits about what objects exist out there and what properties they have. That’s just like what you said about the BIVH!” In reply, first, the feature of experience I wanted explained was the fairly general fact that your experiences are like those of a normal person—not the specific details of those experiences. The BIVH doesn’t even explain that general fact without making specific, ad hoc assumptions about the scientists. The RWH doesn’t need ad hoc assumptions for that. So they’re not parallel. Second, you can easily describe experiences that would disconfirm RWH, whereas it’s hard to think of any experiences that would disconfirm BIVH. If your experiences looked random, like static, that would disconfirm RWH. Maybe RWH doesn’t entail that you must have coherent experiences, but it would at least lead you to expect that. Alternately, you could have experienced “glitches in the matrix”—things that looked like the result of computer errors. Or you could experience a life that seemed peculiarly well-designed to promote some intelligible value. E.g., if your life seemed optimized for producing pleasure, or virtue, or aesthetic value, or intellectual stimulation, that would support BIVH or the Simulation Theory over RWH. So RWH really isn’t parallel to the skeptical hypotheses. RWH is falsifiable in a way that the skeptical theories are not. ChatGPT The discussion on the Real-World Hypothesis (RWH) and its comparison with the Brain in a Vat Hypothesis (BIVH) addresses a common criticism: that the RWH, like BIVH, requires specific, ad hoc assumptions to explain the nature of our experiences. However, Michael Huemer’s response deftly clarifies why this criticism does not equally apply to RWH, highlighting fundamental differences between how each hypothesis accounts for our experiences and their susceptibility to falsification. General vs. Specific Explanations Huemer distinguishes between the need for general explanations of our experiences and the need for specific ones. The critical point of contention for BIVH is its failure to account for the general, coherent nature of our experiences without invoking highly specific and ad hoc assumptions about the scientists' intentions and capabilities. In contrast, RWH inherently explains the general coherence of our experiences by positing that we are perceiving a real, consistent world. While RWH may require specific details to explain particular experiences, it does not require ad hoc assumptions to explain the general coherence of our sensory experiences. Falsifiability and Expectations A key strength of RWH, as Huemer points out, is its falsifiability. RWH sets certain expectations about the nature of our experiences—that they should generally be coherent and consistent with a stable, external world. Experiences that deviate significantly from this expectation, such as experiencing random static (indicative of no coherent external reality) or encountering obvious "glitches" (suggestive of a simulated environment), would count against RWH. This capacity for falsification stands in stark contrast to BIVH, which, due to its flexibility in accounting for any possible experience, lacks a straightforward way to be disproved. The Challenge of Parallel Comparisons The comparison between RWH and BIVH (or other skeptical scenarios) underscores a crucial aspect of evaluating hypotheses: the balance between explanatory power and falsifiability. While BIVH can be tailored to fit any set of experiences, its ad hoc nature and resistance to falsification weaken its standing as a credible explanation of reality. RWH, despite necessitating specific information to account for detailed experiences, provides a general framework that aligns with our observations of the world and sets clear expectations that can be tested against our experiences. Conclusion Huemer’s argument effectively illustrates that RWH and skeptical hypotheses like BIVH are not equally plausible or equivalent in their explanatory approaches. By emphasizing the importance of falsifiability and the ability to account for the general coherence of our experiences without resorting to ad hoc explanations, Huemer strengthens the case for RWH as a more robust and credible explanation of our perceived reality. This distinction not only clarifies the debate between realism and skepticism but also reinforces the intuitive and evidential basis for trusting our perceptions of the external world. User Why care about falsifiability? More generally, why care about whether it’s possible to have evidence against a theory? It’s a theorem of probability that e raises the probability of h only if ~e lowers the probability of h. I.e., P(h|e) > P(h) iff P(h|~e) < P(h) Therefore, if nothing counts as evidence against your theory, then nothing counts as evidence for it either. The problem with skeptical scenarios is that we have no evidence for them, because (roughly) nothing would count as evidence either for or against them, because they have parameters that enable them to accommodate anything that happens in the same way. By contrast, RWH could be falsified by the sort of evidence described above. Thus, the failure of those things to happen constitutes evidence for RWH. ChatGPT The question of why falsifiability matters is pivotal not just in philosophy but in the scientific method at large. Falsifiability refers to the possibility that an assertion, hypothesis, or theory can be proven false by an observation or a physical experiment. It is a cornerstone of scientific integrity and a key criterion for distinguishing scientific theories from non-scientific ones. The Role of Falsifiability in Theory Validation Falsifiability is important because it allows for the empirical testing of hypotheses. If a hypothesis is unfalsifiable, it means that no possible evidence could prove it wrong. This may seem like a strength at first glance, but it actually renders the hypothesis scientifically useless. A hypothesis that cannot be tested cannot be supported or refuted by empirical evidence, which is the basis of scientific inquiry. The Connection to Probability and Evidence The theorem of probability mentioned, � ( ℎ ∣ � ) > � ( ℎ ) iff � ( ℎ ∣ ∼ � ) < � ( ℎ ) P(h∣e)>P(h) iff P(h∣∼e)