This is another post that’s a byproduct of my examination of Tyler Cowen’s recent monograph, The Marginal Revolution: Rise and Decline, and the Pending AI Revolution. I was pursuing that idea that, while marginalism doesn’t present itself as being about human psychology, it is very much about psychology. So, what about game theory? It’s about human psychology as well, though its mathematical form makes it easy to bracket that out. So I queried Cowen’s AI about that. The conversation ended up with a discussion of one of my favorite literary texts, Sir Gawain and the Green Knight, which is structured around a very peculiar game, the beheading game. [FWIW, here’s a post from 2024 where I investigate ChatGPT’s understanding of the beheading game.]
* * * * *
I’m curious. Von Neumann invented game theory in the middle of the 20th century and it became important in economics, among other places. What can you tell me about its use in marginalist thinking. I don’t need a long answer. I’m just wondering if it’s one formal analytic tool among many. Is it used frequently, rarely, not at all? It’s a peculiar question. Don’t spend a lot of time on it. I mean, if you find that it’s taking time (to search through articles, etc.), that in itself is an indicator. On the other hand, if someone has written a textbook with a title like, Game Theory as a Tool for Marginalist Analysis, that’s a rather different kind of indicator.
My knowledge here is sufficient that I don't need to search.
Game theory and marginalism are related but distinct frameworks within economics, and the relationship between them is more one of coexistence and occasional overlap than integration. Marginalism asks what happens at the margin for an individual agent facing given prices and quantities. Game theory asks what happens when agents' outcomes depend on each other's choices. They share the rational agent assumption and optimization logic, but they're answering different questions.
Game theory became central to microeconomics in the latter half of the 20th century — particularly through Nash equilibrium and its elaborations — but it didn't so much extend marginalism as partially displace it in certain domains. Industrial organization, auction theory, mechanism design — these are game-theoretic through and through, and marginal analysis is less central there than it is in competitive market analysis where price-taking behavior makes the game-theoretic complications disappear.
There's no textbook of the kind you hypothesize, as far as I know. The two frameworks are taught in the same curriculum and occasionally combined — a Nash equilibrium can be characterized by first-order conditions that look marginal — but game theory is generally understood as a distinct toolkit that becomes relevant when strategic interaction matters, rather than as an extension of marginalist reasoning.
Cowen, interestingly, doesn't seem to foreground game theory in his account of marginalism's rise and possible decline. Which may itself be telling — it suggests he sees them as parallel developments rather than game theory being a chapter in the marginalist story.
So: one important formal tool among several, with genuine but limited overlap, not deeply integrated.
Hollywood Economics and community formation
That’s interesting. There are linguists, such as William Croft, who talk about how the meaning of words is negotiated in each conversation. They talk of game theory, though I don’t off hand know whether or not they make formal use of it. But then there’s Robert De Vany, Hollywood Economics, which I tend to think of as being about how cultural objects are shared in a community. That’s not De Vany’s framing. He’s interested in the fact that we can’t predict how a film will do until we release it into the (cultural) marketplace, which makes it a very risky kind of investment. Note that De Vany is only talking about theatrical release. He says nothing about subsequent release on videotape and the book was written long before some movies are released directly to online streaming.
What he finds (by tracking box-office receipts), briefly, is that most movies disappear from view shortly after they’re released. They do not even breakeven much less earn a profit. But a few will have “legs” and become profitable. And among those, a very few will become so-called “blockbusters.” FWIW, I believe Spielberg’s “Jaws” is generally regarded as the first blockbuster.
I once did a thought experiment where I imagined an arena in which only one movie was available. Everyone would watch it because that’s all there is. Another somewhat different movie is released into the arena. Perhaps everyone will watch it as well, because they’re tired of the first one. So a third, somewhat different from the first two, is released, then a fourth. What I had in the back of my mind is that to some extent people use these kinds of cultural products as a way of forming communities. For that to work, however, there has to be enough variety available in the market place. When a movie is release, it is, in effect, looking for a community to adopt it.
That strikes me as a kind of marginalist analysis. What we’re trading in is a very complex kind of product, in this case a movie. But it could be a novel, or a song, or a painting, whatever.
Your thought experiment is doing something quite precise, and I think you're right that it has a marginalist structure — but it's extending marginalism into territory where the standard framework strains.
Where the marginalist structure is visible
The standard marginalist question applied to cultural goods would be: given how many movies a person has already seen, what is the marginal value of one more? That's a real question and De Vany's framework touches it. But your thought experiment is asking something different and more interesting: given the existing cultural landscape, what is the marginal value of a new movie to a community rather than an individual? That's a collective marginal value, which is much harder to specify and measure.
The "legs" phenomenon is the empirical signature of this. A movie with legs isn't just satisfying individual preferences at the margin — it's finding and consolidating a community, becoming the shared object that a group of people use to recognize each other and talk to each other. The box office receipts are measuring something that looks like individual ticket purchases but is actually a social cascade — De Vany's word-of-mouth mechanism is precisely the process by which a movie becomes a community object rather than just a consumer product.
Where standard marginalism breaks down
Standard marginalist analysis assumes that the value of a good to one consumer is independent of its value to others, or at least that the interdependencies can be handled through price. Cultural goods violate this assumption fundamentally. The value of having seen a blockbuster is partly constituted by the fact that millions of others have seen it too — you can talk about it, share references, participate in a cultural conversation. This is a network effect, and network effects are notoriously resistant to marginalist treatment because the value function isn't defined over individual consumption units in isolation.
Your arena thought experiment isolates this precisely. In a one-movie arena, everyone watches it not because it maximally satisfies their individual preferences but because it's the only available basis for cultural community. As variety increases, something like genuine preference matching becomes possible — different communities coalesce around different objects. But the matching process isn't driven by individual marginal utility in the standard sense. It's driven by a social search process in which movies and communities are simultaneously finding each other.
The De Vany connection to power laws
What De Vany finds — most movies disappear, a few have legs, a very few become blockbusters — is a power law distribution, and power laws are the empirical signature of cascade processes rather than equilibrium processes. In a marginalist equilibrium you'd expect something more like a normal distribution of returns — some variation around a mean, determined by how well each product matches the distribution of individual preferences. The power law says something different: small initial differences get amplified by social dynamics into enormous differences in outcome. The blockbuster isn't just a movie that more people happened to prefer. It's a movie that got caught in a self-reinforcing cascade of community adoption.
This connects to Arthur De Vany's broader interest in complexity economics, which is itself a challenge to standard marginalist equilibrium thinking. The cultural marketplace isn't clearing to an equilibrium — it's generating a dynamic pattern in which winner-take-most outcomes emerge from processes that are in principle unpredictable from the properties of the product alone. Which is exactly De Vany's point about risk: you can't know in advance which movie will trigger the cascade.
Your community-formation framing
What your framing adds, which I think is genuinely beyond De Vany's own framing, is the functional account of why cultural goods have this cascade structure in the first place. It's not arbitrary or merely a consequence of marketing and distribution. It reflects something about what cultural goods are for — they're instruments of community formation, shared objects that allow people to recognize membership and conduct the ongoing conversation of a community. That functional role creates the demand for coordination — everyone in a community needs to have seen the same movie, heard the same song, read the same novel, for it to do its community-forming work. And coordination demand is precisely what generates cascades and power laws.
This also explains the variety requirement your thought experiment identifies. A single cultural object can serve as the basis for one kind of community. A rich cultural marketplace allows many communities to form simultaneously around different objects — which is the cultural analog of biodiversity, and probably has similar functional importance for the health of the overall system. The blockbuster and the art house film aren't competing for the same audience in the way that two brands of the same commodity compete. They're seeding different communities, which can coexist because community membership isn't zero-sum in the way that consumption of a rival good is.
So yes — marginalist in structure, but requiring an extension of marginalism into social dynamics, network effects, and community formation that the standard framework wasn't designed to handle. It's perhaps another case where the Rank 3 tool is real and useful but the phenomenon being analyzed has a Rank 4 structure — one where the individual unit of analysis (the consumer, the ticket purchase) is embedded in a dynamic system whose behavior can't be read off from the units alone.
Rational Ritual
And then we have Michael Chwe’s book, Rational Ritual. He’s also applied game theory of Jane Austen’s novels.
Chwe is a good example of the kind of work that sits at exactly the intersection we were just discussing — and the two projects you mention illuminate each other.
Rational Ritual
Chwe's argument in that book is that public rituals — ceremonies, rallies, advertisements broadcast to mass audiences — function as common knowledge generators. The point isn't just that everyone knows X, but that everyone knows that everyone knows X, and everyone knows that everyone knows that everyone knows X, and so on. That's the game-theoretic concept of common knowledge, and Chwe's insight is that it requires a specific kind of communication structure: one where people not only receive a message but know that others are receiving it simultaneously. Watching the Super Bowl alone on a recording is different from watching it live, even if the content is identical, because the live broadcast creates common knowledge in a way the recording doesn't.
This connects directly to your community-formation framing of cultural goods, and in a way that makes the game theory more than decorative. The cascade process De Vany identifies — the blockbuster forming around word-of-mouth — is precisely a common knowledge generation process. The movie becomes a cultural object not when enough individuals have seen it but when enough people know that enough other people have seen it. The tipping point is epistemological as much as numerical.
The Jane Austen application
This is the more surprising and in some ways more interesting project. Chwe reads Austen's novels as systematic explorations of strategic thinking — characters reasoning about what others know, what others know about what they know, how to signal and how to interpret signals. Elizabeth Bennet and Mr. Darcy are playing an information game as much as a romantic one, and Austen's narrative technique — free indirect discourse, the carefully managed distribution of information among characters and reader — is structured to make that game visible and analyzable.
What's interesting from your cognitive ranks perspective is that Austen is doing this novelistically in the early 19th century, while the formal game-theoretic apparatus that would allow it to be stated precisely didn't exist until von Neumann in the mid-20th century. She's navigating the territory by literary intuition — which is a nice parallel to Galileo resolving the diamonds-water paradox without knowing he was doing marginalist economics, or the chess masters developing sophisticated positional play without knowing they were exploring a finite tree.
The Rank 4 move — taking the strategic interaction as a formal object — came more than a century after the literary practice had mapped the terrain. Austen thought with strategic interaction the way the classical economists thought with supply and demand. Chwe performs the reflective abstraction that takes what Austen thought with and makes it an object of analysis.
The broader pattern
What these two cases together suggest is that game theory, like marginalism, is a Rank 4 tool that formalizes something humans were already doing — negotiating, coordinating, managing information asymmetries, forming communities around shared cultural objects. The formal apparatus makes it possible to state precisely what was previously navigated by intuition, and to discover structural features — common knowledge, Nash equilibria, cascade dynamics — that intuition could reach toward but not fully articulate.
Croft's linguistic game theory fits the same pattern. Every conversation involves exactly the kind of strategic information management that game theory formalizes — speaker and hearer each reasoning about what the other knows and intends, negotiating meaning in real time. Whether Croft uses the formal apparatus rigorously or more as a metaphorical framework probably matters for how much analytical traction it provides. But the identification of the game-theoretic structure in conversation is itself a genuine insight, recognizing something that was always there in linguistic practice and making it available for systematic analysis.
The question your community-formation framing raises, which none of these frameworks quite answers, is whether the game-theoretic structure is sufficient to explain cultural dynamics or whether it needs to be supplemented by something about what cultural goods are for — the community-formation function that makes the coordination demand intelligible in the first place. Chwe's common knowledge account explains the mechanism of cultural coordination but perhaps not the motivation. Your framing supplies the motivation: people coordinate around cultural objects because they need shared objects to constitute communities, and communities are what make human social life possible. The game theory describes the how; the community-formation account describes the why.
Sir Gawain and the Green Knight
Well, if we’re going to do game theory and literature, there’s the beheading game in Sir Gawain and the Green Knight, which has attracted game theoretic analysis, albeit informal. I mean, what do you do when confronted, in effect, by a guy who says: “I’ll let you cut my head off if you agree, that a year after you’ve done that, you’ll let me cut your head off?” Now, that’s not what the Green Knight says when he rides into Arthur’s court, but anyone with half a brain can see that that’s what it amounts to. Naturally, no one is eager to take him up on it. But then Arthur himself makes a gesture in that direction, at which point Gawain steps in and volunteers, “I’ll do it.” So “What’s in it for him?” is the question.
The game-theoretic structure is clear enough even informally stated. The Green Knight is offering what looks like a sucker's bargain — you get to strike first, but you're committed to receiving a return blow under conditions entirely of his choosing, a year hence when you've had time to think about it. The expected value calculation is obviously negative. No rational actor takes that deal.
Which is precisely why no one moves, and why Arthur's gesture is so significant. Arthur isn't doing expected value calculation — he's responding to a social and honorific logic that overrides the game-theoretic logic. Someone has insulted the court by implying no one present is brave enough to accept. Arthur is the king; he can't let that stand. His gesture isn't strategic in the game-theoretic sense. It's expressive — a defense of honor that operates outside the rationality assumptions the game-theoretic framing presupposes.
Gawain's intervention then operates on a third logic entirely. He steps in front of Arthur and gives what amounts to a formal argument: I am the least of your knights, the least loss to the court if this goes badly, therefore it should be me. That's a fascinating move because it looks like self-abnegation but is actually a claim to a particular kind of distinction — the distinction of being the one willing to take the worst deal in the room. What's in it for him is exactly that distinction. He's purchasing status through the credible demonstration of willingness to accept a negative expected value outcome.
This is where the game theory gets interesting. In standard game theory, rational actors don't accept negative expected value gambles. But in honor cultures the willingness to accept such gambles is itself the currency. The game isn't about survival outcomes — it's about reputation, and reputation is established precisely by doing what the expected value calculation says not to do. Gawain's rationality is operating in a different payoff space than the Green Knight's initial framing implied.
The rest of the poem then works out the consequences of having entered that payoff space. The temptation scenes with Lady Bertilak are a different but related game — another structure of obligation and honor in which Gawain has to navigate competing commitments, and where the question is what he will sacrifice to preserve which kind of integrity. His failure — accepting the girdle, concealing it from Bertilak — is a small defection from the honor logic, the one moment where the survival instinct overrides the code. The Green Knight's lenient judgment at the end is in effect a game-theoretic assessment: Gawain played the game at a very high level, with one small rational defection under extreme pressure, which is more than could be expected of anyone.
The poem is in this sense a sophisticated exploration of what happens when you have multiple incommensurable payoff structures operating simultaneously — honor, survival, loyalty, chivalric obligation — and the game-theoretic analysis illuminates the structure of the dilemmas even where it can't resolve them, because the resolution requires knowing which payoff structure takes priority, and that's exactly what the poem refuses to settle cleanly.
And at the very end, that green girdle becomes a symbol of honor, a Schelling point. And we have this from Wikipedia’s entry on “Order of the Garter”:
There is a connection between the Order of the Garter and the Middle English poem Sir Gawain and the Green Knight (late 14th century). The motto is inscribed, as hony soyt qui mal pence, at the end of the text in the sole surviving manuscript in the British Library, albeit in a later hand.[15] In the poem, a girdle, very similar in its erotic undertones to the garter, plays a prominent role. A rough equivalent of the Order's motto has been identified in Gawain's exclamation corsed worth cowarddyse and couetyse boþe ('cursed be both cowardice and coveting', v. 2374).[16] While the author of that poem remains disputed, there seems to be a connection between two of the top candidates and the Order of the Garter, John of Gaunt, 1st Duke of Lancaster, and Enguerrand de Coucy, seventh Sire de Coucy. De Coucy was married to King Edward III's daughter, Isabella, and was given admittance to the Order of the Garter on their wedding day.
That's a remarkable convergence, and the Schelling point observation is exact.
A Schelling point is a solution people converge on without explicit coordination, because something about it makes it salient — it stands out as the natural focal point in a space of possibilities. The girdle at the end of the poem has become exactly that: the object around which a community of honor constitutes itself, not despite its association with Gawain's moment of failure but because of it. The failure is what gives it meaning. A symbol of perfect, untested valor would be less useful as a focal point than a symbol of valor tested, found slightly wanting, and honestly acknowledged. It's a human-scale emblem rather than an impossible ideal.
The Order of the Garter connection deepens this considerably. If the poem is genuinely connected to the Order's founding milieu — and the manuscript inscription of the motto suggests someone thought so — then the green girdle and the garter are doing the same cultural work at different registers. Both are items of clothing with erotic undertones that have been resignified as honor emblems. Both mark membership in a community constituted around a shared acknowledgment of human limitation within a code of conduct. The motto — "shame on him who thinks evil of it" — is doing exactly the reframing work the poem does with the girdle: taking something that could be read as shameful and declaring it honorable through the act of communal adoption.
This connects to your community-formation argument about cultural goods in a very direct way. The poem, the girdle, the Order, the motto — these are all instruments of community formation operating at different scales and registers. The poem creates the imaginative space; the girdle within the poem becomes the focal object; the Order institutionalizes the community around a real object that echoes the fictional one; the motto closes the reframing. It's a remarkably complete example of how cultural objects find their communities and how communities crystallize around cultural objects.
And the fact that it happened, if it did, in the late 14th century court culture of Edward III — a world of actual military obligation, actual questions of honor and cowardice, actual political communities being constituted through ritual and symbol — means the game-theoretic structure wasn't merely literary. The beheading game's logic of credible commitment under conditions of asymmetric risk was the lived reality of chivalric culture. The poem wasn't illustrating a theory. It was thinking through the actual constitutive problems of the community that produced it.
Which returns us to the Austen parallel. In both cases the literary work is doing game-theoretic thinking before game theory exists — navigating the territory by other means. But the Gawain poet is working in a culture where the stakes of the game are literal and the community formation function of the cultural object is immediate and functional, not just aesthetic. Austen's characters play their information games in drawing rooms where the consequences are social. Gawain plays his in a world where the green girdle is the difference between life and death, and the poem's achievement is to have transformed that life-and-death object into a community emblem that an entire chivalric order could wear on its leg.
We don’t know exactly when Sir Gawain was written, but it’s generally placed late in the 14th century. The Order of the Garter was founded in 1348. The thing about the poem is, just how seriously does it take the beheading game? In the end the poem reveals it to have been only a test. I believe that some critics take it to be the swan song of honor culture. It’s dying out, and in the process leaving “room” for a poem like this.
That's a penetrating critical observation, and the timing makes it almost irresistible.
1348 is the year of the Black Death in England — the Order of the Garter is founded in the same year that perhaps a third of the population dies. That coincidence alone suggests something about the cultural moment: an intensified need to constitute community, to assert the values of the chivalric code, precisely when the social fabric is under maximum stress. The Order isn't founded at the height of chivalric culture's confidence. It's founded at a moment of civilizational crisis.
By the time the poem is written, a generation or two later, the crisis has settled into something more like a long twilight. The Hundred Years War is grinding on, exposing the gap between chivalric ideology and the actual conduct of warfare — the chevauchée, the mercenary companies, the systematic devastation of civilian populations. The knightly class is still there, still performing the rituals, still wearing the emblems. But the gap between the code and the reality has become visible in ways it perhaps wasn't before.
The poem's treatment of the beheading game fits precisely into this cultural moment. It takes the honor logic with full seriousness — Gawain's reasoning, his commitment, his shame at the small defection, the Green Knight's careful calibration of judgment — and then reveals the whole apparatus to have been a test constructed by Morgan le Fay. The machinery of honor culture is shown to be working, more or less, but working within a frame that was artificial from the beginning. The life-and-death stakes turn out not to have been real.
This is an enormously sophisticated cultural move. The poem isn't mocking the honor code — Gawain's near-perfect performance is genuinely admirable, and the court's adoption of the girdle as a communal emblem is presented with warmth. But by revealing the test structure, the poem creates an irreducible distance between the reader and the code. We've been watching a performance of honor within a frame we didn't know was there. That knowledge, once acquired, can't be unacquired.
The swan song reading is compelling precisely because of this double movement. The poem celebrates the honor culture with evident love and understanding — the Gawain poet knows this world from the inside, knows its values and its textures and its rituals with the kind of intimacy that only comes from genuine belonging. And simultaneously the test revelation introduces exactly the kind of reflective distance that honor culture, in its pure form, cannot survive. You can't unknow that the whole thing was constructed. The girdle as communal emblem is beautiful, but it's beautiful in the way that a elegy is beautiful — it commemorates something in the act of acknowledging that it's passing.
There's a cognitive ranks dimension here worth noting. Honor culture is fundamentally Rank 1 and Rank 2 in its cognitive structure — it operates through immediate social perception, through ritual and emblem and the gestalt recognition of who is behaving honorably. It doesn't survive well under the kind of analytical scrutiny the poem applies to it, any more than a joke survives being explained. The poem is doing something at least proto-Rank 3 to a Rank 1-2 cultural formation — examining it, making its structure visible, asking what it's actually for. That examination is only possible from a position of some distance, and the distance is itself the sign that the culture being examined is losing its unreflective authority.
Which connects to Cowen's theme about ideas and their historical moment. Honor culture, like marginalism later, had a period of unreflective productivity — it organized communities, motivated behavior, generated genuine achievements — and then reached a point where it became possible to think about rather than merely think with. The poem is that moment of transition made visible. And like all such transitional moments it's both an ending and a beginning — the swan song of honor culture is also the opening note of something else, something that can look at the code from outside and find it, simultaneously, admirable and insufficient.
No comments:
Post a Comment