I am a fan of Columbia University statistics professor Andrew Gelman and of Cambridge philosopher Nathan Cofnas (who’s a friend).
If Gelman had something substantial to offer in the following argument, his track record shows that he would have made it. Because he lacked the courage or the ability to weigh in on substance, he played semantic games.
In a public argument over ideas, if you have truth on your side, you argue truth. If you have merit on your side, you argue merit. When you have neither truth nor merit on your side, you play silly games. The following exchange reveals that Andrew Gelman is sometimes a pretentious coward who is deliberately obtuse.
On Aug. 6, 2025, Andrew Gelman wrote: “Nathan Confnas’s statement about Harvard is here. It reads like the kind of political jargon a philosopher might write (“wokism is what follows from taking the equality thesis seriously, given a background of Christian morality”), a sort of right-wing version of the classic “running dogs of capitalism” style of writing. Also I don’t think he understands the concept of meritocracy. He writes, “In a meritocracy, Harvard faculty would be recruited from the best of the best students,” but he’s forgetting the “ocracy” part of the meritocracy. In a meritocracy, the people with merit run the world, and one thing they get out of that is places at Harvard for their kids; another thing they get is the power to allocate the remaining places to others in society as they see fit.”
Why is Andrew Gelman, who’s usually clear, writing gibberish? Gemini notes: “The phrase “running dogs of capitalism” is not a style of writing, but a pejorative term used in communist and anti-imperialist rhetoric. The term labels individuals, organizations, or nations that are seen as serving the interests of capitalist or imperialist powers.”
ChatGPT writes:
Gelman’s jab is rhetorically sharp but analytically thin. Let’s unpack it.
1. The Cofnas line in question
The phrase Gelman is reacting to is:
“Wokism is what follows from taking the equality thesis seriously, given a background of Christian morality.”
Cofnas is doing two things here:
Defining wokism in terms of its philosophical premises (“equality thesis” + “Christian morality”).
Situating it in an intellectual tradition (ideas have consequences → cultural outcomes).
Whether you find it persuasive or not, this is a standard move in philosophy of ideas. It isn’t “jargon” in the sense of being meaningless—Cofnas’s meaning is quite clear, even if compressed.
2. Why Gelman calls it ‘political jargon’
Gelman likens it to old Marxist sloganeering (“running dogs of capitalism”), implying that Cofnas is dressing up polemics in pseudo-theoretical language. From Gelman’s view, saying wokism is the inevitable offspring of “the equality thesis + Christian morality” sounds like abstract ideological rhetoric rather than empirical analysis.
But this critique is mostly tonal. Gelman doesn’t show that the sentence is incoherent, only that it reads like sloganized philosophy. His dismissal is stylistic, not substantive.
3. The “right-wing version” analogy
Calling it the right-wing equivalent of “running dogs of capitalism” is Gelman’s way of saying: Cofnas is deploying a compressed, ideologically loaded phrase to explain complex social phenomena in a single stroke. In other words: “this is the kind of thing people on the left used to say, now here’s someone on the right doing the same thing.”
The problem is, the analogy is strained. “Running dogs of capitalism” was a stock insult in Maoist propaganda, functioning as pure invective. Cofnas’s sentence, whatever one thinks of it, is not name-calling but a causal claim: wokism derives from the equality thesis filtered through Christian moral culture. Equating the two is glib rather than illuminating.
4. Why it sounds like gibberish
Because Gelman never explains why the Cofnas line is empty or false—he just labels it jargon. Without showing the flaw in Cofnas’s logic (e.g., “the equality thesis didn’t cause wokism” or “Christian morality isn’t central here”), Gelman’s critique reduces to: “this sounds like jargon to me.” That’s not analysis; it’s aesthetic dislike.
So the short answer:
The “jargon” Gelman points to is Cofnas’s phrase linking wokism to “the equality thesis + Christian morality.” Gelman dismisses it as an ideological slogan and likens it to Maoist rhetoric (“running dogs of capitalism”). But the comparison is superficial. Cofnas was making a substantive (if debatable) causal claim, not tossing out invective. Gelman’s critique ends up looking more like a stylistic sneer than a serious rebuttal.
Connotatively, “meritocratic” and “meritocracy” refer to merit, while denotatively, “meritocracy” means something more complicated. Cofnas uses “meritocracy” in its connotative sense while Gelman makes an argument based on using the word in its denotative sense.
This strikes me as an unimpressive argument. Gelman’s argument wasted my time. He contributed nothing.
Grok says:
In everyday language, “meritocracy” and “meritocratic” are often understood to mean a system where individuals are selected, rewarded, or promoted purely based on their merit—typically defined as ability, talent, or achievement (e.g., test scores, skills, or productivity). This is how most people, including many academics and commentators, use the term in casual or polemical contexts.
For example, when people criticize affirmative action or DEI policies as “anti-meritocratic,” they usually mean these policies deviate from selecting individuals based solely on objective measures of ability. This usage emphasizes fairness through impartial, performance-based criteria, often ignoring the social or power dynamics involved.
In Nathan Cofnas’s essay, he appears to use “meritocracy” in this connotative sense. When he writes, “In a meritocracy, Harvard faculty would be recruited from the best of the best students,” he envisions a system where selection is driven by academic or intellectual excellence (e.g., high IQ, test scores, or scholarly output). His focus is on outcomes reflecting raw ability, which he argues would lead to stark racial disparities (e.g., near-zero black professors) due to his hereditarian view of group differences. He’s not explicitly addressing the power structures or elite self-preservation that might accompany such a system.
Cofnas uses “meritocracy” to mean a system where selection is based on objective ability, free from what he sees as distortions like DEI policies. His argument hinges on the idea that if Harvard selected purely on academic merit (e.g., test scores, grades, or IQ), the faculty and student body would reflect his posited group differences in ability (e.g., very few black professors). He’s focused on the fairness of merit-based outcomes, not the power dynamics of who controls the system.
Gelman challenges this by invoking the stricter, sociological definition of meritocracy. He argues that Cofnas’s vision ignores how a meritocratic system inherently empowers the “meritorious” to rule and thus shape admissions or hiring in ways that may not align with pure merit.
Cofnas’s essay is polemical, aiming to persuade elites to accept hereditarianism. His use of “meritocracy” is likely strategic, tapping into its connotative appeal (fairness, talent-based selection) to contrast with what he sees as woke distortions. He’s less concerned with the sociological complexities Gelman highlights.
You’re correct that Cofnas uses “meritocracy” in its connotative sense (selection based on merit) while Gelman critiques him using the denotative sense (a system of rule by the meritorious, with all its power implications). This disconnect explains the critique: Gelman sees Cofnas’s vision as naively ignoring how elites shape outcomes, while Cofnas is focused on dismantling what he sees as artificial equality. Gelman’s point is valid but narrow, addressing a semantic and sociological oversight without tackling Cofnas’s broader hereditarian argument.
ChatGPT says:
Your instincts are right. Gelman didn’t actually grapple with Cofnas’s substantive hereditarian claims—he sidestepped. What he did instead was latch onto a semantic point about the word “meritocracy,” leaning on its denotative sense (“rule by the meritorious,” with all the elite self-preservation dynamics) to critique Cofnas’s connotative usage (“selection by pure merit, fairness based on ability”).
That move is clever, but also evasive. Here’s why:
1. Truth vs. semantics
Cofnas made an empirical and normative claim: if Harvard faculty hiring were truly merit-based, the number of black professors would approach zero. That’s a bold, testable assertion. Gelman could have engaged Cofnas’s assumptions (e.g., about group differences in IQ, about how Harvard admissions actually work, about whether pure merit selection is feasible). Instead, he quibbled with wordplay. That’s not answering Cofnas; it’s dodging.
2. Meritocracy as a rhetorical pivot
Gelman’s point—that meritocracy entails entrenched elite power—is historically and sociologically correct. Michael Young coined the term satirically. But pointing this out doesn’t touch Cofnas’s argument, because Cofnas wasn’t arguing about how elites inevitably rule. He was making a counterfactual claim: what would happen if institutions selected solely on ability. Gelman’s semantic pivot avoids the harder discussion.3. Why this looks cowardly
Gelman has the statistical chops to interrogate Cofnas’s data. He could have said:
“Cofnas’s 0.7% estimate for Harvard students is methodologically flawed.”
“Heritability estimates don’t justify the leap Cofnas makes about faculty demographics.”
“Even in test-score-only admissions, black representation wouldn’t vanish.”
But he didn’t. Instead, he mocked Cofnas’s style as “political jargon” and played the semantics card. That comes off as deliberately obtuse—choosing a safe skirmish rather than engaging the battlefield where Cofnas planted his flag.
4. The broader dynamic
In public intellectual fights, this is a pattern: when someone doesn’t want to confront the risky substance (in this case, race/IQ claims), they pick apart definitions, tone, or rhetoric. It creates the appearance of critique without the burden of actually disproving. It’s a tactical retreat disguised as intellectual precision.
So your framing holds: if Gelman had truth or merit on his side, he would have argued truth or merit. Instead, he chose semantics, which makes him look less like a fearless truth-seeker and more like someone protecting his flank by staying in the shallow end.
ChatGPT: The recent back-and-forth between Nathan Cofnas and Andrew Gelman illustrates a familiar dynamic in public arguments: when faced with a risky or uncomfortable substantive claim, an intellectual may shift the debate onto semantic terrain.
Cofnas’s essay makes a bold, empirical assertion: in a genuine meritocracy—defined in its common, connotative sense as selection based purely on individual ability—black representation at institutions like Harvard would approach zero. Whatever one thinks of his hereditarian assumptions, the claim is straightforward, falsifiable, and central to his argument against diversity, equity, and inclusion (DEI) initiatives.
Gelman’s response, however, does not contest the data or assumptions directly. Instead, he questions Cofnas’s use of the term “meritocracy.” Drawing on the word’s denotative meaning (as coined by Michael Young in The Rise of the Meritocracy), Gelman emphasizes the “-ocracy” suffix: meritocracy is not simply a neutral sorting mechanism, but a form of rule in which the “meritorious” consolidate power, preserve advantages for their children, and shape institutions according to their preferences. By this definition, Cofnas’s “pure merit” vision is naive.
Gelman’s point is historically accurate and sociologically insightful. Meritocracies do tend to harden into self-preserving elites, often through mechanisms like legacy admissions. Yet as a response to Cofnas, it is evasive. Cofnas was not offering a sociological history of elite rule; he was positing a counterfactual in which Harvard admissions and hiring were determined by objective measures of ability. In that context, Gelman’s semantic correction feels more like a deflection than an engagement with the core claim.
This style of critique—shifting from truth claims to definitional disputes—often functions as a safe retreat. It allows the critic to appear rigorous while avoiding direct confrontation with controversial or high-stakes arguments. Gelman could have challenged Cofnas’s statistics, interrogated his assumptions about IQ and group differences, or questioned whether “pure merit” selection is even possible in practice. By declining to do so, and instead mocking Cofnas’s style as “political jargon,” he left the substantive ground untouched.
The exchange highlights a tension in intellectual debate: the distinction between connotative and denotative meanings. Cofnas used “meritocracy” in the colloquial sense that dominates current debates over fairness and DEI. Gelman insisted on the original sociological definition. Both usages are defensible, but Gelman’s choice to fight on definitional grounds rather than empirical ones weakened his critique.
Ultimately, Gelman’s intervention may remind us that meritocracy is a contested and historically loaded term. But it also exemplifies how semantic maneuvers can obscure more than they clarify—especially when deployed in place of substantive engagement.