Sunday, January 22, 2023

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.


Saturday, January 21, 2023

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.

Thursday, January 19, 2023

Philosophy of public administration?

 

Philosophy has well-developed theories about the foundations of government — the moral principles that underlie the legitimacy of government; the nature of rights and duties of citizens; the limits of government authority; and so on for a large number of issues. These debates take place within social and political philosophy, a field whose lineage extends back to the ancient Greek philosophers, through Hobbes, Locke, Rousseau, Kant, Hegel, Marx, and Mill, and into the twentieth century in the writings of people like Rawls, Habermas, van Parijs, and Nozick.

What does not yet exist is a discipline that treats the workings of government itself as a philosophical subject. This field could be called “the philosophy of public administration.” This subject matter invites us to focus on the “social ontology” of government — the mechanisms of governments as concrete human institutions and the logic of interaction that these constituents produce. How do governments, as extended social entities, perform the functions we attribute to them — knowledge gathering, belief formation, policy and priority setting, legislation, regulation, and enforcement? Governments are not unified entities; they are extended networks of agencies, organizations, alliances, interests, and actors, and it is worth careful philosophical investigation to consider how this kind of entity can be purposive, intentional, and calculating. A philosophical reflection on these questions would focus on issues about mechanisms, order, and dysfunction within government, through attention to the actors, institutions, and organizations that constitute it.

The topics of dysfunction and imperfect functionality run throughout these discussions — not because government is an especially defective kind of social organization, but because all extended social collectivities confront the sources of dysfunction mentioned at many points in Understanding Society. Principal-agent problems, conflicts of interest within individuals and between groups of individuals, multiple understandings of the setting of organizational action and the means that are available, conflicting priorities across agencies and groups involved in coordinated activity — all of these features of social “friction” are to be found within government, as they are within all kinds of large social collectivities.

Moreover, the bureaucratic state has changed greatly in the past century, and plays a much larger role in everyday life than at any earlier point in history. In a sense the subject matter of public administration simply didn’t exist at all in the ancient world of Plato and Aristotle. There was no “public administration” in the polis. (The same cannot be said of the Roman Empire, where there were clear divisions of bureaucratic responsibility and accountability, but I am not aware of any philosophers who studied the functions and dysfunctions of Roman administration.) So the fact of a deeply ramified and bureaucratized state is a fairly modern phenomenon that it makes sense for philosophers to attempt to address.

Another important change that has occurred in the past fifty years is the emergence of a much better-defined area of sociological research aimed at achieving a better understanding the workings of organizations than has been possible in the past. Organizational sociology and organizational studies have progressed rapidly since the 1960s, and these new areas of social-science research provide new theories and questions on the basis of which to try to understand the workings of governments and their agencies.

We might think of this field in analogy with the philosophy of action. Philosophers in the philosophy of action ask questions about the rationality and purposiveness of the individual, the materiality of the acting individual, the connections that exist between mental reasoning and bodily skill and habit, and other intriguing questions about how humans and other organisms can be said to “act”. These questions are similar in form to the questions that can be raised about government: how does an ensemble of separate organizations of government come to function in some limited way as a “collective actor”? How are the individual actors within government brought into some degree of coordination and collaboration in pursuit of common purposes? What is the substrate underlying action in the two realms (neurophysiology and organizational functioning)?

A good start for thinking about the philosophy of public policy is to ask, how does government work? What are the constituent processes of government through which governments “think” and “act”? What kinds of dysfunctions and surprises are embedded in the processes that appear to constitute the workings of government? And what hidden assumptions do we make when we think about the workings of government?

Here is a preliminary list of interesting questions:

  • How is authority conveyed through the multiple levels and organizations of government?
  • How are principal-agent problems solved within governments?
  • How can governments handle problems of conflict of interest in its agents?
  • How can governments address the issues raised by conflicting assumptions and priorities driving the actions of a range of sub-units of government?
  • How are purposes and goals embodied in agencies and departments?
  • Do agencies serve “functions”?
  • How can governments achieve a degree of unity of purpose and action?

And we might add a final question: what makes these topics philosophical rather than sociological?

Monday, January 16, 2023

Is ontological individualism still a viable social ontology?

image: a flat social ontology: actors and structures


Over the years I've continued to advocate for the position of ontological individualism -- the idea that social entities, powers, and conditions are all constituted by the actions, thoughts, and mental frameworks of individual human beings, and nothing else. I'm no longer entirely confident that this is an adequate view of social ontology, because I also maintain that doing good social science requires researchers to work with a rich theory of the social actors who constitute the "substrate" of the social world. In particular, I maintain that we need to view social actors as "socially constituted" and "socially situated". This means, fundamentally, that individuals develop into actors through interaction and exposure with the communities and institutions with which they interact from childhood to adulthood -- thus coming to possess various features of motivation, cognition, and reasoning on the basis of which they act in the social world. Further, individuals exist within institutional, cultural, and normative settings that establish constraints, resources, opportunities, and limitations on their actions. Actors are "socially situated" in ways that profoundly affect their actions.

The diagram above represents a flat social ontology, with individuals and social entities in a range of locally instantiated relationships. As the arrows indicate, influence flows in all directions, from actors to structures and from structures to individual actors and between both structures and actors. (Here is a post from 2015 that considers the logic of a "flat social ontology"; link.)

So if individual actors depend on the local and historically particular social environments in which they exist -- environments that are themselves embodied by other actors -- then in what sense can we legitimately say that the individual level is more fundamental than the social level?

Two ideas seem to be true, and they are in tension with each other. On the one hand, most views about "priority of individuals" over social facts are unsupportable. Individuals are not temporally prior to social relations and influences; individuals are not causally prior to social influences (since each actor is formed and constrained by social relationships and practices); individuals cannot be characterized in terms that avoid "social" characteristics (semantic priority); and individuals are not explanatorily prior to social facts (since social facts must be invoked to describe and explain the individual's mentality and action).

But likewise, social structures, practices, and institutions are not strictly prior to individuals. Social influences on individuals at a time depend upon the actions, thoughts, and relationships of an indefinitely large group of individual actors. That is to say that social arrangements work through the actions and mentalities of the individuals who make them up. Further, social structures are not strictly speaking causally prior to individuals in any absolute sense -- it is not the case that social structures determine the actors, and in fact later iterations of social structures and institutions are changed as a result of the actions and non-actions of the actors themselves.

So it seems clear that individuals are shaped by social realities (practices, institutions, normative systems) and social realities are constituted, maintained, and changed by individuals. We cannot separate them into separate and independent causal factors.

This suggests that neither "individualism" nor "holism" will do as a basis for social ontology. Neither individual mentality and action nor the dictates and constraints of social facts persist by themselves. Instead, social actors depend upon existing social relationships and arrangements, and social facts depend upon individual actors which carry and transform them. We need to conceive of both individual actors and social arrangements as part of a single, iterative and diverse process of change and continuity. And, unfortunately, the label of ontological individualism does not capture the fullness of this set of processes.

Other theorists have tried to solve this problem. Anthony Giddens addresses this complexity through his effort to undermine the strict distinction between agent and structure. He challenges the framework itself -- the idea that "agents determine structures" and the idea that "structures determine agents". He introduces a new term to capture the complexity of the relationship between actors and structures, the idea of structuration. His 1979 collection of essays, Central Problems in Social Theory: Action, Structure, and Contradiction in Social Analysis, provides a statement of some of his views. Here is how he frames his core concern in a key essay, “Agency, Structure”:

The principal issue with which I shall be concerned in this paper is that of connecting a notion of human action with structural explanation in social analysis. The making of such a connection, I shall argue, demands the following: a theory of the human agent, or of the subject; an account of the conditions and consequences of action; and an interpretation of ‘structure’ as somehow embroiled in both those conditions and consequences. (49)

Giddens faults much of sociology for having failed to conceptualize the social-structural context with sufficient nuance. He finds, for example, that Durkheim’s efforts to provide theoretical resources for describing the “external or objective” character of society were inadequate (51). The problem is that neither individualists nor structuralists have succeeded in expressing the inherent interdependence of the two poles. Give primacy to structures and the agents are “dopes” — robots controlled by structural conditions. Give primacy to individuals, and structures and institutions seem to disappear. Giddens' own view is that the two poles of structure and agency must be considered from within a common formulation:

I shall argue here that, in social theory, the notions of action and structure presuppose one another; but that recognition of this dependence, which is a dialectical relation, necessitates a reworking both of a series of concepts linked to each of these terms, and of the terms themselves. (53)

Giddens also observes that action necessarily implies a temporal framework.

‘Action’ or agency, as I use it, thus does not refer to a series of discrete acts combined together, but to a continuous flow of conduct. We may define action … as involving a ‘stream of actual or contemplated causal interventions of corporeal beings in the ongoing process of events-in-the-world’. (55)

This process view of actors-structures-actors is what Giddens refers to as "structuration".

Another fruitful attempt to approach social ontology along these lines has been advanced by Margaret Archer through her concept of morphogenesis. Here are the opening paragraphs of Realist Social Theory.

Social reality is unlike any other because of its human constitution. It is different from natural reality whose defining feature is self-subsistence: for its existence does not depend upon us, a fact which is not compromised by our human ability to intervene in the world of nature and change it. Society is more different still from transcendental reality, where divinity is both self-subsistent and unalterable at our behest; qualities which are not contravened by responsiveness to human intercession. The nascent ‘social sciences’ had to confront this entity, society, and deal conceptually with its three unique characteristics.

Firstly, that it is inseparable from its human components because the very existence of society depends in some way upon our activities. Secondly, that society is characteristically transformable; it has not immutable form or even preferred state. It is like nothing but itself, and what precisely it is like at any time depends upon human doings and their consequences. Thirdly, however, neither are we immutable as social agents, for what we are and what we do as social beings are also affected by the society in which we live and by our very efforts to transform it. (1)

This view too suggests an inseparable entwining of the social and the individual. Neither is primary, and neither is causally determined by the other. Rather, we must postulate a continuing process of interaction between actors and structures, a process that she calls "morphogenesis".

Is there a good label for this more nuanced view of social ontology? "Ontological individualism", even when carefully qualified, still seems to give unwarranted priority to the individual actor. "Ontological holism" is even worse, since it implies that social facts are autonomous after all. I've used the terms "actor-centered sociology" and "methodological localism" to capture the sociality of the individuals who make up the social world, but these phrases are not entirely intuitive. "Structuration" is the label that Giddens uses for his own theory of agent-structure, and his language of "social life as process" is intended to capture the idea of a temporally extended back-and-forth involving actors, structures, norms, and practices. Margaret Archer's theorizing about "morphogenesis" captures much of the back-and-forth nature of the relationship that exists between social arrangements and individual agency. James Coleman offers the idea of institutions as a "house of cards", depending upon the coordinated expectations and actions of individual participants for their relative stability. Other thinkers have used the idea of a "dialectical" relationship between individual and social arrangements, but the idea of dialectical relationships brings a lot of baggage. Zygmunt Bauman's concept of liquid modernity seems to point towards this "process" ontology as well, without offering much theoretical articulation beyond the central metaphor. Even the idea of a flat social ontology, mentioned above, captures some aspects of the more complex view of the social world that we seem to need.

At the moment I can't think of a simple phrase that would adequately capture a view of social ontology that encapsulates the complex nature of the "individuals-within-social-world" view of the social that seems most justified. Whatever scheme we choose, it is crucial to incorporate the diachronic nature of the interdependence of actors and structures into the view. The diagram at the top captures the multiple directions of influence at work in a social environment, and we might imagine a sequence of representations iterated over time, in which both social structures and socially constituted actors have changed over time. There is more to do in the field of social ontology.

Friday, January 6, 2023

Atomism versus holism in social ontology


Frank Jackson and Philip Pettit addressed the micro-macro question in an essay called "Structural Explanation in Social Theory" (link), included in Reduction, Explanation, and Realism (1992, ch. 4). Particularly interesting is the brief distinction that they draw between two senses of individualism: atomism versus holism, and individualism versus collectivism. They believe that these two distinctions are quite different, and yet are commonly conflated. 

The first distinction has to do with the logical characteristics of the properties of intentionality attributed to the actor. The atomist holds that the actor's beliefs, rationality, and intentionality are fundamentally independent of the other individuals in the groups to which he or she belongs, whereas the holist maintains that the individual's beliefs, rationality, and intentionality are inextricably connected to the mentality of the group. "How far, for example, do I depend on the convergent responses of my fellows for being able to form concepts and think thoughts involving those concepts? The atomist tradition says that logically I do not depend on this way on the other members of my society. The non-atomist or holist tradition says that I do" (127). I suppose that both Hobbes and Descartes illustrate this sense of atomistic individuals -- Hobbes with his characterization of the mentality of individuals in the state of nature and Descartes in his philosophical method of doubt.

The second distinction has to do with explanatory direction and autonomy for one level or the other. It revolves around the question of whether micro-explanations are more fundamental than macro-explanations. Do individuals in the aggregate determine the properties of the social world, or do the properties of the social world determine the actions of individuals? "The other significant question ... has to do with how far the members of society, whether they are conceived of atomistically or holistically, retain their apparent autonomy in the presence of higher-order social constraints" (127). Strict collectivists maintain that individuals "must" behave in the way prescribed by social structure; strict individualists maintain that individuals retain the ability to act otherwise than as prescribed by social constraint. 

Jackson and Pettit suggest that the first distinction has to do with "horizontal" issues concerning relations among individuals, whereas the second distinction has to do with "vertical" issues having to do with individuals and social structures. Both holism and collectivism are anti-reductionist, in the sense that they each deny that social facts can be derived from some set of purely individual facts; but they amount to different kinds of claims about the priority of the social world over the aggregate of individuals.

It is worth asking whether the concept of "atomistic" offered here is consistent with the way the concept is usually understood. On the common presentation, atomism maintains that there is a core set of purely psychological characteristics possessed by every human being, and that these characteristics are pre-social. These might include a preference for self-interest, a concern for survival, and an ability to calculate risks and benefits of various actions. In his Stanford Encyclopedia of Philosophy article on methodological individualism, Joseph Heath paraphrases atomism in these terms: "The atomistic view is based upon the suggestion that it is possible to develop a complete characterization of individual psychology that is fully pre-social, then deduce what will happen when a group of individuals, so characterized, enter into interaction with one another" (section 1). The Jackson-Pettit account captures the idea that atomism assumes a pre-social individual with basic characteristics that do not logically entail anything about the social environment. But what is somewhat unclear here is their use of "logical" in this discussion. One way of understanding their meaning is that they mean to assert that, for the atomist, the "basic" psychological characteristics can be formulated in a way that does not imply anything about the social world. For example, if our scheme of the basic psychological characteristics included "an impulse towards reciprocity", then atomism would be false -- because reciprocity implies the existence of social relationships. But there are other relationships besides "logical" that might be invoked here: semantic or causal, for example. Are basic individual characteristics definable in terms that do not analytically (semantically) presuppose some facts about the social world? And are basic individual characteristics in principle wholly caused through processes of individual psychological development, or do they unavoidably involve the causal role of social interaction and structure?

Their explication of individualism and collectivism is noteworthy in a different sense: it is primarily framed around the question of the freedom or autonomy of the individual with regard to the social structures he or she inhabits. Individualism entails that individuals create / determine the social world through their actions; whereas collectivism entails that facts about social structure determine individual actions. This issue is intertwined in their discussion with the idea of explanatory primacy: is the micro-level primary with respect to the macro-level, is the macro-level primary with respect to the micro-level, or does causation flow in both directions? But these are really quite different questions. The philosophical question of "freedom of the actor" seems to have little real importance for the sociologist or the philosopher of social science; whereas the question of explanatory primary is indeed important for both.

Jackson and Pettit give some legitimacy to the idea of real causal efficacy for social structures with respect to social change (and individual behavior). Their preferred view of the explanatory force of a structural explanation of an event is what they refer to as the "program model". A structural factor contributes to the explanation of an event, not by identifying the proximate or instigating cause of the event, but by identifying the frame of circumstances in the context of which the event was likely to occur. Prolonged drought is a "program factor" for the occurrence of a forest fire, not because the drought caused the fire, but because it represented a structural circumstance in the context of which many different kinds of events could ignite the tinder. "The program explanation identifies a condition such that its realization is enough to ensure that there will be causes to produce the event explained: if not the actual causes, then some others" (119).

Jackson and Pettit concede that micro-level facts are "more fundamental" than macro-level facts; but they also give support to the position that Fodor called "relative explanatory autonomy" of higher-level structures in the social sciences, thought they do not refer to Fodor directly. "The third thing to say on the sider of collectivism is that the program model [their preferred interpretation] forces a break, not just with heuristic individualists, but also with those individualists who tolerate structural explanation but think that the micro-explanation of any social fact is always bound to be of more interest.... On the program model, structural explanation serves a different sort of interest from micro-explanation, as micro-explanation serves a different interest from detailed psychological aetiology, since it gives a different kind of information on the causal history of the event explained" (131). In other words, they support the idea that a structural explanation can be just as "interesting" and informative as a micro-explanation.

The program model works well enough for some kinds of social explanations -- for example, the outbreak of a race riot given the ambient racial disparities and patterns of police abuse. What is least satisfying about this article is the almost complete absence of an account of what "structural factors" look like in the social realm. The examples Jackson and Pettit give are almost always social patterns and correlations -- poverty causes delinquency, economic growth causes urbanization, etc. But there is no discussion of the idea of a social structure, a normative system, or an institution. And the causal mechanism linking micro to macro is also a simple one: "All such [social] facts seem to have at least this in common, that they obtain or largely obtain in virtue of the intentional attitudes -- the beliefs, desires, and the like -- of a number of people, and/or the effects of such attitudes: the actions which the attitudes occasion and the consequences of those actions" (97). This is largely an aggregative conception of the causation of "social facts" based on individual characteristics.

In particular, the analysis provided by Jackson and Pettit misses altogether the active causal powers that social structures can be said to possess. These are social features that are the object of study of organizational sociologists and institutional sociologists. And as researchers like Kathleen Thelen demonstrate (link), these kinds of social features link together into causal mechanisms constituting causal explanations in their own right. Surprisingly, their account is not very interested in "structural" explanation at all. For example, Southwest Airlines underwent a catastrophic failure during the winter holidays in 2022. (Zeynep Tufekci's article in the New York Times provides a valuable post mortem of the failure; link.) Southwest Airlines is a business corporation, an organization with leaders and individuals through whose functioning highly complex processes of coordination take place (assignments of aircraft and crews to airports at the right times and work schedules, management of investments over time). Southwest Airlines exists within a profit-driven environment in which quarterly revenue reports are highly consequential for the top executives. The coordination required of a large airline requires sophisticated computing support. But Tufekci reports that the software systems in use at Southwest were said to be woefully inadequate for several years, according to reports by insiders and labor unions, and the company delayed in upgrading these expensive systems. These are all facts about a social entity, a corporation in a specific environment, and the organizational features it possesses in virtue of which failure is likely. The result was a cascading series of thousands of flight cancellations in December that may cost the airline a billion dollars. Here we have a mechanism-based account of a major social failure that is much more complex and realistic than the context-and-influence model implied by Jackson and Pettit's arguments.

In the end, Jackson and Pettit draw a position that refrains from both methodological individualism and methodological holism, in favor of what we might call methodological pluralism:

The program model of structural explanation is not only a satisfactory account of how such explanation works. It also gives us a nice perspective on the debate between individualists and collectivists. It means that we can embrace the persuasive individualist claim that individuals are agent-autonomous. But it also allows us to understand the collectivist thesis that individuals often make little difference in the course of history and that the best way to study society is often from the top down, not from the bottom up. Those claims constitute the true and attractive core of collectivism. (131)

The conception of methodological localism that I have tried to develop over recent years avoids both atomism and individualism, in the distinctions clarified by Jackson and Pettit. Methodological localism represents the view that structures, institutions, normative schemes, and other social entities are created and embodied by social actors interacting with each other. So the structures of the social world depend on the actions and thoughts of existing individuals. But existing individuals are themselves socially enveloped. Methodological localism proposes a view of the social world in which individuals are "social constituted" and "socially situated"; so from the start, there is no hint of the idea of a pre-social individual. This entails that the view is not atomistic. But likewise, the view is "actor-centered", which implies that individuals act according to their own intentional schemes. These schemes are socially influenced, to be sure, but they are also heterogeneous and diverse; and my premise is that individuals are not determined by the ambient social values, cultures, identities, and institutions in which they live. So the view is not "collectivist" in the strong sense described by Jackson and Pettit. And, finally, the view argues that social arrangements have durable causal powers, both with respect to individuals and to other social arrangements, and that these powers do not need to be reduced to facts about individuals. This is the view of relative explanatory autonomy that Fodor introduced, and that seems very compelling in the context of the micro-macro debate.

So methodological localism is not atomistic; it supports an element of holism, in the limited sense that it asserts that social actors are formed and framed within specific social arrangements and institutions; it is not individualist, in that it does not insist that social outcomes must be explained solely through derivation from facts about individuals; it is individualist in another sense, in that it attributed "freedom" to the social actors; it is not collectivist, in the sense that it denies that social arrangements "determine" individual action; but it is sympathetic to one aspect of the collectivist view, the idea that social structures exercise real causal influence over individuals and other structures. Rather than endorsing a simple relationship between micro and macro, methodological localism posits an iterative relationship over time between "socially constituted individual" and "social structure", a view that has deep parallels with Margaret Archer's conception of morphogenesis (link).


Monday, January 2, 2023

Guest post: Varieties of realism by Jamie Morgan


[Jamie Morgan accepted my invitation to contribute a guest post to Understanding Society on the topic of the varieties of realism in the philosophy of social science. Jamie is Professor of Economic Sociology at Leeds Beckett University. He co-edits the Real-World Economics Review with Edward Fullbrook. He has published widely in the fields of economics, political economy, philosophy, sociology and international politics. Jamie is well positioned to provide this assessment. Thanks, Jamie!]

VARIETIES OF REALISM

BY JAMIE MORGAN

j.a.morgan@leedsbeckett.ac.uk

Scientific realism has many overlapping and parallel forms and one of the more prominent has been critical realism (CR). If we date from the original publication of Roy Bhaskar’s A Realist Theory of Science in 1975, then CR has endured for nearly half a century. Longevity, moreover, invites reflection in order to build institutional memory, and with this in mind the Critical Realist Network is engaged in a project to interview proponents, innovators and fellow travelers (link). Some, such as Tim Rutzou’s interview with Chris Smith, author of What is a Person? are available on YouTube. Others take a more longform ‘life and times’ approach and are published in the Journal of Critical Realism. Dan Little's is the latest in this ongoing process (link).

The interviews are a rich conceptual and bibliographic resource on CR as well as general issues in social theory, philosophy, history, methodology and social science, but in addition to this they serve a number of purposes. For those unfamiliar with CR, it tends to be most closely associated with Bhaskar’s work. However, many others have contributed to CR over the years. For example, in addition to Bhaskar’s transformational model of social activity (TMSA), CR associated thinkers have developed several different theorisations that deal with what is often described as the ‘agent-structure problematic’, but more broadly deal with the dynamics of social constitution. Readers are likely most familiar with the sociologist, Margaret Archer's structure, agency and culture (SAC), and morphostatic/morphogenetic (M/M) approach; but others include the political economist, Bob Jessop's strategic-relational approach (SRA), the economic philosopher, Tony Lawson's social positioning theory and the social theorist, Dave Elder-Vass's norm circles. As Dan notes in his interview, there are numerous points of convergence with his own advocacy of an actor-centred theory.

Dan Little, of course, is not merely a social theorist or philosopher, like many of those interviewed his work spans a variety of fields and numerous interests over the years. As Andrew Sayer, author of numerous influential books, such as Method in Social Science and Why Things Matter to People, notes in his interview, he has not found it necessary to always begin each thing he writes with an exhaustive list of CR concepts. They have often formed the background to how he approaches his work. Others, in contrast, have devoted most of their career to development of fundamental concepts. Since Bhaskar's untimely death, Ruth Groff, for example, has perhaps done more than any other within CR to develop realist conceptualizations of causation.

The interviews, then, establish that CR has a long history, is diverse and continues to develop. That said, most CR associated people subscribe to the triad of ontological realism, epistemological relativism and judgmental rationality, as well as use of concepts of depth realism, stratification, emergence, open system cumulative causation and identification of ontic and epistemic fallacies. As the interviews also establish, there is, however, a great deal of debate within CR and continual engagement with interlocutors. Regarding the former (disagreement), there are different takes on various concepts, but also argument focused on different lines of development. Alan Norrie (a leading figure in UK legal studies) and Priscilla Alderson (who has done seminal work on the rights of the child and patient rights in healthcare), for example, are advocates of dialectics, but by no means all CR proponents agree. Regarding the latter (engagement), there are, as the recent special issue of Journal of Critical Realism on pragmatism and a previous interview with Nicholas Rescher illustrate, numerous instances of productive interchange.

Moreover, as readers of this blog are no doubt aware, positions evolve and a great deal of debate has taken place in various threads within Understanding Society, written by Dan and others and taking in reference to and commentary from many of those interviewed and already mentioned, as well as George Steinmetz, Peggy Somers, Guus Duindam, Tuuka Kaidesoja, Justin Cruickshank, Mervyn Hartwig, Phil Gorski and Doug Porpora. Doug Porpora is currently President of the International Association for Critical Realism (IACR) and is another who has been interviewed for the project. Mention of IACR, furthermore, is an important reminder that CR is a growing global community and the interviews conducted so far are no more than a snapshot, able to indicate something of the flavour of CR but not fully convey its organizational form, extent and significance. The Network provides access to various on-line courses and other educational resources, proponents can be found all over the world (from Scandinavia to Asia Pacific), works are available in many languages and the next IACR conference, organized by Johnny Go, is scheduled for August 2023 in Manila, the Philippines.

Finally, as the interviews and also Hubert Buch-Hansen and Peter Nielsen’s recent book Critical Realism makes clear, CR is not, to mix metaphors some ossified dogma, it is a living body of thought. CR at its best is philosophy and social theory to some purpose and advocates work on some of the most pressing issues of our time.

*****

Here is a list of interviews conducted by Jamie Morgan and published in Journal of Critical Realism:

Nicholas Rescher, Jamie Morgan, 2020. Philosophical purpose and purposive philosophy: an interview with Nicholas Rescher, JCR, 19:1, https://doi.org/10.1080/14767430.2019.1695085

Margaret S Archer, Jamie Morgan, 2020. Contributions to realist social theory: an interview with Margaret S. Archer, JCR, 19:2, https://doi.org/10.1080/14767430.2020.1732760

Douglas V Porpora, Jamie Morgan, 2020. American sociology, realism, structure and truth: an interview with Douglas V. Porpora, JCR, 19:5, https://doi.org/10.1080/14767430.2020.1782708

Alan Norrie, Jamie Morgan, 2021. Realism, dialectic, justice and law: an interview with Alan Norrie, JCR, 20:1, https://doi.org/10.1080/14767430.2021.1881274

Tony Lawson, Jamie Morgan, 2021. Cambridge social ontology, the philosophical critique of modern economics and social positioning theory: an interview with Tony Lawson, part 1, JCR, 20:1, https://doi.org/10.1080/14767430.2020.1846009

Tony Lawson, Jamie Morgan, 2021. Cambridge social ontology, the philosophical critique of modern economics and social positioning theory: an interview with Tony Lawson, part 2, JCR, 20:2, https://doi.org/10.1080/14767430.2021.1914904

Dave Elder-Vass, Jamie Morgan, 2022. 'Materially social' critical realism: an interview with Dave Elder-Vass, JCR, 21:2, https://doi.org/10.1080/14767430.2022.2028233

Andrew Sayer, Jamie Morgan, 2022. A realist journey through social theory and political economy: an interview with Andrew Sayer, JCR, 21:4, https://doi.org/10.1080/14767430.2022.2049078

Bob Jessop, Jamie Morgan, 2022. The strategic-relational approach, realism and the state: from regulation theory to neoliberalism via Marx and Poulantzas, an interview with Bob Jessop, JCR, 21:1, https://doi.org/10.1080/14767430.2021.1995685

Daniel Little, Jamie Morgan, 2022. Understanding society: an interview with Daniel Little, JCR, Latest Articles, https://doi.org/10.1080/14767430.2022.2134617

Ruth Porter Groff, Jamie Morgan, 2022. Philosophy, metaphilosophy and ideology-critique: an interview with Ruth Porter Groff, JCR, Latest Articles, https://doi.org/10.1080/14767430.2022.2101342

Priscilla Alderson, Jamie Morgan, 2022. Realist by inclination, childhood studies, dialectic and bodily concerns: an interview with Priscilla Alderson, JCR, Latest Articles, https://doi.org/10.1080/14767430.2022.2068261

Heikki Patomäki & Jamie Morgan, 2023. World politics, critical realism and the future of humanity: an interview with Heikki Patomäki, Part 1, Journal of Critical Realism, https://doi.org/10.1080/14767430.2023.2188527

Heikki Patomäki & Jamie Morgan, 2023. World politics, critical realism and the future of humanity: an interview with Heikki Patomäki, Part 2, Journal of Critical Realism, https://doi.org/10.1080/14767430.2023.2188541

Berth Danermark & Jamie Morgan, 2023. Applying critical realism in an interdisciplinary context: an interview with Berth Danermark, Journal of Critical Realism, https://doi.org/10.1080/14767430.2023.2188710

Caroline New and Jamie Morgan, 2003. Making realism work, from second wave feminism to extinction rebellion: an interview with Caroline New. Journal of Critical Realism, https://doi.org/10.1080/14767430.2023.2283299