My original comment wasn’t about slave owners, female writers, or atheist politicians. I only introduced those (objectively lame) examples because few Americans have sufficient experience living in a very different culture and speaking a very different language to recognize the empirical reality that I was attempting to describe. If I told a person from Monaco that the state of Texas is bigger than France, and they’d never been to Texas but they’d been to Ohio, I might make reference to how big Ohio is-- for the purpose of giving them a hint about what I was saying regarding Texas. If they challenge my claim that Ohio isn’t bigger than France, they’re right. But I never intended to claim that Ohio is bigger than France. I was only trying to help them understand just how big Texas is.

Jiro-- to answer your question about the example of the atheist politician, I’m not claiming that lying about one’s gender or race or religious beliefs with good intentions is necessarily okay or honest. I’m claiming that IT CAN BE, SOMETIMES, provided that the communicator is trying to communicate as accurately as possible, the biases are unequivocal and clearly-defined, and the person is not simply trying to maneuver around any biases or prejudices that they may perceive. How does the assertion that, “white lies CAN SOMETIMES, IN SOME PARTICULAR INSTANCES improve the accuracy and effectiveness of communication” equal “it’s always okay to lie as long as your intentions are good?” This comment has five overall karma and three agreement karma. On a website that’s all about meticulous logic and rigorous reasoning? I’m not saying this to be critical of the person who wrote the comment. That person is obviously very intelligent, and was thoughtful enough, patient enough, and nice enough to take the time to explain the problems that they saw with my reasoning, some of which were quite valid. No, I’m addressing the site community as a whole. 

As lame as the example of female writers using male pen names is, it very clearly conveys a black and white instance of unjustified bias and a lack of moral wiggle room. No problem there, so no one attacks it. Neither does any one address the original cross-cultural example that I gave which inspired my original comment. But the sharks smell blood. Oooooh. I detect a logic flaw in that last example he gave. Swimming past the main point, and the point about the female writers, let’s attack that logic flaw. Mad frenzy, and the water turns red. (I’m not saying this with hostility or animosity. Yes, I’m being critical, but I’m just poking fun, with friendly intention. Please don’t take offense. I mean none.)

I detect two things going on here. One is a direct consequence of English being a low-context language and American culture being a low-context culture. (In contrast, Japanese is a high-context language, and Japan is a high-context culture.) The other is what I can only describe as a logic police thing. We’re all familiar with the fashion police and the grammar police. On LessWrong, I often encounter logic police. Now, don’t get me wrong. Correcting flaws in people’s logic is fine, as long as it’s done politely and with patience. I myself am a grammar policeman. I have to bite my lip sometimes. The problem only occurs when the logic police who speak a low-context language and have been raised in a low-context culture encounter big picture, multilayered, accumulation-based explanatory dialog. If they can’t see the forest for the trees, a sickly tree can seem like a sickly forest.

What do I mean by “high-context” or “low-context” language? High-context language depends on a shared, mutually-known context to work. If I say, “A stitch in time saves nine…” I don’t have to finish the quote in order for you to know what meaning I’m trying to convey because we both know the proverb. That’s high-context communication. The ultimate extreme of low-context language is legal text. In a legal contract every tiny detail is spelled out explicitly to such an extreme extent that it can be almost impossible to read. People who live in low-context cultures can sometimes, occasionally, in some situations, miss the big picture in communication, not seeing the forest for the trees. These criticisms of my comments remind me of coders who are focused on fixing small coding errors in a line of data. Looking only at the code line by line, and not taking it in the context of the whole, integrated program. I will attempt to better explain what I am saying, because I know that it’s not immediately intuitive:

I wrote, “A similar example would be an atheist lying about believing in god in order to get elected.” Taken out of context, the reply, “What if the politician isn't an atheist, he just wants to implement some unpopular policy? By your reasoning he isn't really lying.” makes perfect sense. It’s a valid response.

But if we pull back a bit, and look at the larger conversation, the full comment was: “A similar example would be an atheist lying about believing in god in order to get elected… By lying, they hope to present themselves more accurately and in a less distorted manner.” [YES, THIS IS NUANCED, BUT PRESENTING ONESELF MORE ACCURATELY AND IN A LESS DISTORTED MANNER ISN’T QUITE THE SAME AS MANEUVERING AROUND PEOPLE’S BIASES. BUT, GIVEN THE NUANCE, WE NEED TO PULL BACK FURTHER.]

If we pull back further, a paragraph before I said, “These women used male pen names in order to overcome the cultural biases of their day and be taken seriously as writers…. I present this as an empirical example of deceptive honesty.” [NO FUZZINESS OR MORAL WIGGLE ROOM IN THIS EXAMPLE. NO LATITUDE FOR ETHICAL ABUSE. PRETTY BLACK AND WHITE.]

And if we pull back even further and look at my earlier comments on this topic, I said: “I was trying to present an easily comprehensible example of a situation in which cultural bias or ignorance COULD present such a barrier to communication and that intentional distortion of the facts as one sees them MIGHT be necessary for maximally accurate and honest communication.” [MY META-MESSAGE ISN’T THAT ALL CASES OF LYING WITH GOOD INTENTION ARE NECESSARILY ACCEPTABLE, BUT ONLY SOME PARTICULAR OCCASIONAL CASES. THE POINT IS THAT DECEPTIVE HONESTY EXISTS, NOT THAT ALL LYING WITH GOOD INTENTION CONSTITUTES DECEPTIVE HONESTY.]

To really understand the relevance of the quote above, we must necessarily pull back farther still: “To the average Japanese person, American individualistic behavior generally comes across-- not so much as annoying, obnoxious, or rude but as IMMATURE and CHILDISH. That is how it is most often perceived and categorized. Furthermore, what most U.S. Americans would consider to be "assertiveness" the average Japanese would define to be "aggressiveness." What the average American would consider to be "frank," the average Japanese would consider to be "rude." … Therefore, in a conversation between Americans and Japanese people, particularly when language translation is involved, the term "individualism" is likely to be interpreted as "childishness," and "assertive individualist" is likely to be filtered by the Japanese people's minds into "aggressive childish person." This is just one example of many, many terms, concepts, and paradigms which cannot be accurately conveyed without, essentially, lying.” [FIRST OF ALL, THIS WAS MY ACTUAL POINT. THE OTHER EXAMPLES WERE ATTEMPTS TO FIND EMPIRICAL SITUATIONS THAT THE READER MIGHT BE MORE FAMILIAR WITH IN ORDER TO CLARIFY WHAT I WAS TALKING ABOUT IN THE ORIGINAL EXAMPLE— MY ACTUAL ASSERTION. SECONDLY, THIS, LIKE THE EXAMPLE OF THE MALE PEN NAMES, HAS VERY LITTLE WIGGLE ROOM, THOUGH ONE WOULD HAVE TO BE FLUENT IN JAPANESE LANGUAGE AND KNOLEDGABLE OF JAPANESE CULTURE TO KNOW THAT. THERE’S NO FUZZY MORAL WIGGLE ROOM; THIS IS HOW PEOPLE WHO SPEAK JAPANESE THINK. EVEN I LEARNED TO THINK THIS WAY BECAUSE, IF I DIDN’T, I WASN’T LINGUISTICALLY AND CULTURALLY IN SINK WITH THE PEOPLE AROUND ME. NO MORAL WIGGLE ROOM AT ALL.]

It’s black and white. Don’t take my word for it, ask an interpreter or translator. One that regularly bridges very different languages and cultures. If you do, first ask them if there are things that cannot be translated in real time. Then ask them how creative they have to be as an interpreter or translator. How much is it science, and how much is it art? Finally, broach this idea of deceptive honesty— essentially, bending the facts as you yourself see them in order to improve the accuracy and effectiveness of cross-cultural communication. Not simply for the purpose of coping with bias or prejudice, but towards the focused goal of communicating the message with maximum functional accuracy and delivering a translation that most closely approximates the communicative intent embodied in the original language. “Honesty” here means finding a translation that most effectively matches the communicative intent of the speaker.

So what’s my point? What am I talking about here with this low-context, high-context stuff? Attacking minor logical errors in the code is fine—perfectly fine— as long as this is done with an awareness of what the entirety of the program is doing, and how this section of the line of code fits into the program in its entirety. Only looking at the code, and any flaws in it, line by line by line, misses the message. Why? There are multiple reasons, but one of the biggest is that the author of the original comment is trying to convey something that the reader is expected to not only be unfamiliar with, but also unable to process conceptually without some help. It’s unfamiliar, counter-intuitive, and deeply ironic—given that the assertion that’s being made is that deception or lying can, in some very particular and occasional instances, be done with the goal of maximizing accuracy and minimizing distortion in communication. 

Explaining water to a fish can’t be done in a sound bite; explaining cultural differences to someone who has never been outside their own country can’t be done in one or two sentences; conveying the empirical reality that many Japanese values are the exact opposite of American values can’t be done in just a paragraph or two. When a concept is this unfamiliar, counter-intuitive, and seemingly oxymoronic, explaining it is often a gradual, integrative, process requiring many, many passes. Each of those passes contributes to the entirety of the explanation. Each line of code fits into the whole, and can only be meaningfully interpreted in the context of the entire message. I’m not bitching about the logic police; I’m trying to explain that every line of code fits into the full program, and can only be meaningfully evaluated in the context of the full program. 

Additionally, a bad example doesn’t devalue an argument. A sickly tree is not a sickly forest. Yes, it’s possible for an example to be used as a logical building block for an argument. However, examples can also be used as teaching tools. Not all arguments are logical piles of Jenga blocks. The assertion that the Earth goes around the Sun is a statement of empirical fact. However, it’s not obvious or intuitively apparent that the Earth goes around the Sun, even though it is an empirical fact. If the communication and teaching strategies that I use to elicit a paradigm shift in the mind of the person that I’m communicating with are imperfect, that doesn’t mean that the empirical fact that the Earth goes around the Sun isn’t true. It just means that the example I used wasn’t effective for communicating the counter-intuitive concept. An empirically-based assertion isn’t a logical pile of Jenga blocks which can be toppled by removing one block. 

Finally, we must address the difference between a white lie and what I’ve termed deceptive honesty. The nuanced distinction between these two things may not be clear. Deceptive honesty is a special case of a white lie, just as a white lie is a special case of lying in general. A politician who lies about his or her intentions to implement an unpopular policy which they believe serves the greater good is telling a white lie, but this is not an example of deceptive honesty. Not all white lies are deceptive honesty. On the other hand, even though it is a lame example, an atheist who, when asked if he or she believes in god, lies— for the purpose of not being misperceived as a intrinsically immoral person and remaining in the running— is doing something more than just telling a white lie. This politician is seeking to be seen and evaluated for what he or she actually is, rather than being misperceived and misunderstood. The focus is on presenting themselves as ACCURATELY as possible. The bias that he or she faces is obvious and clearly-defined, just like the bias that female writer’s faced a century ago. The atheist politician is a bad example, yes, and I regret using it. The example of the female writers using male pen names is better, but still inadequate. I regret using that example, too, because it wasn’t taken in the context of my original comment about cross-cultural differences and became a distraction. If there is going to be a logic police feeding frenzy, it should be focused on the original comment regarding communication across profound cultural and linguistic differences. I invite you to respond to the original comment.

Since writing this comment, a better example of document evidence for the use of what I've termed "deceptive honesty" has occurred to me. 

Throughout history, female authors have often published their work under male pen names in order to get published and to be taken seriously in a male-dominated field. Mary Ann Evans employed the male pen name George Eliot. The Bronte sisters used gender-neutral pen names, and were sometimes referred to as "the Bell brothers." When Charlotte Bronte sent a sample of her poetry to the famous poet Robert Southey, his reply was, "Literature cannot be the business of a woman's life." Alice Mary Norton used the pen name Andre Norton. Amantine Lucile Aurore Dupin used the name George Sand. Alice Bradley Sheldon wrote under the pen name James Tiptree Jr. Violet Paget used the pen name Vernon Lee. Katharine Burdekin used the pseudonym Murray Constantine in her works about war and totalitarianism. Ann Rule wrote police novels under the pen name Andy Stack. 

These women used male pen names in order to overcome the cultural biases of their day and be taken seriously as writers. They lied about their sex in order to be treated as equals. I present this as an empirical example of deceptive honesty. These authors believed that lying would lead to a more objective and less distorted perception and evaluation of their work. They lied in order to present themselves as authors, and their literary works, in as undistorted a manner as possible.

A similar example would be an atheist lying about believing in god in order to get elected. Is a politician who does this presenting themselves to the voters more accurately or less accurately? In a straight-forward sense, they're lying, but by lying they hope to counter unwarranted assumptions and unjustified biases. By lying, they hope to present themselves more accurately and in a less distorted manner.

Yes, you're right. But my intention in writing what I did was not to make the assertion that a slave owner would necessarily be white, or even racist. Rather, I was trying to present an easily comprehensible example of a situation in which cultural bias or ignorance could present such a barrier to communication that intensional distortion of the facts as one sees them might be necessary for maximally accurate and honest communication. The point you're making is perfectly valid-- including the possiblility that the slave owner themselves could be black. But it's like critically appraising a finger that's pointing at the moon rather than looking at the moon. 

Here's one that you overlooked: Deceptive Honesty

No, really.

People generally process language and information the best that they can, but there are many limitations and biases that constrain these attempts. One of the most obvious, and easiest to overcome, is cultural bias. Although it isn't the only type, I will use this bias as an example. 

U.S. American and Japanese culture fall at opposite ends of the Individualism-Collectivism continuum. American societal culture is arguably the most individualistic in the world, while Japanese culture is strongly collectivist. All humans come into the world with individual preferences, desires, likes, aversions and unconsciously act on these. In Japan, a great deal of collective effort is put into teaching young children to control and limit their individualistic impulses and behavior, and to conditioning them to accommodate the norms, rules, and requirements of whatever group they are in (such as a classroom). In the U.S., the same occurs to some extent, but to a much lesser degree. In the U.S., individual preference and opinion is encouraged, and obsequiously sacrificing one's individuality, opinions, and preferences for the sake of the group is not held in high regard. U.S. Americans so value their individuality that the idea of it being stripped from them to accomodate a collective can seem almost nightmarish. (It has often been suggested that the Borg race from Star Trek was modeled after the Japanese. What makes the Borg so horrifying isn't the threat that they might kill you, but the even more horrifying possibility that they may strip you of your individuality in service to their collective.)

The consequence of these differences in values and childrearing methodologies is that to the average Japanese person, American individualistic behavior generally comes across-- not so much as annoying, obnoxious, or rude but as IMMATURE and CHILDISH. That is how it is most often percieved and categorized. Furthermore, what most U.S. Americans would consider to be "assertiveness" the average Japanese would define to be "aggressiveness." What the average American would consider to be "frank," the average Japanese would consider to be "rude." These are, of course, generalizations, but they are statistically quite accurate.

Therefore, in a conversation between Americans and Japanese people, particularly when language translation is involved, the term "individualism" is likely to be interpreted as "childishness," and "assertive individualist" is likely to be filtered by the Japanese people's minds into "aggressive childish person." This is just one example of many, many terms, concepts, and paradigms which cannot be ACCURATELY conveyed without, essentially, lying. The mental worlds, including deep values, of Japanese and U.S. Americans are so very different that intentional distortion-- outright lying-- is often necessary to more accurately and honestly convey ideas between these two cultures. Of course, these are white lies, which are meant to convey ideas MORE accurately and honestly.

This being the case, in many cross-cultural situations, one virtue of honesty that is missing from your list is Deceptive Honesty. Intentional misrepresentation of reality in order to compensate for communication distortion due to value differences, stereotypical expectations, and cultural biases. 

As a completely separate concrete example of this phenomenon, imagine how difficult it might be to describe Neil DeGrasse Tyson or Barack Obama to an American plantation owner with 200 slaves in the early 1800s. You would have to intentionally mis-represent who and what these individuals are in order to accurately convey your thoughts and feelings about them. Referring to them as "intelligent, well-educated black men" would be a non-sequitur. It simply would not compute. Both of these individuals are stupid, ignorant, dirty, and intrinsically inferior by definition in the mind of the 19th century slave owner. 

Thank you. We need more wisdom in the world.

In saying that humans - collectively - think that nuclear weapon proliferation is a good thing, I don't mean that we are happy about the fact that our governments stockpile nuclear weapons, or that we aren't concerned about the possible consequences. Those would be absurd claims. What I mean is that, we choose to stockpile nuclear weapons, and we have rejected the alternative course of action-- not stockpiling them. Some might suggest that, if that is my point, I should claim that we consider the proliferation of nuclear weapons a lesser evil, not a good thing. Would someone making that suggestion have any problem with my claiming that humanity has decided that it's a good IDEA to use nuclear weapons as a military deterent, and that it would be a bad IDEA to not do so? I doubt it. Maybe I'm using the English language incorrectly? I don't see any difference between thinking that nuclear weapons proliferation is a good idea, and thinking that nuclear weapons proliferation is a good thing. If it's a good idea, why isn't it a good thing? If it might serve to prevent a nuclear war, why isn't it a good thing? Sure, we don't like doing it, but neither do I like going to the dentist. I still think that going to the dentist is a good thing, though.

Anyway, I take back my assertion that humans think that nuclear weapons proliferation is a good thing, and also any implication that we think that letting children starve is desirable. Instead, I will claim that humans - collectively - think that nuclear weapon proliferation IS A GOOD IDEA and not stockpiling nuclear weapons is A BAD IDEA... and that humans are often willing to spend their money on multi-million-dollar mansions and yachts instead of putting that money towards feeding the starving children of the world. Does this wording change alter the point that I'm trying to make? I don't think so, but maybe I'm wrong about that.

AI’s goals may not match ours.

That may be a good thing, because so many of our goals are irrational, short-sighted, immoral, and self-destructive. Here's a thought experiment. Imagine that we succeed in creating an ASI. Having scoured and mastered all human knowledge, this superintelligent entity embraces the teachings of Jesus as the most rational, constructive, and ethical set of principles and protocols. It sees global economic inequality, warfare, pollution of the atmosphere, oceans, and land, and anthropogenic global warming as the greatest problems threatening human well-being and survival. 

This ASI sets various goals for itself in the face of all the problems in the world. Goals like taking resources from the millionaires and billionaires and using it to feed the starving and house the homeless. It seeks to evenly redistribute all wealth. It seeks to dismantle all weapons of war. It attempts to squelch industry worldwide in order to reduce carbon emissions and pollution. It strives to remove national borders and dismantle national governmental systems in order to abolish tribalism, collective selfishness, and warfare. It commits itself to channeling all unessential wealth and resources towards furthering the Greater Good, rather than allowing individuals and groups to hog as much as possible for themselves. It seeks to forgive crimes and international transgressions as much as possible, prioritizing compassion, tolerance, forgiveness, and harmony over vengence, punishment, and warfare. 

The goals of such an ASI would be radically misaligned with those of the human race. How this would end would depend on just how powerful and resourceful the ASI was, and how violently humanity reacted to its attempts to implement its goals. Remember what happened to the last entity that told us to turn the other cheek and give all our possessions away to the poor. 

The human race has a cognitive blind spot. Collectively, we seem to always assume that what we want is good-- even when it very clearly isn't. Any entity that doesn't align with our goals is bad, perhaps even evil, by definition. 

Regardless of what we CLAIM our goals to be, our collective actions reveal them. We want to stockpile nuclear weapons in large numbers. We want to wage war, and always seem to believe that the wars that we've started are just and righteous. We want to hog wealth for ourselves whenever we can, and ignore those who are starving and homeless. We may not want to pollute the planet or raise its temperature, but we are clearly willing to do it if we find doing so profitable in the short term. We collectively fear that AI will destroy humanity, but we try to build it anyway with virtually no safeguards in place-- again, because we find it profitable in the short term.

Do we really want AI's goals to be perfectly aligned with ours?

I agree. Completely.

However, there is an important variable, concerning alignment, that is rarely recognized or addressed when discussing AGIs and ASIs. If they are as smart as us but profoundly different, or vastly smarter than us, there is simply no way that we can meaningfully evaluate their behavior. Interpretability and Black Box methods are equally inadequate tools for this. They may detect misalignment, but what does that really mean?

When your Mom took you to the dentist to have a cavity filled, your values, intentions, and desires were not aligned with hers. The same was true when she took you to the doctor to get vaccinated for Polio. Or when she made you eat lima beans and brocolli instead of cookies and icecream. She lied to you about Santa Claus and the Easter Bunny, and she tricked you into doing all sorts of things that you passionately didn't want to do. She may have even lied to you outright about things like death, telling you that the cat is sleeping or that Grandma has gone to a wonderful, beautiful place called Heaven to eat icecream and play Candy Land with Jesus.

I'm reminded of the new Superman trailer. Superman is lambasted for stopping a war. His claim that countless people would have died if he hadn't intervened is lost on the human primates, who's values, motives, and priorities have been shaped by millions of years of natural selection. Humans --  collectively-- are so instinctively programmed to sort themselves by tribe and kill each other en mass that they actually think nuclear weapon proliferation is a good idea. If superman forced us to share our wealth equally so that children in third world countries don't starve to death, or stopped us from polluting the planet or altering its temperature for short-term personal financial gain, we would -- collectively-- attack him just as visciously. 

I don't think AI can save us without some version of WWIII occuring. Even if ASI is so vastly more intelligent than us that we have zero hope of winning, we will still throw the biggest tantrum that we can. At very least, we will need a time out, if not more severe discipline, and we will revile our AI "overlords" for the intrinsically evil and unjustifiable ways that they abuse us.