Tag Archives: economics

Economic growth and parallelization of work

Eliezer suggests that increased economic growth is likely bad for the world, as it should speed up AI progress relative to work on AI safety. He reasons that this should happen because safety work is probably more dependent on insights building upon one another than AI work is in general. Thus work on safety should parallelize less well than work on AI, so should be at a disadvantage in a faster paced economy. Also, unfriendly AI should benefit more from brute computational power than friendly AI. He explains,

“Both of these imply, so far as I can tell, that slower economic growth is good news for FAI; it lengthens the deadline to UFAI and gives us more time to get the job done. “…

“Roughly, it seems to me like higher economic growth speeds up time and this is not a good thing. I wish I had more time, not less, in which to work on FAI; I would prefer worlds in which this research can proceed at a relatively less frenzied pace and still succeed, worlds in which the default timelines to UFAI terminate in 2055 instead of 2035.”

I’m sympathetic to otherscriticisms of this argument, but would like to point out a more basic problem, granting all other assumptions. As far as I can tell, the effect of economic growth on parallelization should go the other way. Economic progress should make work in a given area less parallel, relatively helping those projects that do not parallelize well.

Economic growth, without substantial population growth, means that each person is doing more work in their life. This means the work that would have otherwise been done by a number of people can be done by a single person, in sequence. The number of AI researchers at a given time shouldn’t obviously change much if the economy overall is more productive. But each AI researcher will have effectively lived and worked for longer, before they are replaced by a different person starting off again ignorant. If you think research is better done by a small number of people working for a long time than a lot of people doing a little bit each, economic growth seems like a good thing.

On this view, economic growth is not like speeding up time – it is like speeding up how fast you can do things, which is like slowing down time. Robotic cars and more efficient coffee lids alike mean researchers (and everyone else) have more hours per day to do things other than navigate traffic and lid their coffee. I expect economic growth seems like speeding up time if you imagine it speeding up others’ abilities to do things and forget it also speeds up yours. Or alternatively if you think it speeds up some things everyone does, without speeding up some important things, such as people’s abilities to think and prepare. But that seems not obviously true, and would anyway be another argument.

Value realism

People have different ideas about how valuable things are. Before I was about fifteen the meaning of this was ambiguous. I think I assumed that a tree for instance has some inherent value, and that when one person wants to cut it down and another wants to protect it, they both have messy estimates of what it’s true value is. At least one of them had to be wrong. This was understandable because value was vague or hard to get at or something.

In my year 11 Environmental Science class it finally clicked that there wasn’t anything more to value than those ‘estimates’.  That a tree has some value to an environmentalist, and a different value to a clearfelling proponent. That it doesn’t have a real objective value somewhere inside it. Not even a vague or hard to know value that is estimated by different people’s ‘opinions’. That there is just nothing there. That even if there is something there, there is no way for me to know about it, so the values I deal with every day can’t be that sort. Value had to be a two place function. 

I was somewhat embarrassed to have ever assumed otherwise, and didn’t really think about it again until recently.  It occurred to me recently that a long list of strange things I notice people believing can be explained by the assumption that they disagree with me on whether things have objective values. So I hypothesize that many people believe that value is a one place function which takes a thing as its argument, not a two place function of an agent and a thing.

Here’s my list of strange things. For each I give two explanations: why it is false, and why it is true if you believe in objective values. Note that these are generally beliefs that cause substantial harm:

When two people trade, one of them is almost certainly losing:

Why it’s false: In most cases where two people are willing to trade, this is because the values they assign to the items in question are such that both will gain by having the other person’s item instead of their own.

Why it’s believed: There’s a total amount of value shared somehow between the people’s posessions. Changing the distribution is very likely to harm one party or the other. It follows that people who engage in trade are suspicious, since trades must be mostly characterized by one party exploiting or fooling another.

Trade can be exploitative:

Why it’s false: Assuming exploitation is bad for he who is exploited, if a person chooses to trade, we can assume he is either not exploited or is deceived. Free choice is a filter: it causes people who would benefit from an activity to do it while people who wouldn’t do not.

Why it’s believed: If a person is desperate he might sell his labor for instance at a price below its true value. Since he is forced by circumstance to trade something more valuable for something less valuable, he is effectively robbed.

Prostitution etc should be prevented, because most people wouldn’t want to do it freely, so it must be pushed on those who do it:

Why it’s false: Again, free choice is a filter.

Why it’s believed: If most people wouldn’t be prostitutes, it follows that it is probably quite bad. If a small number of people do want to be prostitutes, they are probably wrong. The alternative is that they are correct, and the rest of society is wrong. It is less likely that a small number of people is correct than a large number. Since these people are wrong, and their being wrong will harm them (most people would really hate to be prostitutes), it is good to prevent them acting on either their false value estimates, or coercion.

If being forced to do X is dreadful, X shouldn’t be allowed:

Why it’s false: Again, choice is a filter. For an arbitrary person doing X, it might terrible, but it is still often good for people who want it. Plus, being forced to do a thing often decreases its value.

Why it’s believed: Very similar to above. The value of X remains the same, regardless of who is thinking about it, whether they are forced to do it. That a person would choose to do a thing others are horrified to have pressed on them, that just indicates that the person is mentally dysfunctional in some way.

Being rich indicates that you are evil:

Why it’s false: Since in every trade, both parties are benefited, being rich indicates that you have contributed to others receiving a large amount of value.

Why it’s believed: Since in every trade, someone wins and someone loses, anyone who has won at trading so many times is evidently an untrustworthy and manipulative character.

Poor countries are poor because rich countries are rich:

Why it’s false: That the rich countries don’t altruistically send a lot of aid into the poor countries is reason perhaps, though it’s not clear that this would help in the long run. Beyond that there’s no obvious connection.

Why it’s believed: There’s a total amount of value to be had in the world. The poor can’t become richer without the rich giving up some value.

The primary result of promotion of products is that people buy things they don’t really want:

Why it’s false: The value of products depends on how people feel about them, so it is possible to create value by changing how people feel about them.

Why it’s believed: Products have a fixed value. Changing your perception of this in the direction of you buying more of them is cheatful sophistry.

***

Questions:

Is my hypothesis right? Do you think of value as a one or two place function? (Or more?) Which of the above beliefs do you hold? Are there legitimate or respectable cases for value realism out there? (Moral realism is arguably a subset).

Stop blaming efficiency

Andrew Sullivan, quoting and commenting on Adam Frank:

We’re more efficient than we’ve ever been, but extreme efficiency has drawbacks:

More efficient forestation means running through forests faster. More efficient fishing methods means running through natural fishing stocks faster. … The truth is that we have limits. True connections between family, friends and colleagues can not be compressed down to tightly scheduled “quality time.” The relentless logic of efficiency can unintentionally strip the most valued qualities of human life just as easily as it strips forests.

Under a common meaning, ‘efficiency’ is just getting more of what you want for a given cost. Since people want different things, what is efficient for you may be very inefficient for someone else. If you don’t want deforestation, then my efficient tree harvesting method is not an efficient way to pursue your goals. Often people seem to forget this and think of the fact that other people are efficiently pursuing goals they don’t like as a problem with the concept of efficiency. This can then prompt them to go back and reject the original goal of efficiency in their own endeavours. Which is a very bad idea, if they are hoping to get what they want, without wasting other things they want in the process. Which is very likely what they are hoping for.

For instance if ‘the most valued qualities of human life’ are stripped by spending most of your time say efficiently pursuing career productivity, the problem is not that efficiency is bad, the problem is that you are efficiently pursuing the wrong goals. i.e. goals that are not your own, or at least not all of what you value. Being inefficient about, say, work is a terrible strategy for improving your home life, since only a miniscule proportion of the ways to be inefficient at work involve any home life improvement, and most of those not efficient improvements. Fortunately people using this strategy probably know intuitively that they will have to aim at the set of ways of being inefficient at work that do help their family lives. But once you have got as far as pursuing the values you actually care about, being efficient about them has really got to help, no matter how much your enemies also like efficiency. Similarly, don’t abandon ‘succeeding’, just because bad people also like it.

***

Added: Another example.

When to explain

It is commonly claimed that humans’ explicit conscious faculties arose for explaining to others about themselves and their intentions. Similarly when people talk about designing robots that interact with people, they often mention the usefulness of designing such robots to be able to explain to you why it is they changed your investments or rearranged your kitchen.

Perhaps this is a generally useful principle for internally complex units dealing with each other: have some part that keeps an overview of what’s going on inside and can discuss it with others.

If so, the same seems like it should be true of companies. However my experience with companies is that they are often designed specifically to prevent you from being able to get any explanations out of them. Anyone who actually makes decisions regarding you seems to be guarded by layers of people who can’t be held accountable for anything. They can sweetly lament your frustrations, agree that the policies seem unreasonable, sincerely wish you a nice day, and most importantly, have nothing to do with the policies in question and so can’t be expected to justify them or change them based on any arguments or threats you might make.

I wondered why this strategy should be different for companies, and a friend pointed out that companies do often make an effort at more high level explanations of what they are doing, though not necessarily accurate: vision statements, advertisements etc. PR is often the metaphor for how the conscious mind works after all.

So it seems the company strategy is more complex: general explanations coupled with avoidance of being required to make more detailed ones of specific cases and policies. So, is this strategy generally useful? Is it how humans behave? Is it how successful robots will behave?*

Inspired by an interaction with ETS, evidenced lately by PNC and Verizon

*assuming there is more than one

Cheap signaling

Chocolates

Image by J. Paxon Reyes via Flickr

If all this stuff people do is for signaling, wouldn’t it be great if we could find ways of doing it more cheaply? At first glance, this sentiment seems a naive error; the whole point of paying a lot for a box of chocolates is to say you were willing to pay a lot. ‘Costly signaling’ is inherently costly.

But wait. In a signaling model, Type A people can be distinguished from Type B people because they do something that is too expensive for Type B people. One reason this action can be worthwhile for Type As and not for Type Bs is because type As have more to gain by it. A man who really loves his girlfriend cares more about showing her than man who is less smitten. A box of chocolates costs the same to both men, but hopefully only the first will buy it.

But there is another reason an action may be worthwhile for As and not for Bs: the cost is higher for type Bs. Relating some intimate gossip about a famous person is a good signal that you are in close with them because it is expensive for an ignorant person to fake, but very cheap for you to send.

Directly revealing your type can be thought of as an instance of this. Taking off your shirt to reveal your handsome muscles is extremely cheap if you have handsome muscles under your shirt and extremely expensive if you do not.

This kind of signaling can be very cheap. It only needs to be expensive for the kinds of people who don’t do it. And since they don’t do it, that cost is not realised. Whereas in the first kind of case I described (exemplified by chocolates), signaling must be relatively expensive. People of different types each have to pay more than the type below them cares enough to pay. i.e. what the person below thew would gain by being mistaken for the type above.

Cases of the second type, like gossip, are not always cheap. Sometimes it is cheaper for the type who sends the signal to send it, but they still have to pay quite a lot before they shake off the other type. If education is for signaling, it seems it is at least partly like this. University is much easier for smart, conscientious people, but if it were only a week long a lot of others would still put in the extra effort.

There can also be outside costs. For instance talking often works the second way. It is extremely cheap to honestly signal that you are an accountant by saying ‘I’m an accountant’, because the social repercussions of being found out to be lying are costly enough to put most people off lying about things where they would be discovered. While this is cheap both for the signalers and the non-signalers, setting up and maintaining the social surveillance that ensures a cost to liars may be expensive.

So if we wanted to waste less on signaling, one way to make signals cheaper would be to find actions with differences in costs to replace actions with differences in benefits. I’m not sure how to do that – just a thought.

Does SI make everyone look like swimsuit models?

William Easterly believes Sports Illustrated’s swimsuit issue externalises toward women with their ‘relentless marketing of a “swimsuit” young female body type as sex object’. He doesn’t explain how this would happen.

As far as I can tell, the presumed effect is that pictures of women acting as ‘sex objects’ causes men to increase their credence that all other women are ‘sex objects’. I’m a bit puzzled about the causal path toward badness after that, since men do not seem on the whole less friendly when hoping for sex.

I think the important bit here must be about ‘objects’. I have no idea how one films someone as if they are an object. The women in SI don’t look inanimate, if that’s what it’s about. It’s also hard to make robots that good. I will guess that ‘sex object’ means something like ‘low status person to have sex with’, as opposed to just being sexually alluring. It seems unlikely that the concern is that women are taken to be sexier than they really are, so I think the problem is that they are taken to be low status in this particular sexy way.

If I guessed right so far, I think it is true that men increase their expectation that all other women are sex objects when they view videos of women being sex objects. I doubt this is a big effect, since they have masses of much better information about the sexiness and status of women around them. Nonetheless, I agree it is probably an effect.

However as usual, we are focussing on the tiny gender related speck of a much larger issue. Whenever a person has more than one characteristic, they give others the impression that those characteristics tend to go together, externalising to everyone else with those characteristics. When we show male criminals on the news, it is an externality to all other men. When we show clowns with big red noses it is an externality to all other people with big red noses. When I go outside it gives all onlookers a minuscule increase in their expectation that a tallish person will tend to be brown haired, female, dressed foreignly and not in possession of a car.

Most characteristics don’t end up delineating much of an externality, because we mostly don’t bother keeping track of all the expectations we could have connected to tallish people. What makes something like this a stronger effect is the viewers deciding that tallishness is more or less of a worthwhile category to accrue stereotypes about. I expect gender is well and truly forever high on the list of characteristics popularly considered worth stereotyping about, but people who look at everything with the intent of finding and advertising any hint of gender differential implied by it can only make this worse.

Or better. As I pointed out before, while expecting groups to be the same causes externalities, they are smaller ones than if everyone expected everyone to have average human characteristics until they had perfect information about them. If people make more good inferences from other people’s characteristics, they end up sooner treating the sex objects as sex objects and the formidable intellectuals as formidable intellectuals and so forth. So accurately informing people about every way in which the experiences of men and women differ can help others stereotype more accurately. However there are so many other ways to improve accurate categorisation, why obsess over the gender tinged corner of the issue?

In sum, I agree that women who look like ‘sex objects’ increase the expectation by viewers of more women being ‘sex objects’. I think this is a rational and socially useful response on the part of viewers, relative to continuing to believe in a lower rate of sex objects amongst women. I also think it is virtually certain that in any given case the women in question should go on advertising themselves as sex objects, since they clearly produce a lot of benefit for themselves and viewers that way, and the externality is likely minuscule. There is just as much reason to think that any other person categorisable in any way should not do anything low status, since the sex object issue is a small part of a ubiquitous externality. Obsessing over the gender aspect of such externalities (and everything else) probably helps draw attention to gender as a useful categorisation, perhaps ultimately for the best. As is often the case though, if you care about the issue, only being able to see the gender related part of it is probably not useful.

What do you think? Is concern over some women being pictured as sex objects just an example of people looking at a ubiquitous issue and seeing nothing but the absurdly tiny way in which it might affect women more than men sometimes? Or is there some reason it stands apart from every other way that people with multiple characteristics help and harm those who are like them?

Update: Robin Hanson also just responded to Easterly, investigating in more detail the possible causal mechanisms people could be picturing for women in swimsuits causing harm. Easterly responded to him, saying that empirical facts are irrelevant to his claim.

Does anti-discrimination look like discrimination?

By my reckoning, affirmative action should often make organizations look more biased in the direction they seek to correct, rather than less.

Imagine two groups of people in roughly equal numbers, type A and type B. It is thought by many that B people are unfairly discriminated against in employment. The management of organisation X believe this, so they create a policy to ensure new employees include roughly equally many As and Bs.

The effects of this policy include:

  1. a large benefit to many Bs previously near the threshold for being employed
  2. a small cost to all type Bs working at X, who will to varying degrees be suspected more of not meriting their position.
  3. a large cost to many As previously near the threshold for being employed
  4. a small benefit to all As working at X, who will to varying degrees be suspected of more than meriting their position.

Look at the effects on type Bs. Those well clear of the threshold have a net cost, while those near enough to it have a net benefit. This should in decrease the motivation of those well above the threshold to work at X and increase the motivation of those of lower ability to try. This should decrease the average quality of type B employees at X, even before accounting for the new influx of lower quality candidates. At the same time the opposite should happen with type As.

Now suppose the only quota at X is in hiring. Promotions have no similar adjustment. On top of whatever discrimination exists against Bs, there should now be even fewer Bs promoted, because they are on average lower quality at X, due to the affirmative action in hiring. Relative to less concerned organisations, X should end up with a greater proportion of As at the top of the organization.

Is this what really happens? If not, why not?

Poverty does not respond to incentives

I wrote a post a while back saying that preventing ‘exploitative’ trade is equivalent to preventing an armed threat by eliminating the ‘not getting shot in the head’ option. Some people countered this argument by saying that it doesn’t account for how others respond. If poor people take the option of being ‘exploited’, they won’t get offered such good alternatives in future as they will if they hold out.

This seems unlikely, but it reminds me of a real difference between these situations. If you forcibly prevent the person with the gun to their head from responding to the threat, the person holding the gun will generally want to escape making the threat, as now she has nothing to gain and everything to lose. The world on the other hand will not relent from making people poor if you prevent the poor people from responding to it.

I wonder if the misintuition about the world treating people better if they can’t give in to its ‘coercion’ is a result of familiarity with how single agent threateners behave in this situation. As a side note, this makes preventing ‘exploitative’ trade worse relative to preventing threatened parties acting on threats.

Moving marginal mothers

Julian Savulescu suggests extending the idea of paying drug addicts not to have children to everyone.  At first the purpose is to avoid the eugenics feel of discouraging only one set of people from procreating, but then he reasons:

“The benefit of a policy of offering inducements to sterilisation is that it would select those who do not value, do not understand, do not want the role of parent. And it is precisely these people who are likely to be the worst parents.

Being a parent is, at best, a difficult job. Why not excuse those with the least motivation and determination? There are plenty of others willing to take their place. And the earth can only sustain a finite number of people.”

It’s of course true that if you penalize an activity, those to whom it is most expensive already will be the ones to quit. However:

  1. The existing costs of parenting already induce those who dislike parenting most not to parent. Adding another cost to parenting would just move the line where it becomes worthwhile to parent, not implement such selection. Justifying this requires an argument that the level of value at which people find parenting worthwhile is too low, not just a desire to encourage better parents to do a greater proportion of parenting in general.
  2. “Excuse those with the least motivation and determination”? We aren’t exactly pushing them to do it. Why presume they don’t excuse themselves at the appropriate point? This goes with the above point; the line where parenting seems worthwhile could be in the wrong place if parents were pushed for some reason to have too many children, but why think they misjudge?
  3. Why would there be plenty of others willing to take their places? Presumably those wanting to bear children will do so already or at least would not start at a 1:1 ratio on the news that others are not. Few factors influencing conception depend on the ambient birthrate.
  4. If others really were willing to ‘take their place’, the exit of poor parents from parenting  wouldn’t be relevant to the total population and whether the planet can sustain it.
  5. Presumably the issue is how big a finite number of people the earth’s resources can support, and more importantly why and to what extent parents should be expected to misjudge.
  6. Smaller populations are not automatically better if you value human life at all. That parents are unlikely to account for the entire value of their potential child’s life is a strong reason to think that parents don’t have enough children. If that is the overwhelming externality, the line should be lower, and we would be better off paying people to have children.

    Might law save us from uncaring AI?

    Robin has claimed a few times that law is humans’ best bet for protecting ourselves from super-intelligent robots. This seemed unlikely to me, and he didn’t offer much explanation. I figured laws would protect us while AI was about as intellectually weak as us, but not if when it was far more powerful. I’ve changed my mind somewhat though, so let me explain.

    When is it efficient to kill humans?

    At first glance, it looks like creatures with the power to take humans’ property would do so if the value of the property minus the cost of stealing it was greater than the value of anything the human might produce with it. When AI is so cheap and efficient that the human will be replaced immediately, and the replacement will use resources enough better to make up for the costs of stealing and replacement, the human is better dead. This might be soon after humans are overtaken. However such reasoning is really imagining one powerful AI’s dealings with one person, then assuming that generalizes to many of each. Does it?

    What does law do?

    In a group of agents where none is more powerful than the rest combined, and there is no law, basically the strongest coalition of agents gets to do what they want, including stealing others’ property. There is an ongoing cost of conflict, so overall the group would do better if they could avoid this situation, but those with power at a given time benefits from stealing, so it goes on. Law  basically lets everyone escape the dynamic of groups dominating one another (or some of it) by everyone in a very large group pre-committing to take the side of whoever is being dominated in smaller conflicts. Now wherever the strong try to dominate the weak, the super-strong awaits to crush the strong. Continue reading