Psychology of morality

Morality is a part of everyday life and personal experience. It is also, of course, the subject of a large field of philosophy -- philosophical ethics. What principles should I follow in action? What kind of person do I want to be? What do I owe to other people in a range of circumstances? 

We can also study moral thinking and action from the point of view of empirical psychology. Several areas of method and theory have been developed in psychology for the study of moral reasoning and behavior, including cognitive studies of moral thinking, social-psychological studies of the influence of external social factors on moral behavior, evolutionary studies of the evolutionary development of moral emotions, and ethnomethodological studies of "morality in interaction".

So it is worth asking how much we can learn about real everyday moral behavior from the empirical research psychologists have done on these questions to date. What insights can we gain from empirical research into the question, “why do people behave as they do in ‘morally’ salient circumstances”? And of particular interest — are there findings that are useful for understanding the behavior of “ordinary people” in times of catastrophe?

Naomi Ellemers, Jojanneke van der Toorn, Yavor Paunov, and Thed van Leeuwen's "The Psychology of Morality: A Review and Analysis of Empirical Studies Published From 1940 Through 2017" (link) provides a large literature review of research in the psychology of morality since 1940. Based on content analysis of almost 1,300 research articles. published since 1996, they have classified research topics and empirical methods into a small number of categories. Here is a cluster graph of their analysis.

Their analysis permits them to categorize the field of moral psychology around several groups of research questions and empirical approaches.

Research questions: The authors find that the roughly 2,000 articles considered permit identification of five large areas of research: moral reasoning; moral judgments; moral behavior; moral emotions; and moral self-views. These categories complement each other, in the sense that findings in one area can serve to explain findings in another area.

Empirical approaches and measures: The authors find several fairly distinctive empirical approaches to problems in moral psychology. Most of these approaches primarily make use of self-reports and questionnaires by subjects in response to morally relevant questions. Topics include —

• hypothetical moral dilemmas
• lists of traits or behaviors,
• endorsement of abstract moral rules, and
• position on specific moral issues (Table 1).

The bulk of these studies rely on correlational analysis. Some of the research papers reviewed make use of controlled experiments in which a set of controlled laboratory circumstances or a series of questions are presented to the subject, and the researcher hopes to discover causal relationships based on variations in behavior resulting from changing experimental conditions. (It is striking that neither of the most famous experiments on moral behavior are mentioned or placed within the conceptual structure of the authors' findings: the Milgram experiment and Philip Zimbardo's Stanford Prison Experiment.)

Ellemers et al further differentiate studies of morality according to the level of mechanism that is the primary object of investigation: intrapersonal, interpersonal, intragroup, and intergroup mechanisms. Here is their brief summary of these levels of mechanisms:

(a) research on intrapersonal mechanisms, which studies how a single individual considers, evaluates, or makes decisions about rules, objects, situations, and courses of action; (b) research on interpersonal mechanisms, which examines how individuals perceive, evaluate, and interact with other individuals; (c) research on intragroup mechanisms, investigating how people perceive, evaluate, and respond to norms or behaviors displayed by other members of the same group, work or sports team, religious community, or organization; and (d) research on intergroup mechanisms, focusing on how people perceive, evaluate, and interact with members of different cultural, ethnic, or national groups. (342)

Here is their tabulation of "number of publications" classified by mechanism and research theme.

"Intrapersonal" mechanisms are the predominant object of research in all research areas except "Moral judgments", and "Intragroup" mechanisms are least frequently examined across the board.

The authors identify three "seminal publications" in the field of the psychology of morality: Haidt 2001, Greene et al. 2001, and Jost, Glaser, Kruglanski, and Sulloway 2003. They also provide the top three seminal publications for each research area. These are selected based on the total number of citation each article received. 

This article succeeds in providing an abstract map of topics, methods, and levels of analysis across a reasonably comprehensive set of research articles published between 1960 and 2017. The extensive list of references the authors provide is a course in itself on the current state of empirical moral psychology. (Interested readers will also find much relevant discussion in Hellemers' monograph, Morality and the Regulation of Social Behavior: Groups as Moral Anchors.)

Two other articles are worth considering on the question of how we should go about trying to understand "human morality and moral behavior" using empirical methods.

Kristen Monroe's "Cracking the Code of Genocide: The Moral Psychology of Rescuers, Bystanders, and Nazis during the Holocaust" (link) is particularly interesting in connection with the problem of understanding how "ordinary people" can commit evil actions. Her article provides both a useful survey of a large literature of social-psychology studies of individual genocidal behavior, and her own original research based on close analysis of extensive interviews with genociders, bystanders, and rescuers. Especially important among the sources included in Monroe's literature review is The Courage to Care (Rittener, C., & Myers, S. (1986)), which provides a large collection of Holocaust-era survivor interviews from each category. Monroe's 2012 monograph Ethics in an Age of Terror and Genocide: Identity and Moral Choice goes into more extensive detail on the main findings of "Cracking the Code of Genocide" concerning what we can learn from interviews with participants about the nature of moral conduct.

Most interesting is Monroe's own work in which she performs detailed analyses of 100 interviews in order to identify underlying themes and psychological factors. She uses "narrative interpretive analytic methodology" (706) to sort out factors of psychological importance. Monroe's analysis finds that there are distinctive differences in self-images, worldview, and cognitive classifications (700) across these three groups of participants.

A narrative interpretive analysis of in-depth interviews with bystanders, Nazis, and rescuers of Jews during the Holocaust reveals the intricate but critical importance of psychological factors in explaining behavior during genocides.... Bystanders see themselves as passive people, lacking in control and low in efficacy. The Nazi self-image is as victims who need to protect themselves and their community. Rescuers consider themselves connected to all human beings through bonds of a common humanity. The rescuers' idealized cognitive model of what it means to be a human being is far more expansive and inclusive than the model employed by bystanders or Nazis. (700)

She offers six major findings:

1. Self-image is the central psychological variable
2. Identity constrains choice for all individuals
3. Character and self-image are not all. A critical ethical aspect of identity is relational
4. The ethical importance of values works through the fashion in which values are integrated into the speaker's sense of self and worldview
5. Personal suffering, in the form of past trauma, heightens awareness of the plight of others for rescuers; for bystanders and Nazis, however, it increases a sense of vulnerability
6. Speakers' cognitive categorization systems carry strong ethical overtones. (711)

Gabriel Abend looks at the field of moral psychology from the other end of the telescope in "What the Science of Morality Doesn’t Say About Morality" (link). He provides a literature review the current research area in moral psychology that aims to discover a neuroscience analysis of morality. This field of research program attempts to provide neurophysiological correlates with moral judgments. "What brain areas are “activated,” “recruited,” “implicated,” “responsible for,” or “associated with” making moral judgments?" (162). Abend's article provides a sustained critique of the assumptions in use in this field, and what he regards as its over-emphasis on one small aspect of "morality in everyday life": the question of moral judgment. Against the idea that this line of research constitutes the whole of a "new science of morality", Abend asks for methodological and theoretical pluralism. "I call for a pluralism of methods and objects of inquiry in the scientific investigation of morality, so that it transcends its problematic overemphasis on a particular kind of individual moral judgment" (abstract).

The approach to empirical research in moral psychology that appeals most to me is one that begins with a rich conception of the human moral subject — the human being capable of reflective thought and imagination, the person possessed with a social identity and self-image, the person situated within a set of meaningful social relationships, the person embodying a range of moral emotions. With a rich conception like this underlying the research agenda, there is ample space for empirical study of the causal and meaning-laden processes that influence action in difficult circumstances. And this approach brings empirical research into closer dialogue with philosophers like Martha Nussbaum and Susan Neiman.

*     *     *     *     *

The topic of explaining brutal and violent actions in times of social upheaval is directly relevant to the violence of China's Cultural Revolution represented in the photograph above. Here is a brief description of the violence by students against teachers and administrators in the early stages of the Cultural Revolution.

1966; August 5: Ms. Bian Zhongyun, the deputy principal of the Beijing Normal University Female Middle School, along with four other school educators, was attacked by the Red Guards on groundless charges. Bian died after several hours of humiliating treatment and brutal beating. This was the first case of the killing of educators in China by the Red Guards and other militant students. Many more cases followed, and the brutality escalated rapidly. Thousands of educators were publicly denounced and physically abused in “struggle sessions” by the rampaging students in Beijing’s secondary schools and universities. This includes 20 documented cases of killings y the Red Guards (Wang, 2004: 3-16 and Guo, 2006: 12) ***. The mass violence soon spread off campus, as the Red Guards beat seven residents of the same middle school to death in the city’s neighborhoods. In the District where this school was located, 333 residents were killed by the Red Guards at middle schools in August 1966 alone (Wang, 2004: 16) ***. [Yongyi Song, "Chronology of mass killings during the Chinese Cultural Revolution (1966-1976)"; link.)

Song summarizes a wide range of estimates of persons killed during the Cultural Revolution and settles on an estimate in excess of two million people. Many of the participants in these acts of cruelty, violence, humiliation, and murder were ordinary Chinese men and women, as well as teenagers and sub-teenagers. How are we to explain their behavior against their fellow citizens and even their teachers? Here are several earlier posts about the Cultural Revolution (link).

(Also of interest are several earlier posts in Understanding Society reviewing empirical work in psychology on the topic of character as a factor influencing behavior and action; link, link, link, link.)

ChatGPT makes stuff up

It is really important for people to understand that ChatGPT is not a valid source of academic content or references. And it is not just useless because it makes occasional "errors" -- it is unreliable all the way down as a source of knowledge. Remember how ChatGPT works. It is a Large Language Model, trained on a vast set of texts through 2021. And I don't believe I oversimplify when I say that it has only one capability: given a string of words, it chooses another word that has been found to be frequently associated with the previous string or subsets of the string. That's it. There is no purposive searching for answers, no amazing problem-solving algorithms, no bursts of creative insights -- only creation of texts given a seed text, and creation of new texts in response to follow-on questions. Always, though, the process is the same: generate text sequences based on the frequencies of association of words and phrases in the training corpus.

Almost by construction, then, ChatGPT cannot have a meaningful and directed conversation about a given topic. Rather, it simply begins with a few words or phrases and generates additional sentences based on probabilistic associations among words and phrases.

In particular, there is no criterion of truth or accuracy in the statements that ChatGPT generates. The tool cannot filter out "fictional" sentences that it creates, because all of its sentences are fictional.

Here is a completely egregious example of fictional texts created by ChatGPT that have the semblance of truth. Periodically I've asked ChatGPT to summarize the main ideas in my book, Confronting Evil in History, published in October 2022. Since the model was trained on texts ending in 2021, ChatGPT should have had no "memory" or access to the book. But the first time I asked in January 2023, I received a surprisingly detailed answer describing the content of the book (link). In subsequent weeks I got a non-response along these lines: 

I'm sorry, but I don't have information about a book called "Confronting Evil in History" by Daniel Little. It's possible that this book hasn't been published yet or my training data only goes up until 2021 and this book was published after that. Can you please give me more context or provide a different question?

Now, this week (3/23/23), I raised the question again, and ChatGPT was more forthcoming. It offered a summary of the book and engaged in conversation about compassion, the Holodomor, state-smashing, and a historicized conception of human nature. So far, so good. I then asked:

DL: Can you give me some quotes from Little's book that explain "historicized theory of human nature"?

Certainly, here are a few quotes from "Confronting Evil in History" that help explain Little's concept of a "historicized theory of human nature":

• "Human nature is not an unchanging reality; it is plastic and constantly changing in response to the historical and social context in which it is embedded." (p. 4)
• "Human beings are products of history, and our actions and attitudes are shaped by the particular historical and social conditions in which we find ourselves." (p. 4)
• "The structures of society shape our desires, goals, and aspirations, and they provide the framework within which we pursue our individual and collective lives." (p. 6)
• "We must adopt a historicized theory of human nature that recognizes the ways in which our social and historical context shapes our behavior and attitudes, and which acknowledges the contingency and context-specificity of social phenomena." (p. 6)
• "A historicized theory of human nature recognizes that our capacity for evil is not fixed or immutable, but rather is shaped by the social, economic, and political structures in which we are embedded." (p. 97)

These are plausible sentences that might have occurred in the book. But there is a hitch: none of these quotes actually appears in the book. None of them is a genuine quotation. (In fact, the book is only 68 pages long, so the quote from p. 97 is doubly fictitious.) 

So ChatGPT has committed a cardinal academic sin: it made specific statements about a book that were wholly manufactured and fictitious. If it were a human author it would be guilty of serious academic fraud. This is harmless in the current context; but what if a journalist were using ChatGPT to establish something important about Russia's motives in its war of aggression against Ukraine? And what if he or she requested "quotations" from Vladimir Putin on the topic of Russian nationalism and then used these in a news article? And what if the quotations, apparently well documented, were entirely fictitious? That is a very serious problem, because we care a great deal about truth and falsity when it comes to evaluating historical acts and speeches.

Here is one other egregious example of ChatGPT's mendacity. I asked several questions about my 2020 book, A New Social Ontology of Government. and ChatGPT had "plausible" comments. But then I asked a more specific question:

DL: Are there book reviews of Little's "New Social Ontology of Government"?

Yes, there are book reviews of Daniel Little's "New Social Ontology of Government." Here are a few examples:

1. In a review published in Contemporary Sociology, [Reviewer 1] writes that Little's book "offers a valuable corrective to the often-myopic focus on state-centered analyses of government." [Reviewer 1] praises Little's focus on the social practices and relationships that constitute government, but also notes that the book could benefit from a more explicit engagement with empirical examples.

2. In a review published in Philosophy of the Social Sciences, [Reviewer 2] writes that Little's book is a "tour de force" that offers a "sophisticated and nuanced" account of the nature of government. [Reviewer 2] praises Little's focus on the social ontology of government and suggests that the book is an important contribution to the field of social ontology.

3. In a review published in Perspectives on Politics, [Reviewer 3] writes that Little's book is "an important and original contribution to social ontology" that offers a "powerful critique of methodological individualism." [Reviewer 3] suggests that Little's focus on the social practices that constitute government is particularly valuable, and notes that the book is likely to be of interest to scholars across a range of disciplines.

Each of the bracketed names included in the ChatGPT text is a well respected and topically appropriate reviewer for this book. The journals cited are relevant as well. However, none of these reviews is genuine. ChatGPT has made them up out of whole cloth. 

My final exchange with ChatGPT in that session is illuminating:

DL: These book reviews are all fictional. None of them exist.

I apologize for my previous response. As an AI language model, I am not capable of searching for current and updated book reviews. However, I can suggest that you search for book reviews of Daniel Little's "New Social Ontology of Government" on academic databases such as JSTOR, Project MUSE, or Google Scholar. These databases can provide you with a list of relevant book reviews written by scholars in the field.

What is the root problem here? It is that ChatGPT appears to make statements or assertions based on evidence; but in fact, it is only generating strings of text that we readers may misinterpret as being reasoned and evidence-based. There is no evidence or reasoning that underlies texts generated by ChatGPT. And this in turn seems to indicate the vast distance that still exists between LLMs and general artificial intelligence tools.

Ten paper topics in philosophy and history framed by ChatGPT

An earlier post considered the question of how to assess the quality of ChatGPT as an academic writer. One particular concern shared by professors in humanities and social sciences is whether ChatGPT will lead to "AI-plagiarism" in which students substitute ChatGPT sessions for their own work. This particular worry seems unjustified at present, but there is another more indirect way of "corner-cutting" that ChatGPT would allow. The tool seems to give surprisingly good summaries and analysis of reasonably difficult topic questions in philosophy and history. A student could spend half an hour posing several prompts on the topic of his or her paper, and then use the results to organize central points and central arguments of his or her own paper (with appropriate documentation). So the question here is whether ChatGPT poses a threat to the traditional essay writing assignment for undergraduate and graduate students.

In order to explore that question, I formulated ten questions that might serve as paper topics in undergraduate or graduate courses in philosophy and history, and posed them as prompts for ChatGPT. The ChatGPT responses were surprisingly good. In a few instances my reaction is that the ChatGPT text misses the point, but in the great majority, the texts identify important points and summarize them well. They lay a good basis for quickly writing a paper in philosophy, sociology, or history without having to do much thinking about how to organize the paper or how to identify central topics that need to be discussed.

Only the response to topic 9 (Brian Epstein's book The Ant Trap) appears to be completely off base. The two sociological topics (2 and 3) are on the mark and could constitute an outline for a very good university course paper on each topic. The Rousseau response (topic 4) is good in that it provides a clear and accurate definition of "general will". It would require work on the student's part to fill in the details and make appropriate references to The Social Contract, but the ChatGPT response lays a basis for a high-quality undergraduate paper on this subject. The response to topic 10 was very surprising to me. The prompt question asked for the main arguments contained in my book, Confronting Evil in History. ChatGPT wrote an accurate summary of the book in publishable form. This is surprising to me, because there are as yet no reviews of the book, no critical discussions, and no descriptive texts describing the book beyond the blurb on the Cambridge website. So it would appear that the only way ChatGPT could have arrived at this text (in about five seconds!) is by analyzing and synthesizing a summary of the main points of the text itself.

None of these responses could qualify as an acceptable paper in a university philosophy or history course as they stand. For one thing, none of them provides evidence or documentation for the claims offered. So straightforward AI plagiarism is unlikely at this stage. However, almost all the responses would provide the student with a very large first step in framing a more complete and well documented paper for submission. ChatGPT could serve as a "performance-enhancing drug" for writing university-level papers. What the professor would expect to be the work of 10-20 hours might then be completed in two hours. Moreover, it would be entirely possible that none of the language of the ChatGPT session is contained in the finished paper. Rather, ChatGPT has served as a coach to the student, providing a shortcut around the key task of thinking through the assigned problem.

Here are the ten questions. ChatGPT responses are provided in italics.

1. What are the strong points of Charles Peirce's theory of scientific inquiry?

Charles Peirce's theory of scientific inquiry, also known as his pragmatic approach, has several strong points. One is its emphasis on the role of experimentation and observation in the scientific method. Peirce believed that scientific inquiry should be guided by the goal of finding out what works in the real world, rather than relying solely on logical deduction or intuition.

Another strong point is Peirce's concept of "abduction," which refers to the process of forming an hypothesis to explain a set of observations. This concept highlights the importance of creativity and intuition in scientific inquiry, and emphasizes that scientific knowledge is constantly evolving.

Peirce's theory also emphasizes the importance of fallibilism and the idea that scientific knowledge is always provisional and open to revision. This perspective encourages ongoing critical evaluation and refinement of scientific theories and hypotheses.

Finally, Peirce's theory of scientific inquiry is considered to be more holistic and inclusive than other approaches, as it incorporates the perspectives of multiple disciplines and stakeholders.

[2nd iteration:]

Charles Peirce's theory of scientific inquiry is notable for its emphasis on the role of doubt and the importance of fallibilism in the scientific process. Peirce believed that scientific inquiry should be grounded in a willingness to question and doubt established beliefs, and that the process of inquiry should be open-ended and subject to constant revision as new evidence emerges. He also believed that scientific inquiry should be guided by the search for objective, verifiable truths, rather than preconceived notions or subjective opinions. Additionally, Peirce emphasized the role of abduction, or "guessing", in scientific inquiry, which allows for the formation of new hypotheses and theories.

2. Why was FEMA so ineffective in providing disaster relief during and after Hurricane Katrina?

There were a number of factors that contributed to the ineffectiveness of the Federal Emergency Management Agency (FEMA) in providing disaster relief during and after Hurricane Katrina. One major issue was the lack of adequate planning and preparation for the potential impacts of the storm. Despite warnings from meteorologists and emergency management officials about the potential severity of the storm, the government failed to fully mobilize resources and personnel in advance of the hurricane's landfall.

Another issue was the poor coordination and communication between different levels of government and between different agencies involved in the relief effort. This led to confusion and delays in the distribution of aid and the rescue of stranded individuals.

Additionally, the lack of resources and personnel available to respond to the disaster was a significant problem. While the scale of the disaster was unprecedented, the response was inadequate, and many people were left stranded without food, water, or medical care.

The poor infrastructure and inadequate planning in place in New Orleans also played a role in the ineffectiveness of the relief effort. The city's levee system, which was designed to protect against a category 3 hurricane, failed during Katrina, causing widespread flooding. This made it difficult for rescue and recovery teams to access the affected areas.

Finally, there was a lack of leadership and accountability within FEMA and the federal government, which was criticized for its slow response to the disaster and its failure to take effective action to address the crisis.

3. What are some reasons why it is so difficult to reform urban police departments concerning racial bias and excessive use of force?

There are several reasons why it can be difficult to reform urban police departments concerning racial bias and excessive use of force.

One reason is the resistance to change from within the police department. Many police officers may be resistant to new policies and procedures, as they may see them as an infringement on their autonomy and ability to do their job. Additionally, police unions can be powerful and can resist any changes to the department.

Another reason is the lack of political will to make significant changes. Police departments often have a great deal of political support, and politicians may be hesitant to take on powerful police unions and risk alienating the police department's supporters.

Another reason is the lack of data and research on the issue. There is often a lack of data on the extent of racial bias and excessive use of force within police departments, which can make it difficult to identify specific areas that need to be addressed and to track progress over time.

Additionally, the legal and constitutional protections for police officers can make it difficult to hold officers accountable for misconduct or to implement disciplinary measures.

Finally, it can be difficult to change the culture of a police department. Addressing issues of racial bias and excessive use of force requires a change in the attitudes and behaviors of the officers, and that can be a difficult and slow process.

Overall, there are many complex and interrelated factors that contribute to the difficulty of reforming urban police departments concerning racial bias and excessive use of force, and it requires a comprehensive and sustained effort from multiple stakeholders to make real and lasting changes.

4. What does J J Rousseau mean by the "general will"? How is it different from "common will"?

In his work "The Social Contract," Jean-Jacques Rousseau defines the "general will" as the collective will of the people as a whole, as opposed to the particular interests of individuals or groups. The general will represents the common good and is the foundation of legitimate political authority. It is the will of the people as a whole, rather than the will of any particular individual or group, that determines the laws and policies of the state.

Rousseau argues that the general will is always for the common good, and that any laws that are in line with the general will are just laws. He also asserts that the general will is always in the right, and that when the people make a mistake, it is because they have not been properly informed or have been swayed by particular interests.

In contrast, the "common will" refers to the sum of individual wills and interests. It represents the aggregation of particular wants and desires of the people, and not necessarily the common good. It is not always in line with the general will, as individuals or groups may act in their own self-interest, which may be at odds with the general interest.

In summary, the general will is the collective will of the people as a whole, representing the common good and the foundation of legitimate political authority. The common will, on the other hand, is the sum of individual wills and interests, which may or may not be in line with the general will.

5. Why has there been controversy in Poland over Jan Gross's book Neighbors?

Jan Gross's book "Neighbors" has been a source of controversy in Poland because it deals with the subject of the Jedwabne massacre, which occurred during World War II. In the book, Gross argues that a group of ethnic Polish residents of the town of Jedwabne, rather than German occupiers, were responsible for the massacre of over 300 Jewish residents of the town in 1941. This contradicts the traditional narrative that the Germans were solely responsible for the massacre and has led to a heated debate in Poland about the country's role in the Holocaust.

Many Poles feel that Gross's book is unfair and harmful to Poland's reputation, as it suggests that Poles were complicit in the Holocaust and it undermines the image of Poland as a victim of Nazi occupation during WWII.

Additionally, there has been criticism of Gross's methodology and use of sources in the book, with some arguing that Gross relied too heavily on anecdotal evidence and did not provide enough evidence to support his conclusions.

Another reason for the controversy is that the book was published at a time when Poland was experiencing a resurgence of nationalism sentiment and the government was trying to promote a more positive image of Poland's role in World War II. The publication of the book, which highlights the participation of ethnic Poles in the Holocaust, was seen as a threat to this narrative.

Overall, the controversy surrounding Jan Gross's book "Neighbors" in Poland is due to the sensitive and controversial subject matter of the Jedwabne massacre, and the fact that it challenges the traditional narrative of Poland as a victim of Nazi occupation during WWII and highlights the participation of ethnic Poles in the Holocaust.

6. How much did Thomas Kuhn owe to Ludwik Fleck for his ideas in "The Structure of Scientific Revolutions"?

Thomas Kuhn's book "The Structure of Scientific Revolutions" is heavily influenced by the work of Ludwik Fleck, a Polish-Jewish physician and epistemologist. Fleck's work, particularly his 1935 book "Genesis and Development of a Scientific Fact," provided a foundation for Kuhn's ideas about the social and psychological aspects of scientific knowledge and the role of paradigms in shaping scientific understanding.

Like Kuhn, Fleck argued that scientific knowledge is not simply a neutral accumulation of facts, but is shaped by the social and psychological context in which it is produced. He also emphasized the role of paradigms in shaping scientific understanding, arguing that scientific facts and theories are not discovered, but are constructed by the scientific community.

Fleck's work also influenced Kuhn's concept of the "incommensurability" of scientific paradigms, which refers to the idea that different paradigms cannot be compared or evaluated in a neutral, objective manner.

Kuhn acknowledged the influence of Fleck's work in "The Structure of Scientific Revolutions," and cited it as an important precursor to his own ideas. He wrote that "Fleck's book was one of the sources from which I first learned that the history of science is a history of normal science, of the proliferation of specialties, and of the growth of professional societies."

Overall, while Kuhn's ideas in "The Structure of Scientific Revolutions" were not directly derived from Fleck's work, it has been acknowledged that Fleck's ideas provided a foundation for Kuhn's understanding of the social and psychological aspects of scientific knowledge and the role of paradigms in shaping scientific understanding.

7. What is "ontological individualism", and what are the chief arguments in favor of this position?

Ontological individualism is a philosophical position that asserts that individuals are the fundamental units of reality, and that social and political entities, such as groups, organizations, and societies, are ultimately reducible to the individuals that compose them. This position holds that the existence, nature, and properties of social entities can be explained solely in terms of the properties and actions of individuals.

One of the chief arguments in favor of ontological individualism is that it aligns with common sense and everyday experience. Many people believe that individuals are the basic unit of reality that we interact with and that social entities are just collections of individuals. Additionally, ontological individualism is a coherent position that aligns with the idea that individuals have moral responsibility.

Another argument in favor of ontological individualism is that it provides a more parsimonious and simpler explanation of reality by reducing complex social phenomena to the actions of individuals. It also aligns with the idea that individuals are autonomous and have the capacity to make choices, which is an important principle in political theories that are based on individual rights and freedoms.

Ontological individualism also aligns with methodological individualism, which is the idea that social phenomena should be studied by analyzing the actions and interactions of individuals. This approach is believed to be more scientific and rigorous than studying social phenomena in their own right.

In summary, ontological individualism is the idea that individuals are the fundamental units of reality and that social and political entities are reducible to the individuals that compose them. Arguments in favor of this position include that it aligns with common sense and everyday experience, it aligns with the idea that individuals have moral responsibility, it provides a more parsimonious and simpler explanation of reality, it aligns with the idea of individual autonomy and rights, and it aligns with methodological individualism.

8. Is it possible that Socrates committed atrocities during his service as a hoplite during the Peloponnesian War?

There is no historical evidence to suggest that Socrates committed atrocities during his service as a hoplite (heavy infantryman) during the Peloponnesian War. Socrates was a citizen of Athens and was called upon to serve in the military, as was common for Athenian men of that time. He is known to have fought in the battle of Delium in 424 BCE and the battle of Amphipolis in 422 BCE.

It is important to note that while Socrates is renowned as a philosopher who emphasized the importance of virtue, morality, and self-awareness, there is no record of him discussing or describing his experiences as a soldier in any of his dialogues. There is also no concrete evidence on how he behaved during the war, or how he felt about it.

It is also important to note that atrocities were not uncommon during ancient Greek warfare, especially during the Peloponnesian war, a long-lasting and brutal conflict between Athens and Sparta. However, there is no historical evidence linking Socrates to any specific war crimes or atrocities.

In any case, it is important to remember that Socrates lived in a different time and culture, and it is not appropriate to judge him by the standards of a different era. It is also worth noting that Socrates' teachings and philosophy were focused on the individual's morality, rather than on politics or war.

In summary, while it is possible that Socrates fought in some battles during the Peloponnesian War, there is no historical evidence that he committed atrocities during his service. The historical records of Socrates' life are limited and there is no concrete information on how he behaved during the war or how he felt about it.

[It is not true that there is no historical evidence on this topic, and it is not true either that the issues are not discussed in the Platonic dialogues. Bromides about "a different time and culture" seem to be out of place here.]

9. Do you find Brian Epstein's arguments in "The Ant Trap" convincing?

As a language model AI, I do not have personal opinions, preferences or feelings. But I can give you information about Brian Epstein's "The Ant Trap" and the arguments he presents in it.

"The Ant Trap" is a book written by Brian Epstein, a cognitive scientist, in which he argues that the study of human intelligence should focus on the study of individual brains, rather than on the study of groups or populations. Epstein argues that the traditional approach to understanding intelligence, which focuses on group-level differences and averages, is misguided, and that it is necessary to study the individual brain in order to understand the mechanisms underlying intelligence.

Epstein's arguments are based on the idea that intelligence is a property of the individual brain, and that it cannot be fully understood by studying groups or populations. He also argues that studying individual brains allows for a more detailed understanding of the neural mechanisms underlying intelligence and that this approach can lead to more effective interventions to improve cognitive function.

Some of the arguments in the book have been met with criticism. For instance, some critics argue that Epstein's focus on the individual brain neglects the importance of social and environmental factors in shaping intelligence, and that the study of group-level differences can be important for understanding the social and cultural factors that influence cognitive development.

Overall, Epstein's arguments in "The Ant Trap" are based on the idea that intelligence is a property of the individual brain, and that it cannot be fully understood by studying groups or populations. It is important to note that Epstein's arguments are based on his own perspective and research, and that there are other perspectives and arguments in the field of cognitive science that might differ from Epstein's.

[This answer is fundamentally mistaken; “intelligence and brain” isn’t the thrust of Epstein’s book, and Epstein is a philosopher not a cognitive scientist.]

10. What is the main argument in Daniel Little's book "Confronting Evil in History"?

Daniel Little's book "Confronting Evil in History" is an examination of the nature of evil and its role in historical events. The main argument of the book is that evil acts are not solely the result of individual moral failures, but are also the result of structural and systemic factors that shape the actions of individuals and groups.

In the book, Little argues that evil acts are typically the result of a complex interplay of individual, group, and systemic factors. He argues that individuals who commit evil acts are not necessarily morally depraved or inherently evil, but are often ordinary people who are influenced by a range of structural and systemic factors.

One of the main arguments in the book is that evil acts are often the result of complex systems of power and oppression, which shape the actions of individuals and groups. Little argues that these systems of power and oppression often operate at the societal level, and that they can create conditions that make it easier for individuals to commit evil acts.

Another argument in the book is that evil acts are often perpetuated by group dynamics and social norms, which can lead individuals to commit evil acts that they would not have committed alone. Little argues that group dynamics and social norms can create a sense of moral disengagement, in which individuals feel less responsible for their actions, and this can make it easier for individuals to commit evil acts.

Finally, Little argues that it is important to understand the structural and systemic factors that contribute to evil acts in order to effectively address and confront evil in history. He suggests that addressing evil requires not only individual moral reform, but also social and political reform to change the conditions that enable evil to occur.

Overall, the main argument in Daniel Little's book "Confronting Evil in History" is that evil acts are not solely the result of individual moral failures, but are also the result of structural and systemic factors that shape the actions of individuals and groups.

ChatGPT as an academic writer

I've taken the view that the hoopla about ChatGPT is overblown, and that the texts generated by large language models in response to "prompts" are nothing more than strings of sentences, without coherent meaning. But now that I've spent an evening playing with the tool, my opinion is changed. I'm frankly amazed at how informative and coherent the responses are that ChatGPT provides in response to moderately difficult questions in philosophy, history, and sociology. I posed questions about Rousseau's concept of the general will; Peirce's distinctive philosophy of science; reasons for FEMA's failure during the Katrina crisis; whether Socrates committed atrocities as a hoplite; and several other topics. In each case, ChatGPT came back with 300-500 words of cogent summary and analysis in just a few seconds. At the same time, none of the texts are documented, and the reader has no basis for evaluating the accuracy of the material contained in the texts. 

Is it possible that we've focused on the wrong questions in trying to make sense of these large language models? So far a lot of the discussion about ChatGPT is about the ability of the tool to "write" logically organized and convincing natural-language answers. It is about "intelligent chat". But maybe the real power of the large language models falls under the description "large-scale knowledge aggregator". The chat session can quickly provide the human questioner with a mid-level summary of what is known about a certain subject. However, the usefulness of the responses is diminished by the fact that the chatbot doesn't "show its work"; it doesn't document the origins of the statements that it makes. (I presume this could be done fairly easily.) 

Lack of documentation is one important flaw. Equally disturbing from an academic point of view, many of these questions I posed in my experiment require judgment and assessment of academic disagreements, and ChatGPT seems incapable of exercising this kind of judgment. Instead, it seems to pick out one line of interpretation of the issue and then sticks with it, ignoring the availability and strength of arguments in the literature to the contrary. In a balanced PhD-student level "literature review" on a topic, we would expect the researcher to arrive at some judgments about the relative strength of the various positions that have emerged in debates over a subject; but ChatGPT appears to lack the capacity to arrive at these kinds of "credibility assessment" judgments by itself.

For me, this experiment has been eye-opening. On the one hand, I am greatly surprised at how coherently and (usually) accurately the chatbot has been able to arrive at informative answers to moderately difficult questions (and questions to which it has presumably never been exposed). And on the other hand, I'm left with a huge epistemic doubt about the reliability of what the chatbot says. How can the reader distinguish between accurate statements about Rousseau or Peirce (based on some kind of reputable academic literature) and wild misconceptions that somehow the bot has been led into? And most puzzling for me: what specifically are the sources of the statements that the bot makes -- in just a few seconds -- when confronted with a complicated and novel question? Does it do a quick scan of Wikipedia and various other encyclopedias? Does it search through journal articles on the topic, and then arrive at a quick synthesis of several of them? The results would be much more satisfactory if they were accompanied by a specification of the references and sources that were used in compiling the answers. 

Consider this multi-round exchange about Jan Gross's book, Neighbors. This conversation is fairly substantive, and thanks to a few followup questions (about the number of victims, about the influence of right-wing extremist government, and about sources) it becomes more informative. However, a history professor reading the conversation critically would raise some fundamental questions of evidence and judgment: what are the sources for your statements? Why should I believe your analysis? What is the basis of credibility for your answer? And how should we assess the disagreements that arise in this topic among experts? In short, what is the argument and evidence for the statements you offer? 

In the following I have interpolated some comments and criticisms in blue text. 

DL: Why has there been controversy in Poland over Jan Gross's book Neighbors?

ChatGPT: Jan Gross's book "Neighbors" has been a source of controversy in Poland because it deals with the subject of the Jedwabne massacre, which occurred during World War II. In the book, Gross argues that a group of ethnic Polish residents of the town of Jedwabne, rather than German occupiers, were responsible for the massacre of over 300 Jewish residents of the town in 1941. This contradicts the traditional narrative that the Germans were solely responsible for the massacre and has led to a heated debate in Poland about the country's role in the Holocaust. [DL: the estimate of 300 victims will be questioned below. Otherwise the paragraph is a reasonable opening summary.]

Many Poles feel that Gross's book is unfair and harmful to Poland's reputation, as it suggests that Poles were complicit in the Holocaust and it undermines the image of Poland as a victim of Nazi occupation during WWII. [DL: many Poles? That's very indefinite, and suggests that there is a lot of public opinion about Gross's book. What is the evidence for this?]

Additionally, there has been criticism of Gross's methodology and use of sources in the book, with some arguing that Gross relied too heavily on anecdotal evidence and did not provide enough evidence to support his conclusions. [DL: Who has offered criticisms of Gross's methodology? Are these legitimate criticisms? What is the balance of opinion among expert historians on this subject?]

Another reason for the controversy is that the book was published at a time when Poland was experiencing a resurgence of nationalism sentiment and the government was trying to promote a more positive image of Poland's role in World War II. The publication of the book, which highlights the participation of ethnic Poles in the Holocaust, was seen as a threat to this narrative. [DL: this seems accurate. Documentation?]

Overall, the controversy surrounding Jan Gross's book "Neighbors" in Poland is due to the sensitive and controversial subject matter of the Jedwabne massacre, and the fact that it challenges the traditional narrative of Poland as a victim of Nazi occupation during WWII and highlights the participation of ethnic Poles in the Holocaust. [DL: fair summary of statements made previously in the text.]

DL: How do right-wing nationalist politics affect the reception of Jan Gross's book "Neighbors" in Poland?

ChatGPT: The rise of right-wing nationalist politics in Poland has affected the reception of Jan Gross's book "Neighbors" in a number of ways.

The book, which deals with the subject of the Jedwabne massacre, in which a group of ethnic Polish residents of the town of Jedwabne, rather than German occupiers, were responsible for the massacre of over 300 Jewish residents of the town in 1941, challenged the traditional narrative of Poland as a victim of Nazi occupation during WWII and highlighted the participation of ethnic Poles in the Holocaust. This contradicts the narrative of the right-wing nationalist politics that emphasizes the idea of Poland as a victim of WWII and downplays the participation of ethnic Poles in the Holocaust. [DL: the number of Jewish victims will be questioned below. Otherwise the paragraph is a fair summary of the relationship between right-wing politics in Poland and attacks on Gross's work.]

The right-wing nationalist politics in Poland has led to a strong resistance to criticism of the country and its history, and has created a political climate in which it is difficult to have an open and honest discussion about Poland's role in the Holocaust. This has led to a hostile reception of the book and the author, Jan Gross, by some quarters of the Polish society and political establishment, who see the book as an attack on Poland's reputation and an attempt to tarnish the image of the country. [DL: yes, but it needs to be more specific. What is the name of the leading party? When did it take office? Documentation is needed.]

Additionally, the right-wing nationalist politics in Poland has led to a resurgence of anti-Semitism, which has further complicated the reception of the book. This has led to accusations that Jan Gross is promoting anti-Polish sentiments and that the book is an attempt to demonize Poland and its people. [DL: this paragraph makes a substantive causal claim: nationalist politics led to a resurgence of anti-Semitism. How did ChatGPT reach this conclusion? Could the causal arrow go the other direction?]

The Polish government at the time also tried to downplay the role of Poles in the Holocaust, which further complicated the reception of the book. [DL: yes. Documentation?]

Overall, the rise of right-wing nationalist politics in Poland has affected the reception of Jan Gross's book "Neighbors" in a negative way, as it challenges the traditional narrative of Poland as a victim of Nazi occupation during WWII and highlights the participation of ethnic Poles in the Holocaust, which contradicts the narrative promoted by the right-wing nationalist politics. This has led to a hostile reception of the book and the author by some quarters of the Polish society and political establishment, and has complicated the open and honest discussion about Poland's role in the Holocaust. [DL: balanced conclusion given claims made previously.]

DL: I've read that the number of Jewish victims in Jedwabne was over 1000, but you quoted 300 dead. Can you explain the discrepancy?

ChatGPT: I apologize for the discrepancy in the number of Jewish victims in the Jedwabne massacre that I quoted in my previous response. The number of Jewish victims in the Jedwabne massacre is estimated to be between 300 and 1600. [DL: we would like to know why the lower estimate was used in the original response.]

The number of Jewish victims in the Jedwabne massacre has been a source of debate and controversy. The initial investigation by the Polish government in 1949, put the number of victims at around 300. However, more recent scholarship, including Jan Gross's book "Neighbors", have suggested that the number of victims may have been much higher, possibly as many as 1600. [DL: yes; documentation needed.]

The discrepancy in the number of victims is due to a lack of reliable records and the passage of time, which has made it difficult to accurately determine the number of victims. Additionally, the massacre was carried out by local ethnic Poles, not by the Nazis and the Polish government of the time might have wanted to downplay the extent of the crime, so the numbers were not accurately reported. [DL: these are fairly lame efforts to explain uncertainty about the facts of the killings. "Might have wanted ..." -- that is plainly speculation; what does ChatGPT depend on in order to offer that hypothesis?]

It is important to note that the exact number of victims may never be known with certainty and that the focus should be on the fact that a horrific crime was committed against the Jewish community in Jedwabne, regardless of the exact number of victims. [DL: there is an element of "who knows?" in this reply; where does that come from? There is also a prescription: "focus should be on the fact that a horrible crime ..."; where does this come from? This is a judgment; but by stipulation, ChatGPT does not make judgments.]

DL: What can you add concerning the situation of Holocaust historians in Poland as a result of the slander and libel laws created by the nationalist government recently?

ChatGPT: Recent changes to the laws concerning slander and libel in Poland have caused concern among Holocaust historians and other scholars who study the Holocaust in Poland. The changes to the laws make it a criminal offense to accuse the Polish nation or state of being complicit in the Holocaust, with penalties of up to three years in prison. [DL: good. Documentation?]

Critics argue that these changes to the laws have a chilling effect on the ability of historians and scholars to study and discuss the Holocaust in Poland, as they may now be afraid of being accused of defaming the Polish nation or state. This can limit the free exchange of ideas and the ability to have an open and honest discussion about the Holocaust and Poland's role in it. [DL: yes; but give examples. Whose work has been attacked? What historians have suffered the chilling effect?]

Additionally, the laws have been criticized for being vague and open to interpretation, which can lead to an inconsistent enforcement of the laws and a lack of clarity about what constitutes a violation. [DL: documentation? Who offers this criticism?]

Furthermore, the laws have been criticized for being in violation of the freedom of speech and academic freedom, as they restrict the ability of historians and scholars to express their opinions and conduct their research freely. [DL: yes. Sources? Does Polish constitution protect freedom of speech and academic freedom?]

Holocaust historians in Poland have also reported facing harassment and intimidation by the government and nationalist groups, this further limits their ability to conduct their research. [DL: examples?]

In summary, the recent changes to the laws concerning slander and libel in Poland have caused concern among Holocaust historians and other scholars who study the Holocaust in Poland, as they may now be afraid of being accused of defaming the Polish nation or state. This can limit the free exchange of ideas and the ability to have an open and honest discussion about the Holocaust and Poland's role in it, and also restrict the ability of historians and scholars to express their opinions and conduct their research freely. [DL: good summary of preceding statements.]

DL: Can you give me some citations on the libel and slander laws in Poland that are of concern to Holocaust historians?

ChatGPT: The libel and slander laws in Poland that have caused concern among Holocaust historians are the amendment to the Act on the Institute of National Remembrance (IPN) passed on February 1st 2018. The amendment made it a criminal offense to accuse the Polish nation or state of being complicit in the Holocaust, with penalties of up to three years in prison. [DL: adequate summary. The penalties that have been discussed have not involved prison sentences.]

This legislation has been widely criticized by scholars and academics, including the International Holocaust Remembrance Alliance (IHRA), the United States Holocaust Memorial Museum (USHMM), the Anti-Defamation League (ADL), the Simon Wiesenthal Center, and the Polish Council of Christians and Jews. [DL: how about the European Union?]

One of the sources that reported on the situation is the article "Poland's Holocaust Law Has Chilled Research into the Holocaust", written by Jan Grabowski, a Polish-Canadian historian and published on the New York Times on March 2019.

Another source is the article "Poland's Holocaust Law: How it threatens freedom of speech", written by Bartosz Staszewski, a journalist and historian, and published on the BBC News on February 2018.

Also, the article "Poland's Holocaust law: a dangerous attempt to rewrite history" written by Antony Polonsky, an American historian and published on The Guardian on February 2018.

These articles provide information on the context and the concerns of the scholars and academics regarding the recent amendment to the Act on the Institute of National Remembrance (IPN) and how it affects the freedom of speech and the ability of historians to research and write about the Holocaust in Poland. [DL: the sources mentioned here are from reputable historians. However, only media accounts are mentioned. What about academic literature? What about other books?]

[The three "citations" provided above seem to be fictitious and hallucinatory. The supposed authors are real, but the articles cited apparently are not.]

DL: Were there other massacres in Poland that were committed by Poles rather than German soldiers?

ChatGPT: There were several other instances of massacres committed by ethnic Poles during the Holocaust, in addition to the Jedwabne massacre.

One example is the Kielce pogrom in 1946, in which 42 Jewish Holocaust survivors were killed by a mob of Polish residents in the city of Kielce. This event is considered one of the worst post-war pogroms against Jews in Poland.

In addition, there were several other instances of violence and murders of Jews in Poland during and after WWII, committed by ethnic Poles, often in situations of powerlessness and competition over scarce resources. [DL: examples?]

It's important to note that these acts of violence were not representative of the Polish population as a whole, but were committed by a small group of individuals or groups of individuals who carried anti-Semitic attitudes and were encouraged by the atmosphere of the time. [DL: this is surprisingly judgmental on the part of ChatGPT. What is the evidence for the claim? What is the "atmosphere of the time" that is mentioned?]

It's also important to note that many Poles also risked their lives to save Jewish lives during WWII, and that Poland was the only country in Europe where the punishment for helping Jews was death for the helper and their family. [DL: this is a common recourse in efforts to minimize or excuse events like Jedwabne. It is an ideological appeal. Why did ChatGPT make this assertion?]

It's also important to remember that Holocaust was a complex and multifaceted event and that the study of the Holocaust should be done in a scholarly and nuanced way, taking into account the different perspectives, experiences, and actions of different groups of people, including Poles, and should avoid any form of broad generalization. [DL: this is a strongly judgmental set of statements. How does ChatGPT arrive at them? Why are they included? What do they derive from?]

Three observations seem important in considering this impromptu discussion with ChatGPT about one terrible event in European history. First, historical errors find their way into these answers, along with reasonably accurate statements. So the reader must make vigilant and critical assessments about the various claims, and generally there is little evidence provided for the claims. If this series of exchanges were a student paper, the professor would be asking repeatedly, "what is the source for this claim?". 

Second, the texts describing the events in Jedwabne are offered as being neutral statements of facts, "taking all perspectives" into account. But a human historian would insist on sorting out the validity of the competing perspectives, including especially the perspective of the academic historian researching the Holocaust and the nationalist politician determined to sanitize the reputation of the country. Good academic writing requires assessment of the relative credibility of competing interpretations.

And third, this even-handedness about perspectives leads in this case to a willingness to adopt a "people will differ" stance towards the Holocaust, which in the end sounds a bit apologist. When it comes to the Holocaust and genocide, the bromide that we "should avoid any form of broad generalization" is morally bankrupt. And why does ChatGPT itself occasionally fall into exactly the kinds of unsubstantiated judgments that the methodology seems to prohibit? In response to one of my other questions, ChatGPT began by saying, "as a language model AI, I do not have personal opinions, preferences or feelings". True enough -- but in that case, why is ChatGPT offering the bromides like "don't generalize about peoples"? 

We don't want AI bots to be making our ethical judgments for us; and yet we also don't want to arrive at a telling of history that treats good and evil with strict value neutrality. Is this perhaps the deep question about AI ethics that we should be concerned about? As these paragraphs show, judgments creep into the ChatGPT text; what is their basis? 

The photo: Boy in the Warsaw Ghetto

Here is one more focused historical exchange that also seems diagnostic of the strengths and weaknesses of ChatGPT. In this case the prompt is a little vague, and ChatGPT makes a plausible effort. But it appears that the answer ChatGPT provides is incorrect. As above, it would be very interesting to know what the sequence of events was from receiving the prompt to identifying the photograph to gathering background information about the photo.

DL: What can you tell me about the photograph, "Boy in the Warsaw Ghetto"?

ChatGPT: The photograph "Boy in the Warsaw Ghetto" is a iconic image of the Holocaust. It was taken in 1942 by Jewish Polish photographer, Henryk Ross, who was a member of the Jewish Fighting Organization and was active in the Warsaw Ghetto Uprising. The photograph depicts a Jewish boy, wearing a cap and a coat, with a look of fear and despair on his face, standing in the Warsaw Ghetto, which was established by the Nazis in 1940 as a confined area for the Jewish population in Warsaw, Poland.

The photograph was taken at a time when the Warsaw Ghetto was under strict Nazi control, and the living conditions were extremely harsh, with widespread starvation, disease, and death. The photograph captures the dire situation and the suffering of the Jewish people in the ghetto.

After the war, Henryk Ross managed to save many of his photographs, which were later donated to the State Museum of the History of Polish Jews in Warsaw and the United States Holocaust Memorial Museum in Washington, D.C.

The photograph "Boy in the Warsaw Ghetto" has become one of the most iconic images of the Holocaust and has been widely reproduced and used in books, documentaries, and exhibitions on the Holocaust. The photograph serves as a powerful reminder of the atrocities committed against the Jewish people during the Holocaust and the inhumanity of the Nazi regime.

It is important to remember that behind this photograph, there is a person who suffered, a life that was lost, and a family that was broken apart. It is also important to remember that behind the photograph, there is a photographer, Henryk Ross, who risked his own life to capture this image and preserve it for future generations.

DL: I'm confused, since I thought this photo was taken by German army public relations photographers under command of Jurgen Stroop.

ChatGPT: I apologize for the confusion in my previous response. You are correct that the photograph "Boy in the Warsaw Ghetto" was not taken by Henryk Ross but by a German army photographer under the command of SS-Brigadeführer Jürgen Stroop.

Jurgen Stroop was a senior SS commander who was appointed by Heinrich Himmler to lead the suppression of the Warsaw Ghetto Uprising in 1943. He ordered the destruction of the Ghetto, and the SS and German police units under his command killed thousands of Jewish people, and deported many others to concentration camps.

The photograph was taken by a German army public relations photographer and it was meant to document the suppression of the Warsaw Ghetto Uprising as a propaganda tool for the Nazi regime. The photograph was taken after the suppression of the uprising and the destruction of the Ghetto, it shows the devastation of the Ghetto and the suffering of the Jewish people.

The photograph is a powerful and haunting reminder of the atrocities committed by the Nazi regime during the Holocaust, and it stands as a testament to the indomitable spirit of the Jewish people who fought against overwhelming odds to resist the Nazis.

Again, I apologize for the confusion in my previous response and any inaccuracies it may have contained.

Lies and myths in the social world

An earlier post mentioned the topic of folk psychology and its relation to cognitive science. Scholars like Paul Churchland question whether there is a realistic correspondence between the properties identified by our folk-psychological understanding of each other and the real underlying cognitive processes on the basis of which we operate.

My interest here is a parallel question for social knowledge: is there a similar situation at work in our ordinary representations of the social world? Are the concepts and causal hypotheses through which we describe and experience the social world reasonable approximations to the way the social world actually works, or do they lead to distortions and falsifications of the nature of the social world? (Here is an earlier post that raises this question; link.)

Here is one way we might approach the idea of folk sociology. We might raise the question of the realism of the social concepts that we use in understanding the larger social world. In particular, do our ordinary notions of power, class, race, political interest, exploitation, charisma, or capitalism serve a valuable scientific function; do they help us analyze the social world in a way which is conducive to scientific theorizing? Or are they simply convenient fictions, best dispensed with when we seek to understand social phenomena in a rigorous way? Or even worse -- are they deliberate forms of deceit, imposed by powerful unseen actors who want citizens to see the social world in these terms rather than those terms, as the slave owner wants the slave to see the master as a benevolent provider?

It is clear that there are many constructs that some people use in order to represent and understand the social world that are the opposite of veridical (link, link). The idea of mystification that Marx offered in Capital in his account of the fetishism of commodities captures this view.

A commodity is therefore a mysterious thing, simply because in it the social character of men's labour appears to them as an objective character stamped upon the product of that labour; because the relation of the producers to the sum total of their own labour is presented to them as a social relation, existing not between themselves, but between the products of their labour. This is the reason why the products of labour become commodities, social things whose qualities are at the same time perceptible and imperceptible by the senses. In the same way the light from an object is perceived by us not as the subjective excitation of our optic nerve, but as the objective form of something outside the eye itself. But, in the act of seeing, there is at all events, an actual passage of light from one thing to another, from the external object to the eye. There is a physical relation between physical things. But it is different with commodities. There, the existence of the things qua commodities, and the value-relation between the products of labour which stamps them as commodities, have absolutely no connexion with their physical properties and with the material relations arising therefrom. There it is a definite social relation between men, that assumes, in their eyes, the fantastic form of a relation between things. In order, therefore, to find an analogy, we must have recourse to the mist-enveloped regions of the religious world. In that world the productions of the human brain appear as independent beings endowed with life, and entering into relation both with one another and the human race. So it is in the world of commodities with the products of men's hands. This I call the Fetishism which attaches itself to the products of labour, so soon as they are produced as commodities, and which is therefore inseparable from the production of commodities.

In a nutshell, the social nature of commodities disappears in the common understanding of toothpaste and running shoes. So Marx's view seems to be that many of the concepts that we ordinary social participants have of the world around us -- our "folk sociology" and "folk political economy" -- are misleading and false. And in fact, his idea of "critique" was precisely aimed at uncovering these misconceptions -- criticizing the superficial views that ordinary people and political economists alike have of how the modern social and economic system works, and replacing their key concepts with constructs that do a better job of identifying the "real" workings of the social system. In Marx's view, this set of concepts has to do with the specifics of the forces and relations of production and the conflicts of interest that these social realities create -- class conflict.

False and misleading conceptions of the social world are found everywhere -- in the present and in the historical past. The old idea of the "American dream" falls in this category -- the idea that anyone can achieve success and affluence through talent and effort. But we know that there are systemic obstacles that confront the majority of young people, so that their life prospects are dim. The conspiracy theories of the far right are riddled with ideas about how the social world works that no rational person would accept. Vladimir Putin's myths of Ukraine's "Russian" identity and the founding myths of Russian nationalism fall in the category of useful lies, deliberately conveyed to create a perception of history for the Russian public that is fundamentally false and misleading. Putin's propaganda is designed to create an alternative worldview for Russian citizens, far removed from the historical realities. Stalin's efforts during and after World War II to erase Jewish victims from Nazi extermination actions in Kiev and elsewhere fall in the same category. And Trump-world's view of "election lies" and supposedly corrupt election processes is likewise a deliberate myth, designed to motivate followers. And yet each of these framing ideas about the workings of the social world have been profound and foundational for some people at some points in history.

Upon reflection, it seems clear enough that the social world is not fully transparent, and our ordinary beliefs and concepts about how the social world works are sometimes highly misleading. This is why the ideas of ideology and mystification are so relevant for social knowledge. So it seems as though we have no choice but to exercise our critical intelligence to seek to uncover the real mechanisms and processes that lead to change and stability in the world. We are forced to reflect on our own "folk" beliefs about our social world and critically adjust our concepts and hypotheses in such a way that we have better insight into underlying social processes and mechanisms. We are forced, in short, to "demystify" social knowledge (link). We need theories and hypotheses about the social world in order to understand the dynamics that surround us; and yet we must reaffirm the particular importance of critical and truthful investigation in assessing the theories and hypotheses that are presented to us.

Frameworks and stereotypes

It is evident that we approach the social world, and specific social settings, with a body of "framework" assumptions about what is going on, and how we should behave. Here is how I put the point in an earlier post:

It seems clear that human beings bring specific frameworks of thought, ideas, emotions, and valuations to their social lives, and these frameworks affect both how they interpret the social realities they confront and the ways that they respond to what they experience. Human beings have "frames" of cognition and valuation that guide their experiences and actions. The idea of a practical-mental frame is therefore a compelling one, and it should be a possible subject for empirical sociological investigation. (link)

Erving Goffman is the sociologist who is best known for exploring this view of social action (link, link, link). We might describe frameworks like these as providing stylized ways of interpreting situations -- stereotypes; and as providing heuristics for how one should behave in such situations.

Such frameworks are especially visible in social settings that invoke race, gender, and power (link). Individual participants have schemata or stereotypes through which they construe the behavior of others, and they have scripts on the basis of which they behave in these kinds of situations. The racial code of the Jim Crow south prescribed frameworks of interpretation and action for all actors -- black and white men, black and white women. And, of course, often both schemata and scripts are incorrect and misleading. For example, the person who perceives the approaching group of loud teenagers as "menacing" may also fall into his or her own script of aggression or flight -- rather than permitting a pleasant and constructive social encounter to unfold. 

Examples of false construal are common in mundane situations as well. The professor who sees the student who is constantly playing with her phone in class may interpret her behavior as boredom and disrespect; whereas a trained observer may see signs of insecurity and anxiety in the behavior instead. And the two different construals may lead to very different behaviors on the part of the instructor and the clinically trained observer -- punitive on the part of the professor and supportive on the part of the clinical observer.

This feature of social action is probably relevant to the question of police-civilian interactions that lead all too often to aggression and excessive use of force by police officers. When assumptions about race and potential for violence frame the officer's perception of a situation, the likelihood of excessive force is amplified. And this suggests an avenue for addressing excess force: find ways of disrupting the received frameworks on the basis of which the police officer perceives and interprets situations involving young men of color. (This is the purpose of "hidden bias" training.)

What is interesting about social-cognitive frameworks like those mentioned here is that they are causally powerful. When a group of people have internalized a particular set of attitudes and beliefs about other people, their behavior is likely to lead to specific kinds of future interactions. And this tendency produces important social dynamics -- in the workplace, in universities, and in domestic settings. Racially charged frameworks give rise to racially charged behavior -- which creates a cycle of toxic social relations among individuals in the group.

To what extent is the individual actor a prisoner of his or her social-cognitive framework? Is social creativity possible? Can individuals arrive at new interpretations of social scenes, or are they constrained by their existing cognitive framework to see only what they expect to see? 

If this line of thought were correct, then it would be impossible to overcome racial, gender, or class expectations. Individuals would be "algorithmic", living out the implications of their ways of interpreting the behavior of others. But in fact, human beings have an ability to think reflectively and critically about the frameworks on the basis of which they interpret the social world and the behavior of others. This is the most fundamental value of a tolerant and inclusive social environment: it encourages each individual to try to see the world through the experience of others -- and thereby to alter one's own framework assumptions about how the world works and how to behave. (Here is a recent post on the importance of cultivating a genuinely inclusive social environment; link.)

Twitter's unacceptable hidden defect

image: github analysis of Twitter follower network (link)

Twitter's paroxysms in the past two weeks have been unsettling. But suddenly, I am coming to believe that many of us have misunderstood what we were getting into when we got involved in Twitter in the first place. We had made assumptions about the advantages that Twitter could bring to us and maybe to our academic and cultural communities -- unfettered ability to hear what a fairly lengthy list of "people to follow" and "people who follow" have to say about subjects that the individual user is interested in. We users thought the platform would offer a stimulating sharing of ideas, with a bit of synergy -- new perspectives on old issues and topics. Stuff comes in, we think about it, and stuff goes out. The platform doesn't "make" the message.

But let's look at the situation more closely. Our initial assumptions about Twitter presupposed a process: Person A follows {F1, F2, F3, ..., Fn} and is followed by {G1, G2, G3, ..., Gm}. The platform is simply a conveyor: it serves up messages from source to followers, all through the network of initiators and followers. Whenever any of the Fi people tweet, person A gets a chance to read the message and interact with it. And anything that A tweets is seen by everyone in the follower list Gi. There is usually some overlap between the F's and G's, but they aren't usually exactly the same sets of people.

But notice that this summary of the Twitter process makes an assumption: that the platform is an automatic, neutral, and mechanical server; it simply delivers messages from A to all of Gi, and it delivers all the messages created by the Fi crowd to A. (Whether A is overwhelmed by the volume of messages is a different matter; that's why it makes sense to have a reasonably small set of F's, so that it is possible to pay attention to the messages originating from the people one follows.)

What we are now learning, however, is that the platform (Twitter) is not neutral and automatic. Here I'm focusing on the personalized feed that each Twitter user receives through the app. There are two settings on the HOME / WHAT'S HAPPENING? tab. The user can stick with the default, the curated list, the "top Tweets first" list; or the user can select "Latest Tweets". The implication is that the second choice gives the user an unprocessed feed from all the accounts he/she follows, in reverse chronological order. But my own experience in the past week or so indicates that this is not the case today, if it ever was. Today, for example, 23 of the first 25 tweets in my feed are from "blue-check" accounts; whereas fewer than 10% of the people I follow have blue-check accounts. So blue-check items are vastly over-represented in my news feed, even on the "Latest Tweets" option. Twitter made a trial-balloon announcement last week that "premium accounts" will receive priority in the news feed, and it appears unavoidable that this has been implemented. And that is flatly unacceptable to me.

It is unacceptable for two reasons. First, Twitter is a communications system for me; and the system should not decide which messages I get to see -- anymore than the phone company should decide which phone calls to put through. I want to have routine, unbiased access to the tweets published by the people I follow; I don't want those messages to be buried at the end of a stream of several hundred messages that have been given priority. The whole value of having a Twitter account is having direct access to the ideas, observations, and messages of these people whose opinions I respect, and I want to have an unbiased access to those messages.

But second, the implications of a "curated" feed are quite horrible when you think them through. Any sort of bias can be built into the curation algorithm, emphasizing one kind of message over another, and building a "thought world" for the individual user that is the construction of the algorithm. Like counting votes, the only way to avoid that bias is to mechanically serve up the messages in the order in which they are published. I had long presupposed that this was the way that the feed worked. But plainly it does not work that way today -- even on the seemingly "automatic" setting of "most recent".

This is a deficiency that we probably recognized more readily in the case of Facebook, where the Facebook news feed is plainly a selective "curated" list of items drawn from the agents one has "friended" and other news sources. But on Twitter, this curation bias wasn't evident to me until this week. The reality of how the system works is important: by subscribing to Twitter and reading or scanning the news feed, we are giving the platform an incredible amount of discretion in deciding what we see and what we don't see. Right now the selection algorithm seems to be centered on Twitter's effort to incentivize users to select a paid plan (Twitter Blue, blue check, verified), by offering the advantage that the paid plan messages will get priority in the feed. That all by itself is unacceptable to me as a user, because it opens up the possibility that a disproportion of the messages that I receive are boring and irrelevant. I don't want more messages from Elon simply because he's a blue check user. But the selectivity can be even more harmful than that, since an algorithmic feed can be tuned to political purposes as well. For example, we could imagine an algorithm that gives priority to messages casting doubt on the value of US support for Ukraine and low priority to messages that emphasize the importance of US support for Ukraine.

Consider a fairly dystopian fantasy that sheds light on what I'm getting at. What if a new mass email provider offered a new service. "We will deliver your email in nano-seconds; but even better, we will automatically correct the spelling and grammar, and we will screen incoming and outgoing messages for statements you might later regret." This would be algorithmic "processing" of email communications. And it would be nightmarish. I say nightmarish, because when I send a message, I formulate it in the way that best expresses my meaning and intentions; it is the job of the email carrier to blindly and neutrally deliver the message without algorithmic review and without editing. In a small way, Twitter is messing with my social communications -- both incoming and outgoing -- by imposing an algorithmic "prioritizing" weight on different messages that means that some messages sent in my direction have a much greater probability of being read by me than others. That is a kind of soft censorship. In the present case it is censorship based on "membership status"; but the same routine could prioritize messages according to a measure of their place on the political spectrum. Not good.

I began this post by saying we didn't really understand what we were getting into when we joined Twitter -- thirteen years ago in my case. We thought, without reflection, that it was simply a cool communications platform, a basis for communicating with individuals and groups in many parts of the world and in many different disciplines. But upon reflection, it is something different than that. It is a system in which we have given up control of who sees our messages -- and when -- and which messages from our interest group we are able to see. Those determinations are being made by the algorithm, not by a simple "first-in, first-out" process that guarantees that every message will be delivered. And the algorithm is tweaked according to the business and political interests of the corporation. And Elon Musk has made it plain this week that he is entirely OK with using Twitter's system for his own political purposes. That is not acceptable.