High School Debate
I imagine some of these "activist" judges would argue that due to the legacy of systemic oppression (racism, sexism), there may still be some entrenched, invisible assumptions that create disadvantages for some debaters, and that they are trying to level the playing field. But do you really do that by announcing that arguing a position or even favorably mentioning a perspective will automatically result in points off or even disqualification? And in any case, does replacing one set of vague, ill-defined, and largely unspoken biases with another really level the playing field? I thought debating was about collecting evidence, building an argument, and then performing a rhetorical act. The NSDA used to be called the National Forensics League, after all. I imagine we have all heard stories about students instructed to argue the position they disagreed with, on a controversial topic, who learned a lot in the process. How would that ever happen if there's a "right" and a "wrong" position and those arguing the wrong side are predestined to lose?
The other thing that was alarming about the article was that students were actually rewarded for shifting from debating the issue at hand to ad hominem attacks on their opponents, if they could find something embarrassing the opponent had said on social media. Ratting out other high-schoolers for ideological missteps rather than refuting their arguments in the debate. In addition to being creepy and inculcating a culture of informers that smells a bit like 1984, I think this also reinforces a very binary world-view of good vs. evil. There is no nuance. People are not allowed to be inconsistent, or to hold opinions they may not have fully thought through. Or to be wrong on a particular issue but also perhaps have something meaningful to contribute elsewhere.
This avoidance of nuance and inability to deal with complexity is crippling public discourse. It shows up everywhere; even in the comments section of this story, which I wasn't able to participate in, since it's limited to paid subscribers. As I've observed before, I think this is a flaw of the way some people run their Substacks. Not only is it a disincentive to people to read and engage with the writing (my immediate reaction to locked comments is to consider unsubscribing, and frequently I do) but much worse, it creates an echo-chamber of like-minded commenters. In my opinion, this inevitably dumbs down the discourse. People feel free to make unsubstantiated assertions that they know their fellow enthusiasts won't challenge. An example is the series of comments on "Capitalism" in this comments section. The author of the article had identified himself as a fan of free markets, which wasn't that close to the main point of the article. But a bunch of commenters expressed their opinions about how capitalism "works" and "Communism/Socialism" doesn't, or how capitalism has been around since "somebody set up a fruit stand" in the distant past. Or what type of "communism" the commenter thinks Putin is using in Russia today.
I guess it's possible that even in a more open discussion forum people might have been equally sloppy in their thinking. But it seems like the closed forum creates a safer space for folks to take shortcuts. It's more permissible to avoid specifying what definition of capitalism or socialism they're using or at what scale (fruit stand or global economy?), because like-minded people can be trusted to "get it". Doesn't this fairly rapidly devolve into speaking in coded phrases and ultimately dog-whistling? We dislike Putin and we dislike communism and Russia used to be the USSR, so Putin is a communist. And Bernie is a socialist, so he must be working for Putin. Maybe it's unfair to judge a blog post by the quality of its comments, especially on a site where there are multiple contributors. But doesn't it make you wonder what these paying subscribers are expecting from this Substack?
Thoughts on Teaching History
These are all things we hope to see in our own classes, and sometimes we do. More often though, in my experience, the classroom fills from back to front. Students typically only answer questions when I actually call on them, not when I ask a question of the group. Some students stop coming to class if they determine they will not lose points toward their final grade by not attending (I think they DO lose overall, because they probably retain less from reading the chapter than from the lecture. But I don’t take attendance).
But really, when I think about it, my students are NOT me. Very few of them are even History majors. A larger number are in the Social Studies Education program, preparing to be high school teachers. But most of the students in my surveys (which due to their much higher enrollments means most of my students overall) are checking a “Liberal Education” core requirement box. My surveys fulfill the “History and the Social and Behavioral Sciences” goal. They also fulfill either the “Human Diversity in the United States” goal or the “Global Perspective” goal. They also all help fulfill a “Critical Thinking” requirement, although they aren’t listed as such (pretty much ALL courses at my university supposedly meet this goal, so it isn’t listed on any).
I’ve said several times in the past that I’m very interested in trying to make history relevant to the present for people, and I think about my surveys along these lines. I do think it’s helpful for members of the public to know some basic facts about the past. For me, it’s the same idea as the saying “If you don’t stand for something, you’ll fall for anything.” Similarly, if you know nothing you can be convinced of anything. This has been one of the big downsides of having all the world’s info on your smartphone, and I suppose ChatGPT may only exacerbate the problem.
In any case, I think it’s important for students to learn some info about the past. Especially some info that challenges the “Master Narrative” they have been taught all their lives. And I’m not just talking about the half-assed social studies I was taught in high school by guys whose first priority was coaching football. Even students who have taken APUS or Concurrent Enrollment “college in the high school” classes have often been “taught to the test”, which requires coverage of a fairly limited range of topics. These ARE, I admit, some of the “must-know” bits of info about our past. But it’s not my goal just to revisit that familiar territory.
What I’d prefer to do is to take students to places they might not otherwise have seen. Like a tour guide that leaves the well-worn path for some interesting side trips. The key to these explorations off the beaten path, though, is that they need to enhance the overall picture and give the traveler a more complete understanding of the territory. And it needs to be relevant to their actual lives. So what can I add to survey-level history that will enhance my students’ understanding AND be relevant to their present lives and futures? A couple of things come to mind:
- The idea that what happened was not inevitable. Understanding the contingency of the past, I think, may suggest to them that the present and future are similarly “not a done deal”.
- Awareness of the contested nature of all big social choices. This involves seriously considering the perspectives on both sides of an argument. I’m not expecting students reading a primary source in which a Southerner defends slavery to agree with the author. But I WOULD like them to try to understand why the author thinks so, whether the position is sincerely believed, or whether they are reading a rhetorical rationalization.
- A sense that the past involves choices made not only by “Great Men” but by people like themselves. How did those people make those choices? How did they make their voices heard? Hopefully, this exposure will suggest to students that they too will have the opportunity (and responsibility) to do the same in their lifetimes.
I was talking with my fellow History faculty yesterday and we agreed there are periods in American History that remind us A LOT of the present moment (we actually agreed that in addition to the first Gilded Age of the 1920s, the decade of the 1840s seems particularly resonant). There’s a limit to how directly you can call attention to those similarities. After all, history only “rhymes”, it doesn’t repeat itself. And it’s a bit anachronistic and “presentist” to make this type of correspondence the one and only focus of a history course. But I do think it’s valuable to connect the dots a bit, especially for general students who are not aspiring historians. And it may be interesting to them, too.
Books and Confirmation Bias
I mentioned the title to my wife Steph and her reaction was, "Who's gonna read that book? The people who hate Fox News." When I told Steph I was going to quote her, she said don't, because that had been a sort of automatic hot take rather than a fully-formed judgement. But I think it's a valid question. I have been critical of HCR and others for feeding the blue echo-chamber with daily summaries of news from the "Republicans Suck" food group (to paraphrase the "Useful Idiots" formula they attribute to Matt Taibbi's father). On one hand, it does make sense to build an audience by producing a consistent product that meets their expectations in some way. On the other, my gut tells me that pandering isn't the ideal way to do that, although it's certainly a popular technique in today's media.
Maybe Lepore and HCR don't feel like they are pandering, but rather that they are expressing their particular points of view which just happen to fall squarely into the middle of a current culture-war camp's POV because that group is following their lead. This is possible, but I question the circularity of this chicken/egg dichotomy. Seems a bit like the definition of a filter bubble and I think authors can be as easily caught in them as readers.
But that said, what then is the formula for developing and growing an audience more organically? I don't have as much of a problem, I have to admit, with journalists who have a predictable POV. But I DO tend to prefer reading people who can surprise me. Seymour Hersh, for example, has arguably uncovered issue after issue of US government error or malfeasance, ever since the Vietnam era. But although I look at him as a historical source and value his ongoing exposition of these themes, I don't rush to read every new article of his that drops. I don't seem to be seeking news or commentary that strokes my confirmation bias. I want to be somewhat surprised.
I'm also not a fan of one-sided accounts. While I tell myself that much of the time, the author of such an account probably feels they are setting the record straight by providing a counter-narrative to a dominant story which is so well-known as to not need repetition; the problem is, the dominant story that was obvious at the time may not be a decade later. So it seems like an author ought to try to be a bit explicit about situating the story or interpretation in a context.
A final sort-of pet peeve I have (I'm hoping these issues will be useful as hints to myself and others how to write well, and not just a series of complaints!) is the author who can't see their (I was tempted to use the pronoun “his” because in the past it has usually been a he -- but that may be changing) own cultural assumptions. This is a problem not only for historians but more generally for people critiquing culture. My book club is currently reading Simon Winchester's Knowing What We Know, and I'm getting a bit of a whiff of this in the first hundred pages. He has been going on, for example, about how "western knowledge" has been superior to "eastern"; to such an extent that it has even been grudgingly embraced by people in places like India who objected to all the colonial baggage that came with it. Winchester seems completely (deliberately?) unaware of historical and ongoing economic imperialism (globalization) that is a factor in a nation such as India's choice to follow a high-technology path integrated in western-dominated markets and financial structures rather than adopting the small-producer self-sufficiency advocated by people such as Gandhi. The conclusion that "western knowledge" is objectively better based on such a shallow depiction of a single historical example...just bugs me.
I'll probably have more to say about Winchester. And probably Lepore's and even HCR's new books, since these narratives and perspectives are getting a lot of attention and being accepted uncritically by a lot of readers.
Mankato!
I went to this university in 2006-7, when it was still called Mankato State. Since then it has grown to become the second-largest campus in the state, after the University of Minnesota's Twin Cities campus. We just had lunch in the new dining commons, which was excellent. The fountain between the Union and the Library is sparkling in the sunlight. I'm vicariously very excited for Gio, and although it's hard to be sure I hope he is too.
There are seven universities in the Minnesota State system along with 31 Community and Technical Colleges. That makes it one of the largest systems in the US, along with SUNY and Cal State. Like the rest of higher education, the system is currently facing a number of challenges including demographic changes (fewer high school graduates), the after-effects of COVID, and even more recently, generative AI. Over the next 2 to 5 years, quite a bit could change. My suspicion, which I've mentioned a bunch of times lately, is that in the long(ish) run, the disruptions of technology will shift the emphasis (value? job prospects?) back toward activities that are truly human. That could be a boon to people in the Humanities, including me and Gio. In any case, it's an interesting time to be in higher ed, either as a student or a teacher.
Is It Illegal, If You're Important?
The connections between the oligarchy described by muckrakers of a previous generation like Lundberg and the plutocrats (often the same families or sometimes even the same people!) creating this new world order are an extension to the present of the research I've been doing mapping out this web. This is not to say I straight-up believe everything Webb claims or that I attach the same urgency she does to all of her findings. For that matter, I don't believe everything Lundberg says or the weight he puts on things. One thing I do find really useful is that Webb is quite diligent about citing her sources. There's a wealth of info in her endnotes that I can use to assess the accuracy and importance of people and events in her narrative.
It interests me how similar this recent work is to the things the first generation of muckrakers produced. I wonder whether people reacted similarly at the time? Did regular McClure Magazine readers tend more easily to accept both the focus of authors on exposing corruption and their assumptions about the shared class interests and motivations of the "robber barons" who were the subjects of exposes? Did others shake their heads and mutter “conspiracy theory”?
One of the frames Webb is using is of a network connecting Business, Government, and Organized Crime. Although it's obviously correct to describe someone like Meyer Lansky as a figure of the "underworld", I think we rapidly reach a point in Webb's story where the distinctions between espionage, profit-seeking, and crime become very hazy. Laws change — like Prohibition, which spanned different years in Canada and the US, so someone like Sam Bronfman who was breaking the law at one time and place might be completely legit doing the exact same thing in another time and place. An investment banker might be operating “over the line” while Glass-Steagall is in effect but become strictly legal after its repeal. I've got to imagine the power such an investment banker might have to make that repeal happen must affect their idea about what is legal and what isn't and how much that distinction matters.
I’ll have more to say as I map out the connections Webb describes and attach them to the web I’ve already drawn. In the meantime, although we can all agree that sex-trafficking minors is always and everywhere evil and should be punished, I’m struck by the way other types of illegality may not have meant the same thing for the people who are the subjects of these narratives as it probably does for the readers of the stories.
Planting and Politics
As I was working, I listened to a series of podcasts at 1.25 speed. Chris Hedges talked with an author named Will Potter who has just written about how law enforcement has been targeting environmental activists as ecoterrorists. Then there was a Lex podcast with a comedian which was okay but not that memorable. Then I caught the beginning of a conversation between RFK Jr. and David Stockman. I've never been much of a Stockman fan, although it was interesting hearing some of his backstory. He apparently went to divinity school to avoid the Vietnam draft and he says the first campaign he worked on was that of RFK Sr. At least that allowed Stockman and Kennedy a connection on the anti-war issue.
It's interesting to see how politics is developing in this upcoming election cycle. The "uniparty" seems pretty happy with the status quo and the populists on the left and the right seem likely to be left out in the cold again. I read a really stupid substack by Robert Reich this morning, in which he went way out of his way to mischaracterize RFK Jr. in order to make him seem like a lunatic. This seems a bit unnecessary to me, but I suppose it means the corporate Dems are nervous. I saw RFK Jr. described as "Ralph Nader on crack" yesterday. The implication being that he would spoil voter turnout for the Dem candidate and hand the election to a Republican.
I can't help thinking this is the wrong way to look at it, although I suppose we're likely to see a replay of the "lesser of two evils" and "existential crisis of Democracy" tropes in 2024. The parties in power have no incentive to change, as long as they can count on voters responding to these oversimplified depictions of the political world. And I do think the people who support this story (whether that's Mr. Reich or Dr. Richardson), although they are gaining tremendously loyal followings of readers by validating people’s prejudices, are exacerbating the problem by constantly beating that red vs. blue drum.
I do think that a lot of what these "outsider" voices say is of questionable veracity. Some of it's probably a bit paranoid. Some of it may even be pandering. But at least it's challenging and questioning what we're "supposed" to believe, and asking why we're supposed to believe it and who benefits? The thing about critical thinking is that not every challenge of the conventional wisdom is right. But we won't know if we don't look. One of the things that is typically said (and repeated by the likes of Reich) is that someone like RFK Jr.'s ideas about a certain topic have "all been debunked". But if you dig down a bit, it turns out what Reich says RFK said is inaccurate and what he actually said is a bit more nuanced and complicated. RFK cited a lot of sources in his book; Reich not so many in his takedown. And how many times in the last couple of years have we been assured by the authorities that a dissenting perspective was a tin-foil-hat conspiracy theory, until it turned out to be true?
It's going to be interesting for historians of the future to try to understand this decade. What primary sources will turn out to be valuable? How will they judge today's "muckrakers" and whistle-blowers? What will they consider "yellow journalism"? It's the ten-year anniversary this week of the Snowden revelations. He’s still an exile in Russia. Julian Assange is still a prisoner.
Against Regression to the Mean
I've been thinking about the idea of outliers and means. There's a description of a general idea in recent books by Kahneman and Taleb, that where there is a distribution of outcomes, over time there will be movement toward the mean. Kahneman says "It took Galton several years to work his way from his discovery of filial regression in size to the broader notion that regression inevitably occurs when the correlation between two measures is less than perfect" (Thinking, Fast and Slow, Kindle loc. 2998). This is a bit self-evident, since the mean emerges as outcomes are observed. But it is meaningful if there is something like a normal distribution of outcomes. Taleb mentions this in Fooled By Randomness, which is no surprise really, since he is very interested in tail events. Gregory Clark even mentions it in his book The Son Also Rises, mentioning that endogamy (marrying within one's social class) can be a way of delaying or preventing the rich from sinking back down into the mass of humanity.
But what about the world of ideas? Imagine there can be either a perceptible or a subtle influence of previous outcomes on future ones. This type of thing seems to occur naturally when my thinking about a topic is influenced by things I have read or have observed other people believing. Or have been taught or socialized into. This seems somewhat connected with the power of paradigms described by Kuhn or the stickiness of memes described by Dawkins. Seems to me that original, creative thinking is most often an outcome that diverges from the mean. But now we're looking at a new entrant on the knowledge playing-field: large language models. How do the statistical ways they generate responses relate to this idea of regression?
I asked ChatGPT (May 24 Version) a couple of questions about this and these were the results:
Dan: How does the output of ChatGPT resemble regression to the mean?
ChatGPT:
The concept of regression to the mean refers to the tendency for extreme or unusual observations to move closer to the average in subsequent measurements. While regression to the mean primarily applies to statistical phenomena, it can also have some parallels with the output of ChatGPT.
ChatGPT generates responses based on patterns and information it has learned from its training data. It aims to provide coherent and contextually relevant replies to user queries. However, it's important to note that ChatGPT's responses are not a direct reflection of reality or a perfect representation of the training data. Instead, they are an approximation based on statistical patterns learned during training.
Similar to regression to the mean, the output of ChatGPT can exhibit some tendencies towards moderation or moving closer to the average response. If a user asks a question that requires a highly specific or nuanced answer, ChatGPT might not always provide an accurate or precise response. Instead, it may generate a more general or commonly observed answer that aligns with the patterns it has learned from training data.
In some cases, ChatGPT may provide outputs that are less extreme or less certain than the user's input or previous statements. This moderation or tempering of extreme statements can resemble the concept of regression to the mean. However, it's important to note that ChatGPT's output is influenced by a variety of factors, including the training data, the prompt or query, and the model's architecture, and it doesn't precisely adhere to the statistical concept of regression to the mean.
Dan: How does this similarity between the process ChatGPT uses to generate responses and regression to the mean compare to human creativity?
ChatGPT
The similarity between ChatGPT's response generation process and regression to the mean differs from human creativity in several important ways.
1. Statistical patterns vs. human imagination: ChatGPT's responses are primarily based on statistical patterns it has learned from training data. It generates outputs by identifying common patterns and associations in the data, which may include regression to the mean-like tendencies. In contrast, human creativity involves the ability to imagine and generate novel ideas, concepts, and solutions that may not be directly derived from statistical patterns. Human creativity can encompass originality, inventiveness, and the ability to think beyond conventional boundaries.
2. Context and understanding: While ChatGPT can analyze the context of a conversation to some extent, its understanding is limited to patterns it has learned during training. Human creativity, on the other hand, is driven by a deeper understanding of the world, personal experiences, emotions, and diverse perspectives. Human creative outputs often draw upon a wide range of knowledge, intuition, and contextual understanding that goes beyond statistical patterns.
3. Purpose and intention: ChatGPT's purpose is to generate responses that are contextually relevant and coherent based on its training data. It aims to provide informative or helpful answers, but it lacks intentional creativity or original thought. Human creativity is driven by conscious intention and purpose. Creativity involves actively seeking new perspectives, challenging assumptions, and generating ideas or solutions that are novel, meaningful, and purposeful.
4. Emotional and aesthetic dimensions: Human creativity often involves the expression of emotions, artistic expression, and aesthetic judgments. It encompasses various forms of art, music, literature, design, and more. ChatGPT, while capable of generating text that may seem creative in some cases, lacks true emotional depth and subjective aesthetic judgment.
So the AI's responses are statistically determined by the training data (with some potential tweaks to slightly randomize the responses by taking the second-most frequent next word rather than just grabbing the #1 choice every time). There is a HUGE amount of data readily available, but there really isn't an opportunity to discard boring or conventional answers and hone in on innovative or original ones. Because there isn't a goal involved other than answering a question accurately (#3 above).
So it seems like I need to think more deeply about novelty and insight. Specifically when I'm designing content for students. I want them to experience the human elements of learning, not just reproduce the data accurately. They can get that info anytime (until the machine stops), but what will they do with it? That will be the key to their relevance in the world as humans (not to mention their value-add vs. AI agents in the workplace).
One way of doing this is to curate content that juxtaposes ideas and perspectives in ways that doesn't represent the "mean" or the dominant paradigm. Then ask them to engage with it critically. Primary sources in history are probably a good way to introduce this variation in perspectives. So my instinct about these being more "interesting" than textbook narratives and historians' interpretations is probably useful.
Along these lines, this weekend I listened to a REALLY good America This Week episode, I think it was #41. Matt Taibbi and Walter Kirn talked very intelligently about AI and then discussed Ursula K. Leguin’s short story, “The Ones Who Walk Away from Omelas.” Taibbi’s main issue with AI is that it can be easily used to automate the tasks of surveillance and social control. He mentioned the recent statements made by representatives of the US military that drone targets are being chosen algorithmically. Kirn responded that the ultimate goal might be murder without guilt. Also plausible deniability and a scapegoat the next time US drones wipe out a wedding party. “Oh, the AI screwed up. Oops!”
Kirn’s issues with AI seem to be more generally that it will make some human labor obsolete and that it will speed the culture’s rush to conformity and mediocrity. Conformity because we will have to be socially pressured to pretend (or even convince ourselves) that we like the new Wonder Bread and Tang that AI will produce better than artisan loaves and freshly-squeezed citrus juice. Or, more important, than doing things for ourselves (last week they discussed the Forster story, “The Machine Stops”.) And mediocrity because that’s what convergence to the mean is going to produce. NOT originality, at least at first. If we get originality, then we’ve got much bigger problems.
Along the way, they did agree that the formulaic ways that a lot of intellectual property is currently produced (including a lot of Hollywood scripts, Writer’s Guild!) is already well on its way to that convergence. How problematic, really, will it be if the final step is taken and a couple of scriptwriters lose their jobs? The ones who write crappy scripts, that is. I agree with Walter that great scriptwriters will be safe, especially those who can write dialogue. Somehow I don’t see a David Mamet or an Elmore Leonard being disintermediated by an app. If it’s an app that specifically steals their work and repurposes it, then I think they might have a legitimate legal claim. I think we’re far from seeing an app understand what makes Mamet or Leonard dialogue compelling. To a great extent, I think we’re still doing what Jaron Lanier observed several years ago. Treating the little successes of the AI the way we treat a baby’s first words. Isn’t that precious! We ignore the fact that what ChatGPT produces really isn’t that insightful. It’s just the same info you could get out of a mediocre human-produced article. If it’s true (as Kirn speculates), it’s no surprise that financial and sports news is being taken over by AI.
