Hyperreality, the uncanny valley, and disgust /  by Nathan Jones

A conversation with Copilot this afternoon

Nathan: Develop a thesis that explores the relationship between photographs and AI-generated images with particular emphasis on the "uncanny valley."

Copilot: Certainly! Here’s a thesis that explores the relationship between photographs and AI-generated images, with a focus on the “uncanny valley”:

“Navigating the Uncanny Valley: A Comparative Analysis of Photographs and AI-Generated Images in Contemporary Visual Culture”

Abstract: This thesis examines the evolving relationship between traditional photographs and AI-generated images, with a particular emphasis on the phenomenon known as the “uncanny valley.” The uncanny valley describes the discomfort or eeriness experienced when an artificial figure closely resembles a human but is not quite convincingly realistic. By analyzing the psychological, aesthetic, and cultural implications of this phenomenon, the thesis aims to understand how AI-generated images challenge and redefine our perceptions of authenticity, reality, and artistic expression in the digital age.

Introduction:

  • Background: Overview of the development of photography and the advent of AI-generated imagery.

  • Research Question: How do AI-generated images influence our perception of photographs, and what role does the uncanny valley play in this dynamic?

Chapter 1: Historical Context and Technological Evolution

  • Photography: Evolution from analog to digital photography.

  • AI-Generated Images: Development of AI technologies, including GANs (Generative Adversarial Networks) and their impact on image creation.

Chapter 2: The Uncanny Valley Phenomenon

  • Definition and Origins: Exploration of the uncanny valley concept, originally proposed by Masahiro Mori.

  • Psychological Impact: How the uncanny valley affects human perception and emotional response to AI-generated images.

Chapter 3: Comparative Analysis of Photographs and AI-Generated Images

  • Aesthetic Differences: Visual and stylistic distinctions between photographs and AI-generated images.

  • Perception of Authenticity: How viewers discern and react to the authenticity of photographs versus AI-generated images.

Chapter 4: Cultural and Ethical Implications

  • Artistic Expression: The role of AI in contemporary art and its influence on traditional photography.

  • Ethical Considerations: Issues of copyright, manipulation, and the potential for misinformation.

Chapter 5: Case Studies and Practical Applications

  • Case Studies: Analysis of specific instances where AI-generated images have been used in media, advertising, and art.

  • Future Directions: Predictions for the future of visual culture as AI technology continues to advance.

Conclusion:

  • Summary of Findings: Recap of key insights from the comparative analysis.

  • Implications for Visual Culture: How the interplay between photographs and AI-generated images will shape future perceptions of reality and authenticity.

This thesis aims to provide a comprehensive understanding of the complex relationship between photographs and AI-generated images, highlighting the significant role of the uncanny valley in shaping contemporary visual culture.

Nathan: Elaborate this thesis by including the ideas of Jean Baudrillard, particularly hyperreality and "the desert of the real."

Copilot: Certainly! Here’s an elaborated version of the thesis, incorporating Jean Baudrillard’s concepts of hyperreality and “the desert of the real”:

“Navigating the Uncanny Valley: A Comparative Analysis of Photographs and AI-Generated Images in Contemporary Visual Culture”

Abstract: This thesis examines the evolving relationship between traditional photographs and AI-generated images, with a particular emphasis on the phenomenon known as the “uncanny valley.” The uncanny valley describes the discomfort or eeriness experienced when an artificial figure closely resembles a human but is not quite convincingly realistic. By analyzing the psychological, aesthetic, and cultural implications of this phenomenon, the thesis aims to understand how AI-generated images challenge and redefine our perceptions of authenticity, reality, and artistic expression in the digital age. The work of Jean Baudrillard, particularly his ideas on hyperreality and “the desert of the real,” will be crucial in exploring these themes.

Introduction:

  • Background: Overview of the development of photography and the advent of AI-generated imagery.

  • Research Question: How do AI-generated images influence our perception of photographs, and what role does the uncanny valley play in this dynamic?

Chapter 1: Historical Context and Technological Evolution

  • Photography: Evolution from analog to digital photography.

  • AI-Generated Images: Development of AI technologies, including GANs (Generative Adversarial Networks) and their impact on image creation.

Chapter 2: The Uncanny Valley Phenomenon

  • Definition and Origins: Exploration of the uncanny valley concept, originally proposed by Masahiro Mori.

  • Psychological Impact: How the uncanny valley affects human perception and emotional response to AI-generated images.

Chapter 3: Hyperreality and the Desert of the Real

Chapter 4: Comparative Analysis of Photographs and AI-Generated Images

  • Aesthetic Differences: Visual and stylistic distinctions between photographs and AI-generated images.

  • Perception of Authenticity: How viewers discern and react to the authenticity of photographs versus AI-generated images in a hyperreal context.

Chapter 5: Cultural and Ethical Implications

  • Artistic Expression: The role of AI in contemporary art and its influence on traditional photography.

  • Ethical Considerations: Issues of copyright, manipulation, and the potential for misinformation in a hyperreal world.

Chapter 6: Case Studies and Practical Applications

  • Case Studies: Analysis of specific instances where AI-generated images have been used in media, advertising, and art.

  • Future Directions: Predictions for the future of visual culture as AI technology continues to advance and further blurs the lines between reality and simulation.

Conclusion:

  • Summary of Findings: Recap of key insights from the comparative analysis.

  • Implications for Visual Culture: How the interplay between photographs and AI-generated images, influenced by Baudrillard’s theories, will shape future perceptions of reality and authenticity.

This expanded thesis integrates Baudrillard’s critical theories to provide a deeper understanding of the impact of AI-generated images on our perception of reality and authenticity in contemporary visual culture.

Nathan: Discuss the implications of AI-generated images serving as training data for image generation algorithms with specific reference to Baudrillard's concept of "hyperreality."

Copilot: The use of AI-generated images as training data for image generation algorithms has profound implications, especially when viewed through the lens of Jean Baudrillard’s concept of hyperreality. Baudrillard’s theory suggests that in a hyperreal world, the distinction between reality and simulation becomes blurred, leading to a state where simulations or copies become more real than reality itself.

Implications of AI-Generated Images as Training Data

  1. Feedback Loop of Simulations: When AI-generated images are used as training data, it creates a feedback loop where simulations are used to generate further simulations. This can lead to a situation where the generated images become increasingly detached from any original reality, reinforcing Baudrillard’s idea of hyperreality. The images produced are not based on real-world data but on previous simulations, which can amplify the sense of the “desert of the real” where the original reality is lost.

  2. Erosion of Authenticity: As AI-generated images proliferate and serve as training data, the line between authentic photographs and synthetic images becomes increasingly indistinguishable. This erosion of authenticity can lead to a hyperreal environment where viewers can no longer trust the veracity of visual content. Baudrillard’s notion of hyperreality is evident here, as the images that people consume are simulations that may appear more convincing than actual photographs.

  3. Cultural and Psychological Impact: The widespread use of AI-generated images can alter cultural perceptions of reality. In a hyperreal world, people might start to prefer the polished, idealized versions of reality presented by AI-generated images over the imperfect real world. This shift can have significant psychological impacts, as individuals may develop unrealistic expectations and perceptions based on these hyperreal images.

  4. Ethical and Societal Concerns: The use of AI-generated images as training data raises ethical questions about the manipulation of reality and the potential for misinformation. In a hyperreal context, the ability to create convincing but entirely fabricated images can be exploited for malicious purposes, such as deepfakes or propaganda. This challenges societal notions of truth and authenticity, aligning with Baudrillard’s idea that in a hyperreal world, the distinction between truth and falsehood becomes meaningless.

Baudrillard’s Hyperreality and AI-Generated Images

Baudrillard’s concept of hyperreality is particularly relevant in the context of AI-generated images. Hyperreality describes a condition in which the distinction between reality and simulation is blurred, and simulations become more real than reality itself. AI-generated images, especially when used as training data, exemplify this phenomenon by creating a self-reinforcing cycle of simulations that further detach from any original reality.

In summary, the use of AI-generated images as training data for image generation algorithms can significantly contribute to the creation of a hyperreal world, as described by Baudrillard. This process not only challenges our perceptions of authenticity and reality but also raises important ethical and societal questions about the future of visual culture.

Nathan: Speculate on whether the blurring between reality and simulation (as in Baudrillard's hyperreality) can erase our feelings of unease when we encounter the uncanny valley between photographs and AI-generated images.

Copilot: The blurring between reality and simulation, as described by Baudrillard’s concept of hyperreality, could potentially influence our feelings of unease when encountering the uncanny valley. Here are some speculative thoughts on how this might unfold:

Diminishing the Uncanny Valley Effect

  1. Increased Familiarity: As AI-generated images become more prevalent and sophisticated, people might become more accustomed to them. This increased exposure could reduce the initial discomfort associated with the uncanny valley, as viewers start to accept these images as a normal part of their visual environment.

  2. Normalization of Simulations: In a hyperreal world where simulations are ubiquitous, the distinction between real and artificial becomes less significant. If society collectively starts to value simulations as much as, or even more than, reality, the eerie feeling associated with the uncanny valley might diminish. People might no longer find AI-generated images unsettling because they are perceived as just another form of reality.

  3. Enhanced AI Realism: As AI technology advances, the realism of generated images will continue to improve. If AI-generated images become indistinguishable from photographs, the uncanny valley might effectively disappear. The more seamless the integration of AI-generated content into our visual culture, the less likely it is to trigger feelings of unease.

Persistent Uncanny Valley Effect

  1. Innate Human Perception: Despite the blurring of reality and simulation, there might be an inherent aspect of human perception that continues to detect and react to subtle differences between real and artificial images. This innate sensitivity could mean that the uncanny valley persists, even in a hyperreal context.

  2. Cultural and Psychological Factors: Cultural and psychological factors play a significant role in how we perceive and react to images. Even in a hyperreal world, societal norms and individual psychological responses might maintain a sense of unease when encountering images that are almost, but not quite, human-like. The uncanny valley could remain a relevant phenomenon due to these deep-seated factors.

  3. Ethical and Moral Concerns: The ethical implications of AI-generated images might continue to provoke unease. Concerns about authenticity, manipulation, and the potential misuse of AI-generated content could sustain the uncanny valley effect, as people remain wary of the implications of these technologies.

Conclusion

While the blurring of reality and simulation in Baudrillard’s hyperreality could reduce the uncanny valley effect by normalizing AI-generated images and increasing their realism, it is also possible that inherent human perceptual and psychological factors, along with ethical concerns, will ensure that some level of unease persists. The interplay between these forces will likely determine the future trajectory of our reactions to AI-generated images.

Nathan: Speculate on how the uncanny valley relates to the human emotion of disgust.

Copilot: The uncanny valley and the human emotion of disgust are closely related, as both involve strong, often negative, emotional reactions to stimuli that are perceived as unsettling or disturbing. Here are some speculative thoughts on how these concepts intersect:

Evolutionary Perspective

  1. Survival Mechanism: From an evolutionary standpoint, disgust is a survival mechanism designed to protect us from potential threats, such as rotten food or disease. Similarly, the uncanny valley might trigger a sense of unease or disgust because it signals something that is almost human but not quite right, potentially indicating a threat or anomaly that we should avoid.

  2. Detection of Anomalies: Both disgust and the uncanny valley involve the detection of anomalies. Disgust often arises from things that deviate from the norm in ways that suggest contamination or danger. The uncanny valley effect is triggered by entities that are close to human but have subtle differences that our brains detect as wrong or unnatural, leading to a similar feeling of repulsion.

Psychological and Emotional Responses

  1. Violation of Expectations: The uncanny valley effect occurs when something violates our expectations of what a human should look like. This violation can evoke a sense of disgust because it disrupts our cognitive and emotional equilibrium. When an AI-generated image or robot looks almost human but has slight imperfections, it can create a jarring experience that triggers disgust.

  2. Ambiguity and Uncertainty: Disgust is often associated with ambiguity and uncertainty, such as not knowing whether something is safe to touch or consume. The uncanny valley creates a similar sense of ambiguity, as we are unsure whether to categorize the entity as human or non-human. This uncertainty can lead to feelings of discomfort and disgust.

Cultural and Social Factors

  1. Cultural Conditioning: Our reactions to the uncanny valley and disgust are also shaped by cultural conditioning. Societal norms and values influence what we find acceptable or repulsive. In cultures where human-like robots or AI-generated images are more common, the threshold for the uncanny valley might shift, potentially altering the associated feelings of disgust.

  2. Social Boundaries: Disgust often reinforces social boundaries by marking certain behaviors or appearances as unacceptable. The uncanny valley can similarly reinforce boundaries between humans and machines, highlighting the discomfort we feel when these boundaries are blurred. This discomfort can manifest as disgust, reinforcing the distinction between what is considered authentically human and what is not.

Conclusion

The uncanny valley and the emotion of disgust are interconnected through their shared basis in detecting and reacting to anomalies. Both involve strong emotional responses to stimuli that deviate from the norm in unsettling ways. Understanding this relationship can provide insights into why we react so strongly to near-human entities and how these reactions are shaped by both evolutionary and cultural factors.

Nathan: Given the difference between liberals and conservatives in their susceptibility to disgust (as identified by Jonathan Haidt), speculate on whether conservatives are more likely than liberals to remain "stuck" in the uncanny valley, even as AI realism improves.

Copilot: Jonathan Haidt’s research suggests that conservatives tend to have a higher sensitivity to disgust compared to liberals. This difference in susceptibility to disgust could indeed influence how each group experiences the uncanny valley, especially as AI-generated images become more realistic.

Speculative Analysis

  1. Sensitivity to Disgust: Conservatives’ heightened sensitivity to disgust might make them more prone to experiencing the uncanny valley effect. Since the uncanny valley often triggers feelings of unease or repulsion when encountering near-human but imperfectly realistic images, conservatives might find these images more disturbing and harder to accept, even as AI realism improves3.

  2. Openness to Experience: Liberals generally score higher on openness to experience, which includes a greater tolerance for novelty and ambiguity2. This trait might make liberals more adaptable and accepting of AI-generated images, even when they fall into the uncanny valley. As AI technology advances and images become more lifelike, liberals might be quicker to overcome initial discomfort and integrate these images into their perception of normalcy.

  3. Moral Foundations: Haidt’s moral foundations theory indicates that conservatives place a higher value on purity and sanctity4. This emphasis on purity could make conservatives more sensitive to the subtle imperfections in AI-generated images that trigger the uncanny valley effect. The perception of these images as impure or unnatural might reinforce their discomfort and resistance to accepting them.

  4. Cultural and Psychological Adaptation: Over time, as AI-generated images become more prevalent and realistic, both liberals and conservatives might gradually adapt to these changes. However, the pace and extent of this adaptation could differ. Liberals, with their higher openness to experience, might adapt more quickly, while conservatives might remain more cautious and critical of these images, potentially staying “stuck” in the uncanny valley for a longer period.

Conclusion

While both liberals and conservatives might initially experience the uncanny valley effect, conservatives’ higher sensitivity to disgust and emphasis on purity could make them more likely to remain uncomfortable with AI-generated images, even as their realism improves. Liberals, on the other hand, might be more adaptable and quicker to accept these images as part of their visual landscape.

Nathan: Are there any studies specifically examining how political ideology affects reactions to the uncanny valley?

Copilot: There doesn’t appear to be extensive research specifically examining how political ideology affects reactions to the uncanny valley. However, there are some relevant insights and related studies that can help us speculate on this topic:

  1. Disgust Sensitivity and Political Ideology: Research by Jonathan Haidt and others has shown that conservatives tend to have higher sensitivity to disgust compared to liberals. Since the uncanny valley often triggers feelings of unease or disgust, it’s plausible that conservatives might experience stronger reactions to uncanny stimuli.

  2. Empathy and Perception: Studies have suggested that empathy plays a role in how people perceive human-like robots and AI-generated images. Conservatives and liberals may differ in their levels of empathy and how they process social and emotional cues, which could influence their reactions to the uncanny valley.

  3. Cultural and Psychological Factors: Cultural and psychological factors, which are often influenced by political ideology, can shape how individuals respond to near-human entities. For example, conservatives might be more likely to perceive AI-generated images as a threat to traditional human roles and values, potentially intensifying their discomfort.

While direct studies on political ideology and the uncanny valley are limited, these related findings suggest that conservatives might be more likely to experience and remain “stuck” in the uncanny valley due to their higher sensitivity to disgust and different empathetic responses.

Truth, rational acceptability, values, and dialogue /  by Nathan Jones

The position I have defended is that any choice of a conceptual scheme presupposes values, and the choice of a scheme for describing ordinary interpersonal relations and social facts, not to mention thinking about one's own life plan, involves, among other things, one's moral values. One cannot choose a scheme which simply 'copies' the facts, because no conceptual scheme is a mere 'copy' of the world. The notion of truth itself depends for its content on our standards of rational acceptability, and these in turn rest on and presuppose our values. Put schematically and too briefly, I am saying that theory of truth presupposes theory of rationality which in turn presupposes our theory of the good.

‘Theory of the good', however, is not only programmatic, but is itself dependent upon assumptions about human nature, about society, about the universe (including theological and metaphysical assumptions). We have had to revise our theory of the good (such as it is) again and again as our knowledge has increased and our world-view has changed.

It has become clear that in the conception I am defending there is no such thing as a 'foundation'. And at this point people become worried: are we not close to the view that there is no difference between 'justified' and 'justified by our lights' (relativism) or even 'justified by my lights' (a species of solipsism)?

The position of the solipsist is indeed the one we will land in if we try to stand outside the conceptual system to which the concept of rationality belongs and simultaneously pretend to offer a more 'rational' notion of rationality! (Many thinkers have fallen into Nietzsche's error of telling us they had a 'better' morality than the entire tradition; in each case they only produced a monstrosity, for all they could do was arbitrarily wrench certain values out of their context while ignoring others.) We can only hope to produce a more rational conception of rationality or a better conception of morality if we operate from within our tradition (with its echoes of the Greek agora, of Newton, and so on, in the case of rationality, and with its echoes of scripture, of the philosophers, of the democratic revolutions, and so on, in the case of morality); but this is not at all to say that all is entirely reasonable and well with the conceptions we now have. We are not trapped in individual solipsistic hells, but invited to engage in a truly human dialogue; one which combines collectivity with individual responsibility.

– Hilary Putnam in Reason, Truth, and History (1981)

In which Leo Strauss and Jeremy Bentham encounter the ghost of Aristotle /  by Nathan Jones

Hilary Putnam’s Truth, Reason, and History (itself an excursion prompted by Richard Rorty’s Philosophy and the Mirror of Nature) sent me down the rabbit-hole of investigating the life and thought of arch-utilitarian, Jeremy Bentham. (For context, see my previous post, which includes a lengthy quotation from Putnam that touches on Bentham and Bernard Williams.) I was intrigued to learn (from the Libertarians, no less!) that Bentham was highly critical of natural rights, which he considered to be pernicious fictions promoted by revolutionaries to subvert law and order.

With Natural Right and History by Leo Strauss in mind, and as part of my exploration of large language models in the service of a Langara College working group on generative AI, I decided it would be fun to set a creative test for Microsoft’s “AI companion,” Copilot, in this philosophical context.

PROMPT: Develop a Platonic dialog between Jeremy Bentham and Leo Strauss on the topic of natural right. Interrupt this dialog at an appropriate juncture with an appearance by the ghost of Aristotle, who changes the course of the conversation with his view on the role of government in enforcing natural rights.

RESPONSE:

A Platonic Dialogue between Jeremy Bentham and Leo Strauss on Natural Right

Characters:

  • Jeremy Bentham (B)

  • Leo Strauss (S)

  • Ghost of Aristotle (A)

Setting: A quiet garden in an academic institution, where Bentham and Strauss meet to discuss their views on natural right.

B: Good day, Mr. Strauss. I understand you have some strong views on natural right. I must say, I find the concept rather perplexing and, dare I say, nonsensical.

S: Good day, Mr. Bentham. Indeed, I do hold natural right in high regard. It is a concept deeply rooted in the rational order of nature, as understood by the ancients.

B: Ah, the ancients. You mean those who believed in inherent rights bestowed by nature? I find such notions to be mere fictions, invented to justify rebellion and anarchy. Rights, in my view, are the creations of legal systems, not nature.

S: I see where you are coming from. However, I believe that natural right, as conceived by philosophers like Plato and Aristotle, is not about anarchy but about understanding the rational order of the world. It provides a framework for justice that transcends positive law.

B: But how can we base our moral and legal systems on something so abstract and variable? Natural rights are, as I have said, “nonsense upon stilts.” They lack the concrete foundation that legal rights possess.

S: Natural right, Mr. Bentham, is not as abstract as you might think. It is about recognizing a hierarchy of ends that are universally valid, even if the specific rules of action to achieve these ends can vary with circumstances. This flexibility is what makes natural right adaptable to different contexts.

B: Flexibility, you say? To me, that sounds like a recipe for inconsistency and confusion. How can we ensure justice if our moral principles are so malleable?

S: The flexibility of natural right does not imply inconsistency. Rather, it acknowledges the complexity of human life and the need for moral principles that can adapt to different situations. Unlike the rigid rules of natural law, natural right allows for a more nuanced approach to justice.

B: I remain unconvinced. My utilitarian approach focuses on the greatest happiness for the greatest number, a clear and measurable goal. Natural right, with its talk of hierarchies and ends, seems too nebulous to guide practical decision-making.

S: Utilitarianism, while pragmatic, often overlooks the deeper values and commitments that define human life. Natural right, as I see it, provides a richer moral framework that respects these values. It is not merely about outcomes but about the principles that guide our actions.

B: Principles are all well and good, but without concrete outcomes, they are of little use. My concern is with the tangible effects of our actions on human happiness.

S: And that is where we differ, Mr. Bentham. While I do not dismiss the importance of outcomes, I believe that a focus solely on consequences can lead to a neglect of the moral integrity and the deeper purposes that give life meaning.

B: Perhaps we shall have to agree to disagree. Your natural right remains, to me, an elegant but impractical ideal.

S: And your utilitarianism, Mr. Bentham, while practical, may sometimes miss the profound truths about human nature and justice. But such is the beauty of philosophical discourse—we challenge and refine each other’s views.

B: Indeed, Mr. Strauss. It has been a stimulating conversation. Until next time.

S: Until next time, Mr. Bentham.

(Suddenly, a ghostly figure appears, interrupting their conversation.)

A: Gentlemen, I could not help but overhear your discussion. I am Aristotle, and I have come to offer my perspective on the role of government in enforcing natural rights.

B: Aristotle! This is quite unexpected. Please, enlighten us with your wisdom.

S: Indeed, Aristotle. Your views on natural right and the role of the polis are most welcome.

A: Thank you. In my view, the role of government is to cultivate virtue and ensure the good life for its citizens. Natural rights are not merely abstract principles but are grounded in the nature of human beings as rational and social creatures. The government must create conditions that allow individuals to fulfill their potential and achieve eudaimonia, or flourishing.

B: But how does this translate into practical governance? How can a government enforce such lofty ideals?

A: The government must enact laws that promote justice and the common good. These laws should be based on the natural order and the rational nature of human beings. It is through the enforcement of just laws that the government can protect natural rights and ensure that citizens live virtuous lives.

S: This aligns with my view that natural right involves a hierarchy of ends. The government must recognize and uphold these ends to create a just society.

B: I see. So, you believe that the government’s role is to enforce laws that reflect the natural order and promote human flourishing?

A: Precisely. The laws must be just and aligned with the rational nature of human beings. This is how the government can protect natural rights and ensure the well-being of its citizens.

S: Thank you, Aristotle. Your insights have added a valuable dimension to our discussion.

B: Indeed, Aristotle. Your perspective has given me much to consider. Perhaps there is more to natural right than I initially thought.

A: I am glad to have contributed to your understanding. Remember, the pursuit of wisdom is a lifelong journey. Farewell, gentlemen.

(The ghost of Aristotle fades away, leaving Bentham and Strauss deep in thought.)

An adequate conception of the better /  by Nathan Jones

Imagine a society of farmers who, for some reason, have a total disinterest in the arts, in science (except in such products as assist them in farming), in religion, in short, in everything spiritual or cultural. (I don't mean to suggest that actual peasant societies are or ever have been like this.) These people need not be imagined as being bad people; imagine them as cooperative, pacific, reasonably kind to one another, if you like. What I wish the reader to imagine is that their interests are limited to such minimal goals as getting enough to eat, warm shelter, and such simple pleasures as getting drunk together in the evenings. In short, imagine them as living a relatively animal' existence, and as not wishing to live any other kind of existence.

Such people are not immoral. There is nothing impermissible about their way of life. But our natural tendency (unless we are entranced with Ethical Relativism) is to say that their way of life is in some way contemptible. It is totally lacking in what Aristotle called 'nobility'. They are living the lives of swine – amiable swine, perhaps, but still swine, and a pig's life is no life for a man.

At the same time – and this is the rub – we are disinclined to say the pig-men are in any way irrational. This may be the result of our long acculturation in the Benthamite use of 'rational' and ‘irrational', but, be that as it may, it is our present disposition. The lives of the pig-men are not as good as they might be, we want to say, but they are not irrational.

We do not want to say that it is just a matter of taste whether one lives a better or worse life. We don't see how we can say that it is rational to choose the better life and irrational to choose the worse. Yet not saying some such things seems precisely to be saying that 'it's all relative'; the ground crumbles beneath our feet.

Perhaps some of the corrections to Benthamite psychology suggested by Bernard Williams will help with this case. Let us assume the pig-men are born with normal human potential (if they aren't, then their lives aren't worse than they might be, and we are not justified in feeling contempt, but only, at most, pity). Then they might be led to appreciate artistic, scientific, and spiritual aspects of life; to live more truly human lives, so to speak. And if any of them did this, they would doubtless prefer those lives (even though they might be less fun) to the lives they are now living. People who live swinish lives feel shame when they come to live more human lives; people who live more human lives do not feel ashamed that they did when they sink into swinishness. These facts give one grounds for thinking that the pig-men are making the sort of error, the sort of cognitive short-fall, that Williams discussed; grounds for thinking that they have overlooked alternative goals, and certainly grounds for thinking that they have never made vivid to themselves what realization of those alternative goals would be like. In short, one cannot really say that they have chosen the worse life; for they never had an adequate conception of the better.

– Hilary Putnam in Reason, Truth, and History (1981)