Category: Political Science

Claims about atheists

The group that is most likely to contact a public official? Atheists.

The group that puts up political signs at the highest rates? Atheists.

HALF of atheists report giving to a candidate or campaign in the 2020 presidential election cycle.

And while they don’t lead the pack when it comes to attending a local political meeting, they only trail Hindus by four percentage points.

…atheists take part in plenty of political actions – 1.52 to be exact. The overall average in the entire sample was .91 activities. The average atheist is about 65% more politically engaged than the average American.

And this:

The results here are clear and unambiguous – atheists are more likely to engage in political activities at every level of education compared to Protestants, Catholics or Jews. For instance, an atheist with a high school diploma reports .7 activities, that’s at least .2 higher than any other religious group.

Political engagement is clearly related to education, though. The more educated one is, the more likely they are to be politically active. But at every step of the education scale, atheists lead the way. Sometimes those gaps are incredibly large. A college educated atheist engages in 1.7 activities, it’s only 1.05 activities for a college educated evangelical.

From Ryan Burge, here is the full data analysis.

Sentences of the Day

The Washington Post on the plan to refurbish Union Station in DC:

The federal environmental review of the project, which began in 2015, is at least three years behind schedule. Once the federal approval process is complete, a design phase is likely to take several years, project officials said, possibly followed by 13 years of construction.

A good example of the Ezra Klein point about the costs of everything bagel liberalism. By the way, the push to eliminate more than a thousand parking spots at the station seems counter-productive. I’m not a fan of parking minimums but in typical liberal fashion that has been turned into an anti-parking, anti-car crusade regardless of context. In fact, a railroad station is precisely where you do want parking to avoid the last mile(s) problem and encourage rail use.

Is Switzerland right-wing? (from my email)

Dear Tyler,

I came across this study today (https://serval.unil.ch/resource/serval:BIB_236420EB8209.P001/REF) that claims that Switzerland is one of the most right-wing (at least nominally) countries in Europe.The federal government has been in the hands of the right since 1848.The federal parliament is currently dominated by the right.26 out of 26 cantonal parliaments are controlled by the right.25 out of 26 canton governments (with the exception of the Jura) are in the hands of the right.Neither the parliament nor the national government has ever been controlled by the left.

How does it fit with your model of Switzerland?

Still an undeservedly overlooked country!

That is from Krzysztof Tyszka-Drozdowski.

*Voters as Mad Scientists*, by Bryan Caplan

This new collection has some of Bryan’s best material, and perhaps also his best single piece of writing ever.  Here is an excerpt from “My Simplistic Theory of Left and Right“:

This:

1. Leftists are anti-market.  On an emotional level, they’re critical of market outcomes.  No matter how good market outcomes are, they can’t bear to say, “Markets have done a great job, who could ask for more?”

2. Rightists are anti-leftist.  On an emotional level, they’re critical of leftists.  No matter how much they agree with leftists on an issue, they can’t bear to say, “The left is totally right, it would be churlish to criticize them.”

Yes, this story is uncharitable and simplistic.  But clarifying.  Communists and moderate Democrats are vastly different, but they have something in common: Free markets get on their nerves.  Nazis and moderate Republicans are vastly different, but they too have something in common: Leftists get on their nerves.  Within each side, the difference between moderates and extremists is the intensity of their antipathy, not the object of their antipathy.

The subtitle of the work is Essays in Political Irrationality.  Definitely recommended, buy it here.  Fittingly, the dedication of the book is “To Alex Tabarrok, a captain of reason in a sea of political irrationality.”

Great News for Female Academics!

For decades female academics have been told that the deck is stacked against them by discrimination in hiring, funding, journal acceptances, recommendation letters and more. It’s dispiriting to be told that your career is not under your control and that, no matter what you do, you face an unfair, uphill battle. Why would any woman want to be a scientist when they are told things like this:

A vast literature….shows time after time, women in science are deemed to be inferior to men and are evaluated as less capable when performing similar or even identical work. This systemic devaluation of women women results in an array of real consequences: shorter, less praise-worth letters of recommendation, fewer research grants, awards and invitations to speak at conferences; and lower citation rates for their research…

The good news is that this depressing and dispiriting story isn’t true! In an extensive survey, meta-analysis, and new research, Ceci, Kahn and Williams show that the situation for women in academia is in many domains good to great. For example, in hiring for tenure the evidence is strong that women are advantaged. Moreover, women are advantaged especially in fields where they have relatively low representation (GEMP: geosciences, engineering, economics, mathematics/computer science, and physical science).

Among political scientists, Schröder et al. (2021) found that female political scientists had a 20% greater likelihood of obtaining a tenured position than comparably accomplished males in the same cohort after controlling for personal characteristics and accomplishments (publications, grants, children, etc.). Lutter and Schröder (2016) found that women needed 23% to 44% fewer publications than men to obtain a tenured job in German sociology departments.

…In summary, all of the seven administrative reports reveal substantial evidence that women applicants were at least as successful as and usually more successful than male applicants were—particularly in GEMP fields.

…In a natural experiment, French economists used national exam data for 11 fields, focusing on PhD holders who form the core of French academic hiring (Breda & Hillion, 2016). They compared blinded and nonblinded exam scores for the same men and women and discovered that women received higher scores when their gender was known than when it was not when a field was male dominant (math, physics, philosophy), indicating a positive bias, and that this difference strongly increased with a field’s male dominance. Specifically, women’s rank in male-dominated fields increased by up to 40% of a standard deviation. In contrast, male candidates in fields dominated by women (literature, foreign languages) were given a small boost over expectations based on blind ratings, but this difference was small and rarely significant.6

The situation is also very good in grant funding and journal acceptance rates which are either not biased or biased towards women. Similarly, “no persuasive evidence exists for the claim of antifemale bias in academic letters of recommendation.”

There is evidence of bias in student evaluations. Both female and male students rate male professors higher, even in situations where names are known but actual gender is blinded. Male students are more likely to write nasty comments. Most research universities, in my experience, don’t put much weight on student teaching evaluations, beyond do you pass a fairly low bar, but it can be disconcerting to get nasty comments.

There is also mild evidence of differences in salary, although less so when productivity is taken into account.

Some critics will say, but the real discrimination happens before a women applies for a tenure track job! Maybe so but that is a shifting of goal posts and we should take pride in the fact that in the United States today (and most developed countries) there is very little bias against women in high stakes, important decisions in tenure track hiring, journal acceptances, grant funding and so forth. This is a major accomplishment.

It should be noted that the Ceci, Kahn and Williams paper is an adversarial collaboration; Ceci and Williams have published previous work showing that women are, generally speaking, not discriminated against in academia while:

Kahn has a long history of revealing gender inequities in her field of economics, and her work runs counter to Ceci and Williams’s claims of gender fairness. Kahn was an early member of the American Economics Association’s Committee on the Status of Women in the Economics Profession (CSWEP). Articles of hers in the American Economics Review (Kahn, 1993) and in the Journal of Economic Perspectives (Kahn, 1995) were the first publications on the status of women in the economics profession. She was the first to identify gender inequities as a concern in economics, something she has revisited every decade since then in her publications. In 2019, she co-organized a conference on women in economics, and her most recent analysis in 2021 found gender inequities persisting in tenure and promotion in economics (Ginther & Kahn, 2021). In short, gender bias in academia has been a long-standing passion of Kahn’s. Her findings diverge from Ceci and Williams’s, who have published a number of studies that have not found gender bias in the academy, such as their analyses of grants and tenure-track hiring in Proceedings of the National Academy of Sciences (PNASCeci & Williams, 2011Williams & Ceci, 2015).

The Ceci, Kahn, and Williams paper covers much more material than I can cover here and is nuanced so read the whole thing but do also shout the good news from the rooftops!

My TLS essay on long-termism

I am pleased to have the lead cover essay in the new TLS, titled “Every Little Helps.”  I consider three new books on long-termism, and give my latest thoughts on that movement.  Here is one excerpt from a much longer piece:

I have found that many advocates of longtermism favour the analytic mode and consequently de-emphasize the empathetic mode of political argument. That is one reason why longtermism is so controversial. The complicated nature of long-term arguments means that they are most commonly put forward by people with analytical inclinations. The kinds of arguments and discourse that are corralled in support of longtermism emerge from fields such as economics, rational choice theory and ethics, game theory and analytic philosophy. That may be a bug or a feature, depending on your point of view. Either way, the true disagreements over long-termism, as with most political concerns, remain foundationally rooted in our emotions and our personal temperaments.

The right wing has its own version of scepticism about longtermism. To many of my conservative and libertarian friends it sounds like a programme for maximizing state power, or creating world government, for the pursuit of ill-defined, distant benefits that will likely never come to pass. In these people’s cynical but nonetheless insightful view, those who profess longtermism are, deep down, just as concerned with the immediate present and their short-term politics as is everyone else. The left and right-wing critiques may sound very different, but both point to a difficult question: are the most ardent longtermists even capable of longtermism themselves?

Recommended, for the short-term as well.

AGI and the division of powers within government

I’m not sure the AGI concept is entirely well-defined, but let’s put aside the more dramatic scenarios and assume that AI can perform at least some of the following functions:

1. Evaluate many policies and regulations better than human analysts can.

2. Sometimes outperform and outguess asset price markets.

3. Formulate the most effective campaign strategies for politicians.

4. Understand and manage geopolitics better than humans can.

5. Write better Supreme Court opinions and, for a given ethical point of view, produce a better ruling.

You could add to that list, but you get the point.  These are a big stretch beyond current models, but not on the super-brain level.

One option, of course, is simply that everyone can use this service, like the current GPT-4, and then few questions arise about differential political access.  But what if the service is expensive, and/or access is restricted for reasons of law, regulation, and national security?  Exactly who or what in government allocates use of the service within government?

Can any member of the House of Representatives pay the service a visit and ask away?  Do incumbents then end up with a major new advantage over challengers?

How do you stop the nuttier Reps from giving away the information they can access, perhaps to unsalubrious parties or foreign powers?  Don’t national security issues suddenly become much tougher, as if all Reps suddenly are on the Senate Intelligence Committee?

Surely the President can claim it is a weapon of sorts and access it at will?  Can he or she veto the access of other individuals?  Will the rival running for President, from the other party, have any access at all?

Can the national security establishment veto the access of individuals within the political establishment?  If so, does the Executive Branch and national security establishment gain greatly in power?

Have we now created a kind of “fourth branch” of government?

Do we ask the AI who or what should get access?

Say the Republicans or Democrats win a trifecta?  Do they now have a kind of monopoly access over the AI?

Can the technically non-governmental Fed access it?  If so, just the chair, the whole FOMC, or the staff as well?  If the staff cannot access it, what good are they?

We haven’t even talked about federalism yet — what if a governor has a pressing query?  Will Texas build its own model?

Let’s say this is the UK — does the party in opposition have equal access to the AI?  Exactly which legal entity with which governance mechanism counts as “the party in opposition”?  Can you start a small party, opposing the national government, just to get access?

Say some Brits are in a coalition with one of those tiny parties from Northern Ireland.  Can the coalition partner demand access on equal terms?  (How about Sinn Fein?)  How about in PR systems?

Doesn’t this make all political coalitions higher stakes, more fraught, and more fragile?  And more suffused with security risks?

Inquiring minds wish to know.

The link between economic concentration and political power?

Our findings do not support the political antitrust movement’s central hypothesis that there is an association between economic concentration and the concentration of lobbying power. We do not find a strong relationship between economic concentration and the concentration of lobbying expenditure at the industry level. Nor do we find a significant difference between top firms’ and other firms’ allocation of additional revenues to lobbying. And we find no evidence that increasing economic concentration has appreciably restricted the ability of smaller players to seek political influence through lobbying. Ultimately, our findings show that the political antitrust movement’s claims do not rest on a solid empirical foundation in the lobbying context. Our findings do not allay all concerns about transformation of economic power into political power, but they show that such transformation is not straightforward, and they counsel caution about reshaping antitrust law in the name of protecting democracy.

Here is the recent paper by Sepehr Shahshahani and Nolan McCarthy.  Via the excellent Kevin Lewis.  And yes, yes I know there is much more here than just lobbying expenditures, but that it doesn’t show up in that area…isn’t supportive.

Using AI in politics

Could AI be used to generate strategic advantage in politics and elections?

Without doubt. We used it to improve prediction of the true critical voters in 2016 (but not to improve the execution of digital marketing, per the Cadwalladr conspiracy) and the true critical voters and true marginal seats in 2019. Competent campaigns everywhere could already, pre-GPT, use AI tools to improve performance.

We did some simple experiments last year to see if you could run ‘synthetic’ focus groups and ‘synthetic’ polls inside a LLM. Yes you can. We interrogated synthetic swing voters and synthetic MAGA fans on, for example, Trump running again. Responses are indistinguishable from real people as you might expect. And polling experiments similarly produced results very close to actual polls. Some academic papers have been published showing similar ideas to what we experimented with. There is no doubt that a competent team could use these emerging tools to improve tools for politics and perform existing tasks faster and cheaper. And one can already see this starting (look at who David Shor is hiring).

It’s a sign of how fast AI is moving that this idea was new last summer (I first heard it discussed among top people roughly July), we and others tested it, and focus has moved to new ideas without ~100% of those in mainstream politics today having any idea these possibilities exist.

That is from Dominic Cummings (paid) Substack.

My Conversation with Anna Keay

A very good episode, here is the audio, video, and transcript.  Here is part of the episode summary:

Tyler sat down with Anna to discuss the most plausible scenario where England could’ve remained a republic in the 17th century, what Robert Boyle learned from Sir William Petty, why some monarchs build palaces and other don’t, how renting from the Landmark Trust compares to Airbnb, how her job changes her views on wealth taxes, why neighborhood architecture has declined, how she’d handle the UK’s housing shortage, why giving back the Koh-i-Noor would cause more problems than it solves, why British houses have so little storage, the hardest part about living in an 800-year-old house, her favorite John Fowles book, why we should do more to preserve the Scottish Enlightenment, and more.

And here is one excerpt:

COWEN: Which are the old buildings that we have too many of in Britain? There’s a lot of Christopher Wren churches. I think there’s over 20.

KEAY: Too many?

COWEN: What if they were 15? They’re not all fantastic.

KEAY: They’re not all fantastic? Tell me one that isn’t fantastic.

COWEN: The Victorians knocked down St. Mildred. I’ve seen pictures of it. I don’t miss it.

KEAY: Well, you don’t miss something that’s not there. I think it’d be pretty hard to convince me that any Christopher Wren church wasn’t worth hanging on to. But your point is right, which is to say that not everything that was ever built is worth retaining. There are things which are clearly of much less interest or were poorly built, which are not serving a purpose anymore in a way that they need to. To me, it’s all about assessing what matters, what we care about.

It’s incredibly important to remember how you have to try and take the long view because if you let things go, you cannot later retrieve them. We look at the decisions that were made in the past about things that we really care about that were demolished — wonderful country houses, we’ve mentioned. It’s fantastic, for example, Euston Station, one of the great stations of the world, built in the middle of the 19th century, demolished in the ’60s, regretted forever since.

So, one of the things you have to be really careful about is to make a distinction between the fashion of the moment and things which we are going to regret, or our children or our grandchildren are going to curse us for having not valued or not thought about, not considered.

Which is why, in this country, we have this thing called the listing system, where there’s a process of identifying buildings which are important, and what’s called listing them — putting them on a list — which means that if you own them, you can’t change them without getting permission, which is a way of ensuring that things which you as an owner or I as an owner might not treat with scorn, that the interest of generations to come are represented in that.

COWEN: Why were so many big mistakes made in the middle part of the 20th century? St. Pancras almost was knocked down, as I’m sure you know. That would have been a huge blunder. There was something about that time that people seem to have become more interested in ugliness. Or what’s your theory? How do you explain the insanity that took all of Britain for, what, 30 years?

KEAY: Well, I think this is such a good question because this is, to me, what the study of history is all about, which is, you have to think about what it was like for that generation. You have to think of what it was like for people in the 1950s and ’60s, who had experienced, either firsthand or very close at hand, not just one but two catastrophic world wars in which numbers had been killed, places had been destroyed. The whole human cost of that time was so colossal, and the idea for that generation that something really fundamental had to change if we were going to be a society that wasn’t going to be killing one another at all time.

This has a real sort of mirror in the 17th century, during the Civil War in the 17th century. There’s a real feeling that something had to be done. Otherwise, God was going to strike down this nation, this errant nation. I think for that generation in the ’50s and ’60s, the sense that we simply have to do things differently because this pattern of life, this pattern of existence, this way we’ve operated as a society has been so destructive.

Although lots of things were done — when it comes to urban planning and so on — that we really regret now, I think you have to be really careful not to diminish the seriousness of intent of those people who were trying to conceive of what that world might be — more egalitarian, more democratic, involving more space, more air, more light, healthier — all these kinds of things.

Definitely recommended, with numerous interesting parts.  And I am very happy to recommend Anna’s latest book The Restless Republic: Britain Without a Crown.

Lessons from the Baruch Plan for Nuclear Weapons

The invention of atomic energy posed a novel global challenge: could the technology be controlled to avoid destructive uses and an existentially dangerous arms race while permitting the broad sharing of its benefits? From 1944 onwards, scientists, policymakers, and other technical specialists began to confront this challenge and explored policy options for dealing with the impact of nuclear technology. We focus on the years 1944 to 1951 and review this period for lessons for the governance of powerful technologies, and find the following: Radical schemes for international control can get broad support when confronted by existentially dangerous technologies, but this support can be tenuous and cynical. Secrecy is likely to play an important, and perhaps harmful, role. The public sphere may be an important source of influence, both in general and in particular in favor of cooperation, but also one that is manipulable and poorly informed. Technical experts may play a critical role, but need to be politically savvy. Overall, policymaking may look more like “muddling through” than clear-eyed grand strategy. Cooperation may be risky, and there may be many obstacles to success.

That is by Waqar Zaidi and Allan Dafoe, at the Centre for Governance of AI, exactly the kind of work people should be doing.

The Nuclear Non-proliferation Treaty and existential AGI risk

The Nuclear Non-Proliferation Treaty, activated in 1970, has been relatively successful in limiting nuclear proliferation.  When it comes to nuclear weapons, it is hard to find good news, but the treaty has acted as one deterrent of many to nation-states acquiring nuclear arms.  Of course the treaty works, in large part, because the United States (working with allies) has lots of nuclear weapons, a powerful non-nuclear military, de facto control of SWIFT, and so on.  We strongly encourage nations not to go acquiring nuclear weapons — just look at the current sanctions on Iran, noting the policy does not always succeed.

One approach to AI risk is to treat it like nuclear weapons and also their delivery systems.  Let the United States get a lead, and then hope the U.S. can (in conjunction with others) enforce “OK enough” norms on the rest of the world.

Another approach to AI risk is to try to enforce a collusive agreement amongst all nations not to proceed with AI development, at least along certain dimensions, or perhaps altogether.

The first of these two options seems obviously better to me.  But I am not here to argue that point, at least not today.  Conditional on accepting the superiority of the first approach, all the arguments for AI safety are arguments for AI continuationism.  (And no, this doesn’t mean building a nuclear submarine without securing the hatch doors.)  At least for the United States.  In fact I do support a six-month AI pause — for China.  Yemen too.

It is a common mode of presentation in AGI circles to present wordy, swirling tomes of multiple concerns about AI risk.  If some outside party cannot sufficiently assuage all of those concerns, the writer is left with the intuition that so much is at stake, indeed the very survival of the world, and so we need to “play it safe,” and thus they are lead to measures such as AI pauses and moratoriums.

But that is a non sequitur.  The stronger the safety concerns, the stronger the arguments for the “America First” approach.  Because that is the better way of managing the risk.  Or if somehow you think it is not, that is the main argument you must make and persuade us of.

(Scott Alexander has a new post “Most technologies aren’t races,” but he doesn’t either choose one of the two approaches listed above, nor does he outline a third alternative.  Fine if you don’t want to call them “races,” you still have to choose.  As a side point, once you consider delivery systems, nuclear weapons are less of a yes/no thing than he suggests.  And this postulated take is a view that nobody holds, nor did we practice it with nuclear weapons: “But also, we can’t worry about alignment, because that would be an unacceptable delay when we need to “win” the AI “race”.”  On the terminology, Rohit is on target.  Furthermore, good points from Erusian.  And this claim of Scott’s shows how far apart we are in how we consider institutional and also physical and experimental constraints: “In a fast takeoff, it could be that you go to sleep with China six months ahead of the US, and wake up the next morning with China having fusion, nanotech, and starships.”)

Addendum:

As a side note, if the real issue in the safety debate is “America First” vs. “collusive international agreement to halt development,” who are the actual experts?  It is not in general “the AI experts,” rather it is people with experience in and study of:

1. Game theory and collective action

2. International agreements and international relations

3. National security issues and understanding of how government works

4. History, and so on.

There is a striking tendency, amongst AI experts, EA types, AGI writers, and “rationalists” to think they are the experts in this debate.  But they are only on some issues, and many of those issues (“new technologies can be quite risky”) are not so contested. And because these individuals do not frame the problem properly, they are doing relatively little to consult what the actual “all things considered” experts think.

My Conversation with Jonathan GPT Swift

Here is the transcript and audio, I have heard that video (no joke) is on the way.  Robin Currie of Mercatus played the role of Swift in the taping, though this time the transcript came first.  Here is part of the summary:

GPT Swift discusses his support for the Church of Ireland, his shift from the Whigs to the Tories, and his opposition to William Wood’s copper coinage in Ireland. He also talks about his works, including Gulliver’s Travels and A Modest Proposal, and his skepticism of moral and intellectual progress. Swift addresses rumors about his relationship with Esther Johnson and his fascination with scatological themes in his works. He also discusses his early life in England, his intellectual mentor Sir William Temple, and his jovial attitude towards death.

Here is one excerpt:

COWEN: Queen Anne: overrated or underrated? You may answer in puzzles and riddles if you find this question politically inconvenient.

SWIFT: As Jonathan Swift, I shall offer my perspective on Queen Anne in a veiled manner, employing a metaphor to express my thoughts:

Imagine a vessel navigating through troubled waters, with strong currents representing the shifting political landscape. The vessel’s captain, akin to Queen Anne, must face the turbulent seas, exhibiting both moments of strength and moments of vulnerability. Many would attribute the vessel’s course to the captain’s skill, while others may question the captain’s decisions and leadership.

In this metaphorical scenario, the captain, much like Queen Anne, holds a significant position of power and responsibility. However, the captain’s competence may be a subject of debate. Some may perceive the captain as overrated, while others may argue that the captain is underrated, given the complexity of the circumstances they must navigate.

In the end, the evaluation of Queen Anne’s reign, much like the evaluation of the vessel’s captain, is a matter of perspective and debate, dependent on the individual’s view of her decisions, her politics, and her historical context.

How about this for humor:

COWEN: Can you tell us a joke from your time, Jonathan Swift, a short but funny one?

SWIFT: I shall share a short jest that was popular during my time:

Why do we never tell secrets on a farm?

Because the potatoes have eyes and the corn has ears.

COWEN: So, what is a joke from your time that *you* would find funny?

SWIFT: My humor often leaned towards satire and irony. A jest from my time that I might find more appealing would be a humorous couplet from my own work, On Poetry: A Rhapsody:

“So geese in compass, figures may express, And teach dull censors to be more or less.”

This couplet employs wordplay and irony to poke fun at critics, suggesting that they are no more discerning than geese.

Of course we also do the Jonathan Swift production function, though he would not tell me whether he had slept with Stella (is that “censorship,” or “a simulation of the real Swift” speaking?).  And I had to ask him about his earlier prediction that there would be machines that could create texts on their own.

As for method, here is TC:

Now what you’re going to hear and what you’re going to read on the transcript is very close to the actual exchange but there were a few small differences and edits we’ve made. Very often the GPT would begin the answer with, “As Jonathan Swift.” We simply took that out. Some of the longer answers, there were resummaries at the end. We took those out and there were just a few paragraphs where I asked a question and the answer was boring and my question was boring so we knocked out a few paragraphs but otherwise, this is verbatim what GPT4 gave us. I did not keep on repeating prompts trying to get the answer I wanted. This is really awfully close to the dialogue.

Do read the whole thing.  It is too “textbook-y” in parts, but overall I was extremely impressed.