Acknowledge the Elephant (entry for AI Alignment Prize)

You know what I’m talking about. Whose values?

Humans want different things, individually and collectively, and I claim that bracketing this by imagining that the main part of the problem is not turning everything into paper clips is a major mistake.

I have seen way too much hand-waving about this and it doesn’t do this community any credit to eschew politics as mind-killing. I get why we do that, because the naivete and ideological Turing test incompetence around here is often staggering, but that means this is an area where we have failed to improve and we swim in a sea full of sharks.

Of course, “politics” is just a label for something that is really even more fundamental, which includes religion and psychology and sociology and basic human attitudes that vary in a much vaster space than most of us are used to acknowledging.

You have to get serious about whose values. Coherent Extrapolated Volition is a crock unless you preface it with a specification of who you will leave out, and how you will weight their anguish and frustration against the satisfaction of the Coherent Ones. Here are some concrete questions you need to start talking about:

(1) Is the ultimate source of an AI’s values to be an individual, a community of specified individuals, a text or code of some kind which relevant humans have hammered out somehow, a method by which the AI observes human society as a whole and forms its own synthesis of values according so some previously specified recipe, or something else?

“Which one of these sources turns out to be the surest and safest way to install the values the installers actually want?” is not at all the same question as “Which way of doing it is likeliest to give the AI the best values to install?”

Technical research won’t be enough, it will just allow the winners of the race to accomplish their goals whatever they are. This leads to the next concrete question that shouldn’t be dodged:

(2) As activists, should we push for international cooperation with suppression of unauthorized AI research, open-source research, working with a particular government, or something else?

Avoiding an AI arms race is a good top-level goal, but accomplishing that is inevitably political. This question also has potentially different answers depending on whether you care about succeeding in giving the AI the intended values or whether you care what the values actually are.

I am being kind here, because my questions (1) and (2) are still phrased in a process-oriented way which allows you all to stay comfortable, without identifying specific values and actors, but now I’m going to drill down and make you squirm. If you’re good at Noticing Confusion, the squriming should trigger that.

(3) What about God?

Most of the people on this planet ground their values in a religion. Are we to take seriously the idea that “everyone’s values should be accomodated” or its approximation “do the equivalent of taking a vote” or its meta-approximation “do the equivalent of what a vote would give us if everyone was able to get smarter and more educated to the extent that they wanted to” might maximize coherence by excluding atheists? I’m not an atheist so it’s not a problem for me as much as it is for some of you, but both theists and atheists should recognize that the dynamical system of coherent valuations might have multiple attractors and not assume that the one the system is headed for won’t be evil in any of the senses people use that word. (I’m not even going to get into specifically theistic concerns like whether spiritual entities are going to contribute to the process in some way, I just want us to admit that we must have something to say to people who ask what God wants.) The biggest religion by some measures is Islam, which is expansionist and problematic in various ways from the point of view of most of us here, but Christians will have their own priorities if a Singularity is being contemplated, ranging from Teilhard’s Omega Point theology to the identification of a powerful AI with entities they have been taught to anticipate will be apocalyptically relevant.

(4) What about freedom?

Read Maureen Dowd’s interview with Jaron Lanier in the 11/08/17 NY Times. I’ll wait. …. OK. Obviously we can use terms like “maximize human flourishing” to dance around the issue, but there are fundamental polarities between individualism and collectivism, between democracy and autocracy, between virtual reality and traditional lifestyles, which are going to factor in to specifying values and need to be discussed much harder. Yeah, we probably want to avoid a Wirehead Matrix endgame, just like we want to avoid being Clippy, but it gets more uncomfortable when you need to start getting your hands dirty. Do you want to maximize the weighted summation from N=1 to 7.6 billion of the integral of Q(L,N)dL? You’re going to need to define Q in terms of present-subjective-mood or reflective-life-satisfaction or comformance-to-current-value-system or something and build a time-discounting function into dL and figure out what happens when N increases and decide if the weights ought to all be equal, but before you can tackle that you have to figure out what is even possible. Maybe it’s important that people all have some actual input or voice or vote in the final value set, but maybe that’s impossible, and maybe we can maximize their ongoing experience by some measure but it will lead ultimately to anomie and alienation, or maybe we can give the people who want a say a say and give the ones who want money money and give the ones who want work meaningful work but we’d better know what we’re talking about when we talk about those things. This isn’t something to be bracketed away.

(5) What about China?

That’s another elephant we shouldn’t ignore, and it’s necessary to integrate the perspectives of the blind men who each perceive a part of it. It’s probably going to be the most important country economically, possibly militarily, possibly in AI research, and y’all don’t have much of a clue about the conversations they are having over there about the things you want to talk about over here. The biggest Unavoidable is who is in charge there and how much they control what happens and what they want. You may not care much who is in charge, but both their values and the values of the people in China collectively (which have a positive correlation) might come as a shock to you if you haven’t studied them. It’s easy to ignore what’s going on there, there are all kinds of incentives to, so here are a couple of things to chew on: most of the Bitcoin mining that occurs happens in China (which means anyone who controls it ultimately controls the blockchain), and China already has more billionaires than the USA does. In some ways they can get things done a lot faster than Western societies; their inadequacies are not our inadequacies.

I could go on, but I want to spark a discussion so I’m posting this now, trusting that Christiano will allocate his judgy-points fairly if the rest of you build productively on what I am saying.

Advertisements
Posted in Uncategorized | Leave a comment

A logical gap

I am seeing dozens of stories that are full of evidence that chemical weapons were used in Syria.

Almost all these stories claim that the evidence proves not only that chemical weapons were used, but that the Assad regime used them, but the only hard facts are that people died from chemicals, and it is always only an inference from the fact that the rebels controlled the area and there is nothing to contradict the alternative theory that this was a false flag operation where the rebels used the weapons themselves in order to give Western powers an excuse to intervene.

Just because you can’t imagine ever using such an evil tactic yourself doesn’t give you the right to ignore the long history of false flag attacks in wars in the Mideast and pretend they don’t happen.

So I ask, has anyone seen ANY EVIDENCE that distinguishes between the two possibilities “Assad did it” and “the rebels did it”?

Earlier this year there was another alleged use of chemical weapons in Syria, and a preliminary UN report blamed the rebels, and THEN THAT STORY VANISHED.

They don’t expect people to remember but I remember.

http://bbc.co.uk/news/world-middle-east-22424188

http://www.presstv.ir/detail/2013/07/30/316273/west-war-crimes-in-syria-exposed/

UPDATE: To the person whose comment I spammed: if you provide me with a real email address, OR you simply rewrite the comment to omit the places where you called me obscene names, I will post it and reply to it. If you aren’t capable of basic civility, then good-bye.

Posted in Uncategorized | 1 Comment

The persecution of Shellie Zimmerman

Mrs. Zimmerman is being prosecuted on much flimsier grounds than her husband was

If you have any knowledge whatsoever of how the legal process for prosecuting felonies works, read the article linked here CAREFULLY. It shows pure vindictiveness by the state with no basis whatsoever for the charges. If you understand the article, you will see that we no longer live in a country where the state has any accountability to follow the law. I expect an acquittal if this isn’t thrown out before trial, but what we will never see, that we ought to see, is all the prosecutors involved in this travesty having their careers terminated.

Posted in Uncategorized | Leave a comment

Race and Crime in America

Ron Unz on race and crime in America

This is a long article, but it’s worth reading the whole thing. I learned some things I didn’t expect to.

Of course I already knew that the relationship between race and crime rates was very strong. The two most surprising things to me were

(1) New York City is a huge outlier which strongly affects the nationwide results. The relationship between race and crime would be much stronger if New York City is excluded. What New York City shows is that changes in policing can tremendously reduce urban crime, and that therefore the racial statistics are much less depressing.

(2) Many right-wingers, baffled by the enthusiasm of American elites in both political parties for unrestricted immigration, see this as a sinister plot to replace white people with a politically and economically more controllable population. The author makes an interesting argument that an even bigger motivator is the desire to displace black people.

UPDATE: America’s Real Criminal Element: Lead | Mother Jones

I knew about this problem, but I had no idea how much of the crime statistics it explained. One of the most disturbing things about the article is how hard it has been to get people whose job it is to understand the causes of crime to pay attention to this research. Almost everyone has their own pet theory, which accepting this environmental explanation would reduce the relevance of.

Posted in Uncategorized | 1 Comment

Bayesianity: How Scientists Think About Evidence

Most people don’t understand conditional probability and Bayes’s Theorem, which are the scientifically correct tools for reasoning using probabilities. I am going to give a simple example that I guarantee most people will understand AFTER they see the answer, and that I guarantee most people will NOT understand BEFORE they see the answer.

If you get this wrong, and then understand the answer, you might feel stupid because the answer is not difficult. You shouldn’t feel stupid. Instead you should feel SMARTER! This kind of reasoning should be taught in high school but it usually isn’t. There’s no shame in not having learned it — although to some people it is truly common sense, most people’s brains do not use this logic naturally and need to be taught.

Here’s the situation (the numbers are realistic but rounded off to make the math simpler). Women are recommended to get their first mammogram when they reach 40, to test for breast cancer. The following facts are known about breast cancer and mammograms for 40-year-old women who haven’t yet been tested or diagnosed:

1) 1% of these women have breast cancer
2) If they have breast cancer, the mammogram has an 80% chance of detecting it and returning a “positive” result, and a 20% chance of missing it and returning an incorrect “negative” result.
3) If they don’t have breast cancer, the mammogram has a 90% chance of correctly saying “negative” and a 10% chance of falsely saying “positive”.

In other words, the test is accurate but not perfect, and if you get a positive result you have to get further more expensive testing to confirm it or contradict it.

Here is the key question which very few people know how to answer: if you go in and get tested and the results are positive, what is the chance you actually have breast cancer, based on this information?

Obviously it’s now more than 1%, because it was 1% before you took the test and you now have new evidence that increases the chance you have it, but it’s less than 100% because the test sometimes gives a wrong answer.

Please answer in the comments so I can get a good-sized statistical sample and we can learn how good at scientific thinking people here are. Each time a comment arrives I will hide it temporarily so as not to give the answer away too soon.

Posted in Uncategorized | 4 Comments

Double Drone Strikes

U.S. Drone Warfare: Secondary Strikes Target First Responders

This is way worse than I thought. A drone strike is an act of war, but can sometimes be justified just as war can sometimes be justified. I don’t see how this practice of following a drone strike with another one in quick succession isn’t a war crime.

The article says they used 2 bombs because 1 would be too inaccurate but that logic would fail in a war crimes trial since drone strikes are normally aimed at mobile rather than fixed targets! After the first explosion, if it was inaccurate the target is likely to leave the area PDQ and if it was accurate no second strike is needed.

I am appalled, it has been quite a while since my last downward re-estimation of the morals of our ruling class but it’s time for a new one. On my recently developed Evil/Crazy/Stupid metric for evaluating government actions, this scores 70/10/20.

Posted in Uncategorized | Leave a comment

NY Times: trials should be about racial history rather than the facts of the case

http://www.althouse.blogspot.com/2013/07/the-zimmerman-trial-needs-to-be-more.html

The article from the NY Times that Ann Althouse savagely deconstructs here is a perfect example of the utter corruption of journalism (not that it was ever a paragon of objectivity and fairness, but this article is from the most prestigious journalistic medium of all and is so completely wrong that it’s actually evil, as Althouse demonstrates (some of the comments are also very good)).

Posted in Uncategorized | Leave a comment