Why Every Politician Thinks They’re So Right (and Why That’s a Disaster)
Since childhood, I have been troubled by the following paradox:
Suppose that in some country there are several parties. Each of them has its own vision of how to achieve economic and all other kinds of prosperity. Let’s assume they are all driven purely by the desire to help the country[1].
Suppose these parties do certain things that are destructive to the country but effective for gaining power — for example, things that are obviously bad if you thought about them for 10 minutes, but most people didn’t spend those 10 minutes (e.g., direct governmental control of some companies).
The paradox is this: from the outside it seems that if all the parties simply stopped engaging in populism together, the country would be better off, because if everyone stopped doing populism at the same time, the same party would end up in power, but it would no longer be forced to fulfill silly pre-election promises.
However, if you are one of the party leaders, it seems to you that if you use populism to come to power, you will be able to apply your truest vision of the economy, not only to repair the damage from populism, but ultimately to come out ahead. It is very strange that from the outside, for the good of the people, you should not use populism, but from the inside—you should.
What would a politician of this country say if I explained this to him? I think something like: “Well, other parties are just wrong, and we are not; if they use populism, that’s bad because they do it to obtain power to implement their bad policies, and our policies are good.”
Here there is a counter-argument understandable to anyone: “Almost all people (at least all your political opponents) make mistakes; that is, people do not know how to seek truth, and often are extremely certain of something and then turn out to be wrong. And now, the climax: you are a human!”
[Read the last three lines two more times]
“But I am smarter than average!”
“Some of your political opponents are also smarter than average.”
Do you doubt that people are mistaken so often? Look at those who disagree with you on any political question, or on the question of religion, and at how confident they are. I witnessed how my mother’s acquaintance was puzzled about how her acquaintance could fail to understand the obvious thing that Ukrainian Orthodoxy is better than Russian. Another acquaintance of my mother added that since her friend could not understand such obvious arguments in favor of Ukrainian Orthodoxy, she must be crazy. To you this may seem funny, because you are a Protestant or Catholic. To me it is even funnier, because I am an atheist.
Even if you already understand that one should not use dirty tricks to obtain power, I would like to resolve the paradox from another side.
Let us imagine such a situation: half the inhabitants of the world believe in political theory A, and the other half—in political theory B. Expert opinions are also split in half. The experts believing in theory A appear just as educated in politics and just as intelligent as the experts believing in B.
What is the probability that A is right? 50%, if we do not take into account the possibility that both are wrong.
Now, replace A with a position on a controversial political question, where opinions are evenly divided, and B with the opposite position. Now, of course it seems to you that position A is correct with ≈100%.
But why does it seem so to you? Are you a super-genius, and the reasoning of others compared to yours is simply useless? When you took an IQ test, did you solve every single task perfectly, so that no one can even understand just how smart you are? Or have you studied collective disagreements for 30 years, and now you are so good at it that you can describe in detail every reasoning error of your political opponents, and if you explain it to them, they will immediately change their opinion? No? Well then, your conclusion is no better than that of any random person.
(In fact, I consider the guideline “until you convince 7 out of 10 of your political opponents of your ideology, do not do anything too large-scale” very useful. If the truth is on your side, you will be able to convince others without using dirty tricks if you have enough time, won’t you? And if you cannot, then either you are wrong, or people do not know how to argue effectively, and in that case, how can you be sure that you are not believing complete nonsense on all issues, but no one can convince you otherwise because you, as a human, do not know how to argue?)
I hope you were frightened by the problem I pointed out, by this wound of the world destroying the destinies of whole countries, but which people do not notice. So how do we fight it?
First of all, you can use heuristics. For example, if there are positions C and D, and the population is equally divided between them, but almost all experts are confident in C, and the remaining ones seem to be connected to companies that benefit from people believing in D, then one should believe in C.
But how to decide what to believe if you are going to become an expert? If you just repeat after other experts, you will add nothing to the discussion (by the way, if you do this, UNDER NO CIRCUMSTANCES should you forget to mention that you believe in a certain position only because other experts believe in it. This will save us from many collective traps, like the one where all “experts” believe in C only because other “experts” say they believe in C).
To form your own opinion, you need to debate. Debate a lot.
Professional politicians spend thousands of hours of their lives on political struggle. It seems reasonable to spend at least 100 hours in debates, so as not to fight on the side of evil all your life without knowing it.
“But I have probably spent 100 hours watching videos of the opposite side and coming up with replies!”
The other side also watches your videos and also comes up with convincing rebuttals of what was said, so this is clearly not the path that can lead you to the truth.
Watching videos of your political opponents and inventing elegant refutations of their silly arguments is an order of magnitude less effective than debate. I have seen many debates, and most of the content is devoted to discussing things that are not particularly relevant.
If you ask any non-communist why he is not a communist, he will answer that if you abolish rewards for labor, people will not work. In fact, communists believe that abolishing rewards for labor will make people more altruistic, and they will work for free. This is the real root of disagreement, and this is what all debates about communism should be about, but in reality online debates about it usually drift into something completely unrelated to this stumbling stone, because debaters think that their silly viewers can only understand crooked analogies and historical examples. If you want to make sure that communism does not work, find a real communist and try to persuade him—then, if you misunderstand the essence of their arguments, he will point it out to you. Even if in the end he changes his opinion, you will realize that debating with a living person feels different from thinking over a video. A living person will use arguments you would never have thought of, which, even if wrong, require significant effort to refute (otherwise he would have refuted them himself already).
Here are some tips on how to conduct debates:
Respect your interlocutor, never use insults.
Say only those arguments that, if you found out they were false, would weaken your confidence in the position you defend (if an argument does not meet this criterion, then it simply has nothing to do with the conclusion, and any result of its discussion will not change your opponent’s opinion either).
Use the technique from this article:
Repeat the previous tips to your interlocutor if he does not follow them.
(Why did I even write about this political overconfidence, if Eliezer mentioned some kind of similar logic in the Sequences? Because we cannot make it so that everyone reads the Sequences, but we can make it so that a significant part of the population reads this article. The world still suffers from the opinion that those who disagree with you are simply crazy or evil, and therefore politicians are overconfident in their views, and instead of spending energy on double-checking whether they are right, or on good debate with opponents, they spend all their energy inventing better ways to throw sand in the voters’ eyes so that they, even for stupid reasons, believe in their ideology. Therefore, I would like you to share this article with your acquaintances who are not rationalists.)
Another thing we can use instead of debates is experiments. Just imagine: instead of arguing for decades about whether higher minimum wages cause unemployment or not, and changing policy every 4 years so that under half of U.S. presidents ineffective economic policy is carried out, we simply take two towns of 10,000 people, almost identical in all respects, and in one we set a high minimum wage, in the other a low one, and look at the results. Yes, one of these towns will suffer, but when the experiment is over, a 340-million country will not suffer under half its presidents.
In fact, such experiments should be conducted on most political questions.
Deng Xiaoping, before introducing many capitalist reforms, implemented them in one province and looked at the results. China is out of poverty now.
Some political ideas will almost certainly not work—that is, with a probability of 1% they will greatly benefit society, but with a probability of 99% they will destroy it. It is reasonable to test such an idea in a small town of 10,000 inhabitants from the point of view of the country’s good, but from the point of view of the town’s inhabitants, this will almost certainly destroy it. Therefore, it would be fair if the federal government, after the destruction of the town, allocated a lot of money for its restoration, to fully compensate for the cost of the experiment. Such experiments will never be conducted under the current system, because no mayor could sell to the voters the near-certain destruction of their town.
Conducting those experiments is clearly a reasonable solution, so why is it not used constantly? There are two reasons. The first and most important—it is too complicated: legislators’ time is limited, and they simply cannot constantly launch experiments simultaneously with their main work. This problem is not difficult to solve: it is enough just to create a “Ministry of Experiments,” which would not need to have every experiment approved by parliament, but whose members could be fired for bad work, like judges.
The second reason—if a leader is so sure that communism (or something else) works, then why bother with experiments at all? Just introduce communism throughout the country at once, despite the fact that it has never been implemented anywhere before, and send all dissenters to the gulag. What may go wrong???
Conclusion: if you have not found obvious mistakes in this text, which the author does not notice out of his human stupidity, then it would be very useful for society if you shared this article with your acquaintances. Otherwise, I would be glad to hear your criticism in the comments.
(maybe) To be continued: How to get rid of populism?
- ^
I’m talking about the majority of the population or party members, not about political leaders. But imagine that political leaders are altruistic too—just for a thought experiment.
I think this post greatly overestimates how many political disagreements depend on fact and science, and underestimates how many depend on values and morality.
This. Many fundamental disagreements have more to do with where to land on the Pareto frontier of trade offs between different moral values than what truth is. Freedom vs security, justice vs mercy, independence vs community, etc. There aren’t necessarily any “true” answers to these questions.
Obviously, this isn’t always the case and plenty of positions are not on the Pareto frontier, but it’s more complicated than a scale from right to wrong.
I’m pretty sure that I couldn’t convince a creationist that evolution is correct. And not because creation and evolution each have a 50% chance of being correct.
what if you have enough time and they know how to discuss correctly?
No, I couldn’t. Because the object level is important. Both evolutionists and creationists can say that the other side is biased, refuses to look at evidence, etc. But when it comes to creation versus evolution, only one side actually is. The symmetry collapses into asymmetry. Creation versus evolution is a prime example of your thesis being wrong. There are two sides, they can’t convince each other, they say the other side is reasoning poorly… and yet someone who understands evolution can fairly and honestly say that their position is about 100% correct.
I agree that any discussion of god-related topics might take several times longer, since you’d have to go into cognitive biases. You’d probably need to explain Bayesianism—or even argue for it—before you could move on. In the worst case, you’d have to drop them Sequences: highlighted. Okay, they won’t read it, because it’s hundreds of pages long, and because Eliezer constantly speaks out against religion, so believers wouldn’t enjoy reading it anyway.
Right, that would take an absurd amount of time.
Still, I personally only estimate the probability that creationists are wrong at about 80%, simply because I haven’t really looked into their line of argumentation, and I’ve never even debated a believer seriously. Intuitively, it feels absurd to deny something without really understanding what exactly it is you’re denying.
Okay then, let’s use homeopathy as an example. I can fairly and honestly say that my position—which is that homeopathy is crap—is basically 100% correct. Or Holocaust deniers. I can fairly and honestly say that my position—which is that the Holocaust was real—is basically 100% correct.
Saying “everyone’s human, every side has smart people on it, so the sides are 50% correct” doesn’t work. Holocaust deniers are certainly human, and they’re not stupid. But they and I are not equally correct.
(I’d also ask, if you’re going to exclude god-related topics because of cognitive biases, how is that not special pleading? In other contexts, you reject the idea of saying “my political opponents have cognitive biases”. After all we’re all human, all sides have smart people, etc.)
I don’t mean that the probability is always 50⁄50. But it’s not 100% either.
In Europe, the smartest people for centuries believed in god, and they saw endless confirmations of that belief. And then—bam! It turned out they were simply all wrong.
Or take any case of ancient medicine. European doctors believed for centuries that bloodletting cured everything, while Chinese doctors believed that eating lead prolonged life.
There are also other examples where all the experts were wrong: geocentrism, the ether theory, the idea that mice spontaneously generate in dirty laundry, the miasma theory of disease…
In all these cases it was either about cognitive biases (God, medicine) or about lack of information or broken public discussion (geocentrism).
Today we fight biases much better than a thousand years ago, but we’re still far from perfect.
And we still sometimes operate under very limited information.
I think one should have fundamental rational habits that would protect me from being so sure in god or bloodletting. That’s why, from any conclusion I make, I subtract a few percentage points of confidence. The more complex the conclusion, the more speculative my reasoning or vulnerable to diases, the more I subtract.
If you claim that my way of fighting this overconfidence shouldn’t be used, I’d want you to suggest something else instead. Because you can’t just leave it as it is—otherwise one might assign 99% confidence to some nonsense.
Hypothesis space is so large that it’s absurd to give anything more than a passing glance if it doesn’t make sense and nobody can convince you in a fairly short period that it’s at least worth exploring.
I guess you can fall on radical agnosticism, but it’s hard to recommend any policy or decision based on not knowing anything.
We don’t know, because both of those conditions are false in almost every case.
Unfortunately, we really can’t convince all creationists. We only have time for a few. However, if you pick some and manage to persuade all those who actually have the time for a discussion, at the very least it would give you personally the confidence that you’re right. And if you document it, that would give the same confidence to everyone else. Moreover, if your experiment turned out to be clear-cut enough, it would become a very strong argument to convince believers in god. If I wholeheartedly believed in something, and then found out that someone took 10 people who believed in the exact same thing I do and managed to change their minds, I’d assume he could probably convince me too—so why not save myself the time and just accept right away that I was wrong about this?
How does that update work? I already suspect (say, 95% that creationism is wrong, 92% that evolution and luck explains most of current biological existence) I’m right, and they’re quite wrong. If I convince them, that’s more about them being uncertain and wishy-washy than them being able to provide evidence that I am, in fact, right?
It’s surprising that they can be convinced, so I guess I update a bit against creationists being unwilling to discuss, but that tells me nothing about the underlying question.
Social proof only goes so far, and for most topics between large groups of humans it’s not terribly precise.
Good discussions take a lot of time, so people ≈can’t discuss. Because of that, even if 90% of people believe very wrong things, the other 10% can never convince them. So you may be one of those 90% on any question, and the others can’t explain you that you are wrong, so you shouldn’t be so confident in your reflexions.
So if you know that a few believers found 20 atheists who were ready to discuss a lot, and as a result 5 of them got bored and left the discussion after 5 hours, but the other 15 were convinced, it should be an extremely powerful prior of god’s existence.
I’m fairly confident in some of my predictions for future experience. Never 100%, of course.
But that’s not my point. My point is that searching for truth is only very lightly correlated with convincing idiots that they’re wrong. Good conversations among epistemically-sane (or even intelligent but brainwashed) people are very good for discovering better models and refining your beliefs. Trying to convert the median or worse is not helpful (for knowledge/understanding; it may be helpful for actual power or outcomes).
Interesting model. Probably you are right and I didn’t considered this because all my friends and me are not idiots.
Let’s not assume that, it seems to be incredibly false, and borderline incoherent. They are all driven by different private and public beliefs about which subsets of “the country” are more important than the others. Literally zero “leaders” live anywhere near the median of their populace in terms of wealth or luxury.
There are some legitimate differences in beliefs of policy-contingent measurable outcomes. But most of the power struggle is about power itself, and about how to help the favored/pivotal supporters in order to gain/keep power.
The situation in the real world isn’t as neat as in my thought experiment, but we still see the same dynamic, where people with the same goals end up fighting each other. It’s a hyperbolized example meant to highlight that particular dynamic as clearly as possible, but I don’t claim it’s the only one.
From this I think the far more correct conclusion is that their goals are not the same, but only superficially appear the same. While their real goals, in a more Hansonian sense, deal far more with increasing personal status and the like (instead of whatever lofty policy ambitions they advocate in public).
When writing the article, I assumed that politicians’ altruism reflects the distribution of altruism among the general population, but then I remembered that practically every dictator is concerned only with plundering their country.
Still, a lot of goals are shared by all voters, yet some support one set of politicians while others back their opponents. I acknowledge that there is a genuine value difference between the right and the left—nationalism versus internationalism, in the sense of how much importance is placed on the lives and happiness of foreigners. But there is also a clash over economic issues, and everyone would be better off if both the left and the right understood the point of my article and became less certain in their economic ideas.
I really wish there were more experiments in politics, but most people are unwilling to tolerate them.
In theory different countries could try different policies and see what the outcomes are. Within countries like the United States and Spain where lots of power is devolved to local authorities, even better experiments can be run over very similar populations.
In theory this could work great. One place tries one policy. Another tries another. After 10 years or so, everyone will know which policy worked better, and other places can adopt the better policy, then run more experiments.
The problem, though, is that many people aren’t will to let others run experiments. They’re happy to run local “experiments” of adopting a policy they like, but want to prohibit other countries from running experiments they dislike. Many political battles happen because there’s a lack of willingness to leave people in other jurisdictions alone to try their own policies.
Now, yes, we should try to enforce bans on some policies due to their large negative externalities. That’s why we collaborate to ban the spread of nuclear weapons, to mitigate climate change, etc. But many other policies have few externalities, yet because those policies make us uncomfortable, so we’re unwilling to let people experiment.
I suspect, like many things in politics, that the main issue here is domestic politics more than foreign affairs.
If you’ve ever compared election results between single and multi-member systems, you’ll have noticed a trend. Even if via first preference count, a minor party seems to best represent a significant chunk of the population, unless they’re geographically concentrated you can expect them to pick up on the order of ~0 seats.
Similarly, if we’re not going to abandon democratic principles, we should probably have the consent of the majority in an area before we perform an experiment on them. Problem with this is that even if world/country wide there’s a quorum of people who would consent to a given experiment, it’s highly unlikely that they all live in the same place.
While something like a Schengen area might in principle alleviate some of these concerns, it introduces two main additional ones:
1) Does your experiment actually improve society? Or does it just attract the types of people who improve society themselves?
2) Most people aren’t a big fan of being told they have to move cities/countries to continue living their lifestyle. I suspect that Lesswrong users as a cohort undervalue stability relative to the rest of the population.
I don’t understand this, and the use of ‘populism bad’ in general.
I understand populism to consist of appealing to the mass of ordinary people and promising them things they want, in exchange for votes—even if those things run counter to the interests of established institutions and agencies.
How is this different to any other rational action taken by politicians seeking to be elected in a democratic society?
In a democracy, you need votes, and lots of them. People will give you their vote if they feel you will do good things for them. You hear what they say and promise to enact it if you are elected. Other people are unhappy about that, but you do it anyway.
Is that populism, or is it describing every election ever?
I know this is overly simplistic! I don’t understand it enough to steelman ‘populism bad’.
What are the most compelling arguments for ‘populism bad, and populism different to normal political activity’?
Thank you for your comment, I changed this part so it is cleaner now
I believe the implication of decrying something as populist is that it would not actually be good for the masses. So a populist promise is one that the masses want and think will be good for them, but in actuality would be bad for them. Then a populist politician is one that promises popular policies regardless of whether they will be net good or bad.
I think whether or not someone considers populism bad is downstream of whether or not they think the masses can accurately assess what would be good for them.
Enjoyed, thanks! And agree with rather everything. FWIW:
Economic policy experiments happen very regularly (applied economic research), but you’re still right: they’re costly (I guess one could say because we cannot randomly ‘mistreat’ people/a town, we can rather give it only a treatment where arguably they clearly cannot loose out compared to status quo) and we lack enthusiasm (or your Ministry for Experiments) thus still too rare and too small and cautious, very much in line with what you write
Ideas in direction of “Independent and Competing Institutions” is another idea towards similar aim: have no unique block ‘country’ gvmt, but independent services with providers competing (in practice I think it’s difficult but maybe worth investigating deeper)
Different point:
Values! Sometimes differences in ultimate values i.e. ultimate preferences actually exist, and can lead to very different conclusions without anyone actually necessarily being ‘wrong’ unless you’re sure you really want to call something ‘wrong preference’.
Firstly, thank you! Praise is very important for beginning writers.
Agreed with 1 and 3.
Even without an A/B comparison, if policies came with measures of success, that would go a long way to steering into better policies. Do school vouchers improve outcomes for students? It seems plausible, but we should be able to track graduation rates, and GPAs. Maybe we can even agree that that is an important goal. If after 5 years, those measures are not showing significant improvement, we can conclude that the voucher program didn’t meet its goals, and at the very least the policy needs to change, if not directly reversed.
It’s not perfect, as there can be confounding effects, but by tying the life of a policy to success metrics (that hopefully would be easier to agree on), we can at least we can show progress, and rule out the worst ideas.