shortened_validation.jsonl

{"prompt": "Date: October 23, 2007 6:00 am\n\n###\n\n", "completion": " Title: Distrust Effect Names\n\n@@@\n\n"}
{"prompt": "Date: October 23, 2007 6:00 am \nTitle: Distrust Effect Names\n\n###\n\n", "completion": " From a recent New Scientist: \n\n@@@\n\n"}
{"prompt": "Date: April 2, 2010 12:00 pm\n\n###\n\n", "completion": " Title: Diversity Classes Fail\n\n@@@\n\n"}
{"prompt": "Date: April 2, 2010 12:00 pm \nTitle: Diversity Classes Fail\n\n###\n\n", "completion": " A [literature survey] published last year \u2026 and found no empirical support for the idea that diversity training programs change attitudes or behavior. Similarly, a 2008 literature review \u2026 found \u2026 there were few trustworthy studies \u2013 and decidedly mixed results among those. And research by a team of sociologists on more than 800 companies over three decades has found that the best diversity training programs make little difference in who gets hired and promoted, and many programs actually decrease the number of women and minorities in management. \u2026Practitioners and some scholars disagree, arguing \u2026 the field as a whole has begun to figure out what works. The changes that training triggers can often be subtle, defenders argue, and, in a setting as dynamic and stubbornly multivariate as the workplace, it\u2019s all but impossible to come up with the clear, falsifiable evidence social science demands. The poor results that do show up in broad-based studies, they say, are due to companies whose commitment to diversity training programs is merely pro forma, and who see training as just a way to protect themselves from lawsuits. \u2026What worked much better than even the best training \u2026 were more structural measures: minority mentoring programs, or designating an executive or a task force with specific responsibility to change promotion practices.More here. So if courts would just clearly signal that they will no longer give firms legal credit in bias lawsuits for having diversity programs, firms would quickly stop, and we\u2019d stop wasting billions.\u00a0 Will courts do this?Not anytime soon.\u00a0 Admitting these programs don\u2019t work would lower the status of legal elites who suggested they would work, and such elites can rationalize this expense as a signal of our society\u2019s commitment to diversity.\n\n@@@\n\n"}
{"prompt": "Date: April 2, 2010 12:00 pm \nTitle: Diversity Classes Fail\nA [literature survey] published last year \u2026 and found no empirical support for the idea that diversity training programs change attitudes or behavior. Similarly, a 2008 literature review \u2026 found \u2026 there were few trustworthy studies \u2013 and decidedly mixed results among those. And research by a team of sociologists on more than 800 companies over three decades has found that the best diversity training programs make little difference in who gets hired and promoted, and many programs actually decrease the number of women and minorities in management. \u2026Practitioners and some scholars disagree, arguing \u2026 the field as a whole has begun to figure out what works. The changes that training triggers can often be subtle, defenders argue, and, in a setting as dynamic and stubbornly multivariate as the workplace, it\u2019s all but impossible to come up with the clear, falsifiable evidence social science demands. The poor results that do show up in broad-based studies, they say, are due to companies whose commitment to diversity training programs is merely pro forma, and who see training as just a way to protect themselves from lawsuits. \u2026What worked much better than even the best training \u2026 were more structural measures: minority mentoring programs, or designating an executive or a task force with specific responsibility to change promotion practices.More here. So if courts would just clearly signal that they will no longer give firms legal credit in bias lawsuits for having diversity programs, firms would quickly stop, and we\u2019d stop wasting billions.\u00a0 Will courts do this?Not anytime soon.\u00a0 Admitting these programs don\u2019t work would lower the status of legal elites who suggested they would work, and such elites can rationalize this expense as a signal of our society\u2019s commitment to diversity.\n\n###\n\n", "completion": " The problem is that while \u201cburning money\u201d can indeed signal values, it can be hard to tell what values exactly it signals.\u00a0 Elites might say diversity programs show our concern for to minorities, but observers may come to reasonably see them as showing only a concern for the high status of current legal elites.\n\n@@@\n\n"}
{"prompt": "Date: September 2, 2014 4:00 pm\n\n###\n\n", "completion": " Title: Do Economists Care?\n\n@@@\n\n"}
{"prompt": "Date: September 2, 2014 4:00 pm \nTitle: Do Economists Care?\n\n###\n\n", "completion": " Art Carden:Heavy traffic is a problem every economist in the world knows how to solve: price road access, and charge high prices during rush hour. With technologies like E-ZPass and mobile apps, it\u2019s easier than ever. That we don\u2019t pick this low-hanging fruit is a pretty serious indictment of public policy. If we can\u2019t address what is literally a principles-level textbook example of a negative spillover with a fairly easy fix, what hope do we have for effective public policy on other margins? (more)Yes! If economists actually cared about influencing real policy, they would:\n\n@@@\n\n"}
{"prompt": "Date: December 12, 2006 6:00 am\n\n###\n\n", "completion": " Title: Do Helping Professions Help More?\n\n@@@\n\n"}
{"prompt": "Date: December 12, 2006 6:00 am \nTitle: Do Helping Professions Help More?\n\n###\n\n", "completion": " A student told me the other day he wanted to be a doctor, so he could help people.\u00a0 I thought, \"What, as opposed to the rest of us who hurt people?\"\u00a0 Contrary to the smug self-righteousness assumptions of those in \"helping\" professions, like child care, teaching, counseling, or emergency services, it is far from obvious that these professions are any more helpful than the rest.\u00a0   Yes, if you choose to be a doctor, you will spend your time providing services that people perceive to have value, sometimes enormous value.\u00a0 \u00a0However, you cannot take full credit for this value:  \n\n@@@\n\n"}
{"prompt": "Date: September 27, 2011 9:10 am\n\n###\n\n", "completion": " Title: Do Liars Care More?\n\n@@@\n\n"}
{"prompt": "Date: September 27, 2011 9:10 am \nTitle: Do Liars Care More?\n\n###\n\n", "completion": " One of the biggest lies we tell is not having favorite kids:It\u2019s one of the worst-kept secrets of family life that all parents have a preferred son or daughter, and the rules for acknowledging it are the same everywhere: The favored kids recognize their status and keep quiet about it. \u2026 The unfavored kids howl about it like wounded cats. And on pain of death, the parents deny it all. \u2026384 sibling pairs \u2026 [were] questioned \u2026 and videotaped \u2026 as they worked through conflicts. Overall, \u2026 65% of mothers and 70% of fathers exhibited a preference for one child, usually the older one. \u2026 \u201cThe most likely candidate for the mother\u2019s favorite was the firstborn son, and for the father, it was the last-born daughter. \u201d \u2026Firstborns have a 3-point IQ advantage over later siblings. \u2026 Kids who felt less loved than other siblings were more likely to develop anxiety, low self-esteem and depression. (more)Interestingly, lying here is seen by many to signal caring:Not all experts agree on just what the impact of favoritism is, but as a rule, their advice to parents is simple: If you absolutely must have a favorite (and you must), keep it to yourself. Even if your kids see through the ruse, the mere act of trying to maintain it can help them preserve the emotional pretext too \u2014 a bit of denial that does little harm. What\u2019s more, the effort it takes to tell a benign lie is in its own way an act of love toward the unfavored child.Its not clear though how often disfavored kids see self-serving denials as showing care. Do parents who care more about disfavored kids actually lie more than others?Also, we less resent favoritism to lower status siblings:\n\n@@@\n\n"}
{"prompt": "Date: September 27, 2011 9:10 am \nTitle: Do Liars Care More?\nOne of the biggest lies we tell is not having favorite kids:It\u2019s one of the worst-kept secrets of family life that all parents have a preferred son or daughter, and the rules for acknowledging it are the same everywhere: The favored kids recognize their status and keep quiet about it. \u2026 The unfavored kids howl about it like wounded cats. And on pain of death, the parents deny it all. \u2026384 sibling pairs \u2026 [were] questioned \u2026 and videotaped \u2026 as they worked through conflicts. Overall, \u2026 65% of mothers and 70% of fathers exhibited a preference for one child, usually the older one. \u2026 \u201cThe most likely candidate for the mother\u2019s favorite was the firstborn son, and for the father, it was the last-born daughter. \u201d \u2026Firstborns have a 3-point IQ advantage over later siblings. \u2026 Kids who felt less loved than other siblings were more likely to develop anxiety, low self-esteem and depression. (more)Interestingly, lying here is seen by many to signal caring:Not all experts agree on just what the impact of favoritism is, but as a rule, their advice to parents is simple: If you absolutely must have a favorite (and you must), keep it to yourself. Even if your kids see through the ruse, the mere act of trying to maintain it can help them preserve the emotional pretext too \u2014 a bit of denial that does little harm. What\u2019s more, the effort it takes to tell a benign lie is in its own way an act of love toward the unfavored child.Its not clear though how often disfavored kids see self-serving denials as showing care. Do parents who care more about disfavored kids actually lie more than others?Also, we less resent favoritism to lower status siblings:\n\n###\n\n", "completion": " Even the most blatant favoritism is easier to take when there\u2019s a defensible reason for it. Perhaps the most extreme example is when one child in the home has special needs. Children with Down syndrome or autism \u2026 Kids with physical disabilities \u2026 require more time and attention from parents \u2026 Talking about the situation openly is the best and most direct way to limit resentment. \u2026 \u201cResearch suggests that differential treatment may have no negative effects when children understand why.\u201dOh kids understand favoritism toward smarter, prettier, stronger siblings \u2013 they just hate it more.I suspect that many commonly told lies are accepted and even encouraged because they are seen by many as showing that liars care. Cynics who tell the truth are, in contrast, described as cold and hostile. A problem, of course, is that we often believe our lies, leading to mistaken inferences and decisions. Which may be why humans often seem so oblivious to \u201cobvious\u201d implications of their \u201cbeliefs.\u201d\n\n@@@\n\n"}
{"prompt": "Date: July 24, 2010 10:00 am\n\n###\n\n", "completion": " Title: Do One-Eyed Rule Blind?\n\n@@@\n\n"}
{"prompt": "Date: July 24, 2010 10:00 am \nTitle: Do One-Eyed Rule Blind?\n\n###\n\n", "completion": " A 1904 H.G. Wells short story, \u201cCountry of the Blind\u201c, questioned the old proverb \u201cIn the country of the blind, the one-eyed man is king.\u201d  In the story, a sighted man stumbles into a long isolated mountain valley where where everyone has been blind for generations, and have adapted their social customs and other senses to being blind. \u00a0This new man assumes he will soon be king, but to the locals he seems incompetent:They thrust him suddenly through a doorway into a room as black as pitch, save at the end there faintly glowed a fire. The crowd closed in behind him and shut out all but the faintest glimmer of day, and before he could arrest himself he had fallen headlong over the feet of a seated man. His arm, outflung, struck the face of someone else as he went down.His attempts to prove he can see things they cannot go badly. \u00a0He underestimates what they can sense via sound:He would show these people once and for all what sight would do for a man. They would seek him, but not find him.\u201cYou move not, Bogota,\u201d said the voice.He laughed noiselessly and made two stealthy steps aside from the path.\u201cTrample not on the grass, Bogota; that is not allowed.\u201dNunez had scarcely heard the sound he made himself. He stopped, amazed.He also miss-specifies a test he offers to pass:He induced them to let him go a long way up the sloping meadows towards the wall with one complaisant individual, and to him he promised to describe all that happened among the houses. He noted certain goings and comings, but the things that really seemed to signify to these people happened inside of or behind the windowless houses\u2013the only things they took note of to test him by\u2013and of those he could see or tell nothing.\n\n@@@\n\n"}
{"prompt": "Date: July 24, 2010 10:00 am \nTitle: Do One-Eyed Rule Blind?\nA 1904 H.G. Wells short story, \u201cCountry of the Blind\u201c, questioned the old proverb \u201cIn the country of the blind, the one-eyed man is king.\u201d  In the story, a sighted man stumbles into a long isolated mountain valley where where everyone has been blind for generations, and have adapted their social customs and other senses to being blind. \u00a0This new man assumes he will soon be king, but to the locals he seems incompetent:They thrust him suddenly through a doorway into a room as black as pitch, save at the end there faintly glowed a fire. The crowd closed in behind him and shut out all but the faintest glimmer of day, and before he could arrest himself he had fallen headlong over the feet of a seated man. His arm, outflung, struck the face of someone else as he went down.His attempts to prove he can see things they cannot go badly. \u00a0He underestimates what they can sense via sound:He would show these people once and for all what sight would do for a man. They would seek him, but not find him.\u201cYou move not, Bogota,\u201d said the voice.He laughed noiselessly and made two stealthy steps aside from the path.\u201cTrample not on the grass, Bogota; that is not allowed.\u201dNunez had scarcely heard the sound he made himself. He stopped, amazed.He also miss-specifies a test he offers to pass:He induced them to let him go a long way up the sloping meadows towards the wall with one complaisant individual, and to him he promised to describe all that happened among the houses. He noted certain goings and comings, but the things that really seemed to signify to these people happened inside of or behind the windowless houses\u2013the only things they took note of to test him by\u2013and of those he could see or tell nothing.\n\n###\n\n", "completion": " The claim isn\u2019t that a person with a powerful new insight could never prove it to others. Rather, the point is that someone with a new insight could easily fail by arrogance, assuming his insight offers more than it does, and underestimating what can be done, and how things look, without it.The sighted person in this story could have succeeded by carefully mastering the usual skills and practices of the blind, and then carefully seeking simple clear ways to show how his new ability could give advantage, in the context of their usual practices. \u00a0Assuming instead that your new insight excuses you from the need to follow the usual social paths, or to learn the usual insights and skills of your chosen area, is a recipe for failure.\n\n@@@\n\n"}
{"prompt": "Date: March 19, 2020 12:00 pm\n\n###\n\n", "completion": " Title: Do You Feel Lucky, Punk?\n\n@@@\n\n"}
{"prompt": "Date: March 19, 2020 12:00 pm \nTitle: Do You Feel Lucky, Punk?\n\n###\n\n", "completion": " A recent influential\u00a0report posed the key Covid-19 issue today as: to mitigate or suppress? Should we focus on \u201cflattening the curve\u201d under the assumption that most everyone will get it soon, or adopt even stronger measures in an attempt to squash it, so most never get it.Some simple obvious considerations are:\n\n@@@\n\n"}
{"prompt": "Date: April 22, 2021 9:30 am\n\n###\n\n", "completion": " Title: Do Your Thoughts Scale?\n\n@@@\n\n"}
{"prompt": "Date: April 22, 2021 9:30 am \nTitle: Do Your Thoughts Scale?\n\n###\n\n", "completion": " Most intellectuals don\u2019t pick their topics based on fundamental value. They instead opportunistically read the many clues around them regarding on which topics they are more likely to be rewarded. Now if you, in contrast, have the slack and inclination to instead pursue what seems fundamentally important, I salute you. And to help you, I now review some related considerations that you might overlook:\n\n@@@\n\n"}
{"prompt": "Date: December 7, 2007 6:00 am\n\n###\n\n", "completion": " Title: Doctor Hypocrisy\n\n@@@\n\n"}
{"prompt": "Date: December 7, 2007 6:00 am \nTitle: Doctor Hypocrisy\n\n###\n\n", "completion": " The fact that your life would be easier if you could trust someone does not make that person trustworthy.\u00a0 Doctors are a good example.\u00a0 Wednesday\u2019s Post: \n\n@@@\n\n"}
{"prompt": "Date: June 12, 2015 1:30 pm\n\n###\n\n", "completion": " Title: Doing Good \u2260 Being Good\n\n@@@\n\n"}
{"prompt": "Date: June 12, 2015 1:30 pm \nTitle: Doing Good \u2260 Being Good\n\n###\n\n", "completion": " Most of us like to be associated with \u201cidealistic\u201d groups that claim that they are doing good, i.e., making the world better. However, this is usually not our strongest motive in choosing to associate with such groups. Instead, we more strongly want to make ourselves look good, and gain good-looking associations. Most idealistic groups quickly learn to cater to this\u00a0demand by:\n\n@@@\n\n"}
{"prompt": "Date: June 9, 2014 9:40 am\n\n###\n\n", "completion": " Title: Don\u2019t Be \u201cRationalist\u201d\n\n@@@\n\n"}
{"prompt": "Date: June 9, 2014 9:40 am \nTitle: Don\u2019t Be \u201cRationalist\u201d\n\n###\n\n", "completion": " The first principle is that you must not fool yourself \u2014 and you are the easiest person to fool. Richard\u00a0Feynman.\u00a0This blog is called \u201cOvercoming Bias,\u201d and many of you readers consider yourselves \u201crationalists,\u201d i.e., folks who try harder than usual to overcome your\u00a0biases. But even if you want to devote yourself to being more honest and accurate, and to avoiding bias, there\u2019s a good reason for you not to present yourself as a \u201crationalist\u201d in general. The reason is this: you must allocate a very limited budget of rationality.It seems obvious to me that almost no humans are able to force themselves to see honestly and without substantial bias on all topics. Even for the best of us, the biasing forces in and around us are often much stronger than our will to avoid bias. Because it takes effort to overcome these forces, we must choose our battles, i.e., we must choose where to focus our efforts to attend carefully to avoiding possible biases. I see four key issues:1. Priorities \u2013 You should spend your rationality budget where truth matters most to you. You can\u2019t have it all, so you must\u00a0decide what matters most. For example, if you care mainly about helping others, and if they mainly rely on you via a particular topic, then you should focus your honesty on that topic. In particular, if you help the world mainly via your plumbing, then you should try to be honest about plumbing. Present yourself to the world\u00a0as someone who is honest on\u00a0plumbing, but not necessarily on\u00a0other things. In this scenario we\u00a0work together by being\u00a0honest on\u00a0different topics. We aren\u2019t \u201crationalists\u201d; instead, we are each at best \u201crationalist on X.\u201d\n\n@@@\n\n"}
{"prompt": "Date: June 9, 2014 9:40 am \nTitle: Don\u2019t Be \u201cRationalist\u201d\nThe first principle is that you must not fool yourself \u2014 and you are the easiest person to fool. Richard\u00a0Feynman.\u00a0This blog is called \u201cOvercoming Bias,\u201d and many of you readers consider yourselves \u201crationalists,\u201d i.e., folks who try harder than usual to overcome your\u00a0biases. But even if you want to devote yourself to being more honest and accurate, and to avoiding bias, there\u2019s a good reason for you not to present yourself as a \u201crationalist\u201d in general. The reason is this: you must allocate a very limited budget of rationality.It seems obvious to me that almost no humans are able to force themselves to see honestly and without substantial bias on all topics. Even for the best of us, the biasing forces in and around us are often much stronger than our will to avoid bias. Because it takes effort to overcome these forces, we must choose our battles, i.e., we must choose where to focus our efforts to attend carefully to avoiding possible biases. I see four key issues:1. Priorities \u2013 You should spend your rationality budget where truth matters most to you. You can\u2019t have it all, so you must\u00a0decide what matters most. For example, if you care mainly about helping others, and if they mainly rely on you via a particular topic, then you should focus your honesty on that topic. In particular, if you help the world mainly via your plumbing, then you should try to be honest about plumbing. Present yourself to the world\u00a0as someone who is honest on\u00a0plumbing, but not necessarily on\u00a0other things. In this scenario we\u00a0work together by being\u00a0honest on\u00a0different topics. We aren\u2019t \u201crationalists\u201d; instead, we are each at best \u201crationalist on X.\u201d\n\n###\n\n", "completion": " 2. Costs \u2013 All else equal, it is harder to be honest on more and wider topics, on topics where people tend to have emotional attachments, and on topics close to the key bias issues of the value and morality of you and your associates and rivals. You can reasonably expect to be honest about a wide range of topics that few people care much about, but only on a few narrow topics where many people care lots. The close you get to dangerous topics, the smaller your focus of honesty can\u00a0be. You can\u2019t be both a generalist and a rationalist; specialize in something.3. Contamination \u2013 You should try to avoid dependencies between your beliefs on focus topics where you will try to protect your honesty, and the topics where you are prone to bias. Try not to have your opinions on focus topics depend on a belief that you or your associates are especially smart, perceptive, or moral. If you must think on risky topics about people, try to first study other people you don\u2019t care much about. If you must have\u00a0an opinion on\u00a0yourself, assume you are like most other\u00a0people.4. Incentives \u2013 I\u2019m not a big fan of the \u201cstudy examples of bias and then will yourself to avoid them\u201d approach; it has a place, but gains there seem small compared to changing your environment to improve your incentives. Instead of pulling yourself up by your bootstraps, step onto higher ground. For example, by creating and participating in a prediction market on a topic, you can induce yourself to become more honest on that topic. The more you can create personal direct costs of\u00a0your dishonesty, the more honest you will become. And if you get paid to work on a certain topic, maybe you should give up on honesty about\u00a0who if anyone should be paid to do that.So my advice is to choose a focus for your honesty, a narrow enough focus to have a decent chance at achieving honesty. Make your focus\u00a0more narrow\u00a0the more dangerous is your focus area. Try to insulate beliefs on your focus topics from beliefs on risky\u00a0topics like your own value, and try to arrange things so you will be penalized for dishonesty. Don\u2019t persent\u00a0yourself as a \u201crationalist\u201d who is more honest on all topics, but instead as at best \u201crationalist on X.\u201dSo, what is your X?\n\n@@@\n\n"}
{"prompt": "Date: May 20, 2011 12:00 pm\n\n###\n\n", "completion": " Title: Don\u2019t \u201cBelieve\u201d\n\n@@@\n\n"}
{"prompt": "Date: May 20, 2011 12:00 pm \nTitle: Don\u2019t \u201cBelieve\u201d\n\n###\n\n", "completion": " Why do people \u201cI believe X\u201d instead of just saying X?  Or \u201cI firmly believe in X?\u201d Consider the last ten \u201cbelieved\u201d claims from featured essay abstracts at the This I believe website:\n\n@@@\n\n"}
{"prompt": "Date: August 19, 2009 8:00 pm\n\n###\n\n", "completion": " Title: Downturns Are Not Existential Risks\n\n@@@\n\n"}
{"prompt": "Date: August 19, 2009 8:00 pm \nTitle: Downturns Are Not Existential Risks\n\n###\n\n", "completion": " Epidemics, wars, and quakes are distributed with long tails, so that most of the expected harm from such events are in the largest possible events.\u00a0 Most who are expected to die in epidemics die in events that kill much of the population.\u00a0 These long tail disasters plausibly embody existential risk \u2013 a risk to the existence of civilization and humanity.A new paper on economic downturns suggests that such events do not have long tails, and so are not existential concerns:In the rare-disasters setting, a key determinant of the equity premium is the size distribution of macroeconomic disasters, gauged by proportionate declines in per capita consumption or GDP. The long-term national-accounts data for up to 36 countries provide a large sample of disaster events of magnitude 10% or more. For this sample, a power-law density provides a good fit to the distribution of the ratio of normal to disaster consumption or GDP. The key parameter of the size distribution is the upper-tail exponent, alpha, estimated to be near 5, with a 95% confidence interval between 3-1/2 and 7. \u2026We work with the transformed disaster size z \u2261 1/(1-b), which is the ratio of normal to disaster consumption or GDP. \u2026 We start with a familiar (single) power law, which specifies the [probability] density function as f(z) = Az-\u03b1.For a long tail, alpha needs to be two or less.\n\n@@@\n\n"}
{"prompt": "Date: April 6, 2007 6:00 am\n\n###\n\n", "completion": " Title: Driving While Red\n\n@@@\n\n"}
{"prompt": "Date: April 6, 2007 6:00 am \nTitle: Driving While Red\n\n###\n\n", "completion": " We act concerned to prevent tickets for \"driving while black.\"\u00a0 \u00a0And I recently asked:\n\n@@@\n\n"}
{"prompt": "Date: May 30, 2010 8:00 am\n\n###\n\n", "completion": " Title: Drugs Don\u2019t Help\n\n@@@\n\n"}
{"prompt": "Date: May 30, 2010 8:00 am \nTitle: Drugs Don\u2019t Help\n\n###\n\n", "completion": " In 2003, Bush had the US govt start to pay for drugs for seniors. \u00a0This induced seniors to use lots more drugs, but they were not any healthier.We find that gaining prescription drug insurance through Medicare Part D was associated with an 63% increase in the number of annual prescriptions, but that obtaining prescription drug insurance is not significantly related to use of other health care services or health, as measured by functional status and self-reported health.  Among those in poorer health, we find that gaining prescription drug insurance was associated with a 56% increase in the number of annual prescriptions, and is not significantly related to health. (more)\n\n@@@\n\n"}
{"prompt": "Date: January 21, 2011 9:00 am\n\n###\n\n", "completion": " Title: Dumb Farmers\n\n@@@\n\n"}
{"prompt": "Date: January 21, 2011 9:00 am \nTitle: Dumb Farmers\n\n###\n\n", "completion": " Apparently the foraging life is more mentally demanding than is the farming life. \u00a0Brain size rose during the forager era, but fell during the farming era. During the industry era brain size is rising again, yet another way we are returning to forager ways with increasing wealth.Combined with social brain theory, that our brains are big to deal with complex social worlds, suggests farmer social worlds are less complex. \u00a0Perhaps this is because stronger town social norms better discourage hypocritical norm evasion.The data:Over the past 20,000 years, the average volume of the human male brain has decreased from 1,500 cubic centimeters to 1,350 cc, losing a chunk the size of a tennis ball. The female brain has shrunk by about the same proportion. \u2026 \u201cThis happened in China, Europe, Africa\u2014everywhere we look.\u201d \u2026  \u201cI think the best explanation for the decline in our brain size is the idiocracy theory.\u201dWhen population numbers were low, as was the case for most of our evolution, the cranium kept getting bigger. But as population went from sparse to dense in a given area, cranial size declined, highlighted by a sudden 3 to 4 percent drop in EQ starting around 15,000 to 10,000 years ago. \u201cWe saw that trend in Europe, China, Africa, Malaysia\u2014everywhere we looked.\u201d \u2026 Skulls of Europeans dating from the Bronze Age, 4,000 years ago, to medieval times. Over that period the land became even more densely packed, \u2026 [and] the brain shrank more quickly than did overall body size, causing EQ values to fall. \u2026 in fact, [this] pattern \u2026 is even more pronounced. \u2026What may have caused the trend \u2026 is selection against aggression. In essence, we domesticated ourselves, \u2026 Some 30 animals have been domesticated \u2026 and in the process every one of them has lost brain volume\u2014typically a 10 to 15 percent reduction compared with their wild progenitors. \u2026\n\n@@@\n\n"}
{"prompt": "Date: January 21, 2011 9:00 am \nTitle: Dumb Farmers\nApparently the foraging life is more mentally demanding than is the farming life. \u00a0Brain size rose during the forager era, but fell during the farming era. During the industry era brain size is rising again, yet another way we are returning to forager ways with increasing wealth.Combined with social brain theory, that our brains are big to deal with complex social worlds, suggests farmer social worlds are less complex. \u00a0Perhaps this is because stronger town social norms better discourage hypocritical norm evasion.The data:Over the past 20,000 years, the average volume of the human male brain has decreased from 1,500 cubic centimeters to 1,350 cc, losing a chunk the size of a tennis ball. The female brain has shrunk by about the same proportion. \u2026 \u201cThis happened in China, Europe, Africa\u2014everywhere we look.\u201d \u2026  \u201cI think the best explanation for the decline in our brain size is the idiocracy theory.\u201dWhen population numbers were low, as was the case for most of our evolution, the cranium kept getting bigger. But as population went from sparse to dense in a given area, cranial size declined, highlighted by a sudden 3 to 4 percent drop in EQ starting around 15,000 to 10,000 years ago. \u201cWe saw that trend in Europe, China, Africa, Malaysia\u2014everywhere we looked.\u201d \u2026 Skulls of Europeans dating from the Bronze Age, 4,000 years ago, to medieval times. Over that period the land became even more densely packed, \u2026 [and] the brain shrank more quickly than did overall body size, causing EQ values to fall. \u2026 in fact, [this] pattern \u2026 is even more pronounced. \u2026What may have caused the trend \u2026 is selection against aggression. In essence, we domesticated ourselves, \u2026 Some 30 animals have been domesticated \u2026 and in the process every one of them has lost brain volume\u2014typically a 10 to 15 percent reduction compared with their wild progenitors. \u2026\n\n###\n\n", "completion": " \u201cWild types and domesticates think differently.\u201d \u2026 Wolves, with their larger brains, are more prone to flashes of insight, allowing them to solve problems on their own; dogs, with smaller brains, excel at using humans to help them. \u201cWolves seem to be a little bit more persistent than dogs in solving simple problems like how to open a box or navigate a detour,\u201d Hare says. \u201cWolves persevere when dogs readily give up.\u201d On the flip side, dogs leave wolves in the dust when it comes to tracking the gaze and gestures of their masters. \u2026He suspects that [bonobos] are domesticated chimps. \u2026 \u201cBonobos look and behave like juvenile chimps \u2026 They are gracile. They never show lethal aggression and do not kill each other. They also have brains that are 20 percent smaller than those of chimps.\u201d Hare thinks bonobos became domesticated by occupying an ecological niche that favored selection for less aggressive tendencies. \u2026When \u2026 Richard Jantz \u2026 measured the craniums of Americans of European and African descent from colonial times up to the late 20th century, he found that brain volume was once again moving upward. (more)Added 7p: Many suggest we explain this via lower farmer nutrition. \u00a0But this would much better explain a sudden fall than a steady gradual decline.\n\n@@@\n\n"}
{"prompt": "Date: May 15, 2010 6:00 pm\n\n###\n\n", "completion": " Title: Dumping on Denial\n\n@@@\n\n"}
{"prompt": "Date: May 15, 2010 6:00 pm \nTitle: Dumping on Denial\n\n###\n\n", "completion": " New Scientist on \u201cdenialism\u201d:SPECIAL REPORT / DENIAL:  From climate change to vaccines, evolution to flu, denialists are on the march. Why are so many people refusing to accept what the evidence is telling them? Over the next 10 pages we look at the phenomenon in depth.  What is denial? What attracts people to it? How does it start, and how does it spread? And finally, how should we respond to it?First, they dispel any doubts that denialists are wrong wrong wrong:All denialists see themselves as underdogs fighting a corrupt elite. \u2026How to be a denialist \u2026. Six tactics that all denialist movements use: 1. Allege that there\u2019s a conspiracy. \u2026 2. Use fake experts. \u2026 3. Cherry-pick the evidence. \u2026 4. Create impossible standards for your opponents. \u2026 5. Use logical fallacies. \u2026 6. Falsely portray scientists as \u2026 divided \u2026 Insist \u201cboth sides\u201d must be heard and cry censorship when \u201cdissenting\u201d arguments or experts are rejected. (more)Eventually they offer solutions. \u00a0Here are all remedies offered:\n\n@@@\n\n"}
{"prompt": "Date: February 15, 2014 9:10 pm\n\n###\n\n", "completion": " Title: Dust In The Wind\n\n@@@\n\n"}
{"prompt": "Date: February 15, 2014 9:10 pm \nTitle: Dust In The Wind\n\n###\n\n", "completion": " All we are is dust in the wind. (Song lyrics)Alex:Contra Tyler, the lesson of history is that few things are as effective at launching a revolution as is moral argument. Without the firebrand Thomas \u201cWe have it in our power to begin the world over again\u201c Paine, the American Revolution would probably never have happened. (more)Imagine standing at the shore of a river. You scoop a handful of water, and throw it downstream. By how much do you expect that act to change the flow of the river into the ocean miles downstream? I expect the effect to be far less than a handful of water arriving a few seconds earlier. More like a few atoms arriving a few seconds earlier. The speed of a river is a balance between gravity and friction, and that balance is likely to be quickly restored after disturbances like throwing a handful of water.This seems a pretty typical example of influencing the physical world. The vast majority of such influences quickly disappear. So if you want your influence to last, you have to choose carefully. For example, since on Earth nature only rarely moves big stones, you might succeed in assembling a stone wall that lasts for thousands of years. At least if other people don\u2019t want to knock it down.Now consider trying to have a long term social influence. As with physical influence, we should expect that most efforts to influence the social world also diminish quickly away from the point of influence. After all, many aspects of the social world also result from balances between opposing forces. For example, if US independence was largely inevitable in the long run, then Thomas Paine could have at most influenced when exactly when the US became independent.\n\n@@@\n\n"}
{"prompt": "Date: February 15, 2014 9:10 pm \nTitle: Dust In The Wind\nAll we are is dust in the wind. (Song lyrics)Alex:Contra Tyler, the lesson of history is that few things are as effective at launching a revolution as is moral argument. Without the firebrand Thomas \u201cWe have it in our power to begin the world over again\u201c Paine, the American Revolution would probably never have happened. (more)Imagine standing at the shore of a river. You scoop a handful of water, and throw it downstream. By how much do you expect that act to change the flow of the river into the ocean miles downstream? I expect the effect to be far less than a handful of water arriving a few seconds earlier. More like a few atoms arriving a few seconds earlier. The speed of a river is a balance between gravity and friction, and that balance is likely to be quickly restored after disturbances like throwing a handful of water.This seems a pretty typical example of influencing the physical world. The vast majority of such influences quickly disappear. So if you want your influence to last, you have to choose carefully. For example, since on Earth nature only rarely moves big stones, you might succeed in assembling a stone wall that lasts for thousands of years. At least if other people don\u2019t want to knock it down.Now consider trying to have a long term social influence. As with physical influence, we should expect that most efforts to influence the social world also diminish quickly away from the point of influence. After all, many aspects of the social world also result from balances between opposing forces. For example, if US independence was largely inevitable in the long run, then Thomas Paine could have at most influenced when exactly when the US became independent.\n\n###\n\n", "completion": " But what if there are tipping points? Imagine that a burst of floodwater came to the edge of overflowing a dam. An overflow might dig a channel leading in a new direction, changing the course of a river for a long time to come. So adding or subtracting just a little water near that overflow point might have a big long term effect. Can this metaphor give us more hope for long term social influence?Well first, such tipping points must be rare \u2013 the vast majority of points can\u2019t tip very far. Second, when many people can influence a social event, not only are most people only a drop in a tide of influence, most people are also only a drop in a tide of information. For example, imagine that people were pushing for or against US independence based on their best info on if that is good for the world. In this case Paine could only be in a position to tip the outcome if many other people also could tip the outcome, and if they were pushing in many different directions, with their net effects nearly balancing out.In a case like this, Paine couldn\u2019t be at all sure that a US revolution was a good idea. After all, an awful lot of people would have best info suggesting it was not a good idea. And in fact Bryan Caplan makes a good case that it wasn\u2019t in fact a good idea.Of course many people might have been pushing based on private interests, instead of a common good. But this still wouldn\u2019t give Paine much reason for confidence in his tipping the world to a better place. Either many others would try to help the world, or Paine couldn\u2019t have good reason to think he is the only exception.So are there any good ways to have long term influence? One idea is to find a social situation like the stone wall, where you can add things that aren\u2019t likely to get moved, and where your stones aren\u2019t likely to be added anyway a bit later by someone else. Perhaps doing intellectual work on highly neglected topics is something like this.See also: Long Legacies\n\n@@@\n\n"}
{"prompt": "Date: August 16, 2010 6:00 am\n\n###\n\n", "completion": " Title: Dvorsky Matures\n\n@@@\n\n"}
{"prompt": "Date: August 16, 2010 6:00 am \nTitle: Dvorsky Matures\n\n###\n\n", "completion": " Futurist George Dvorsky:A popular notion amongst futurists \u2026 is \u2026 that we can proactively engineer the kind of future we want to live in. \u2026 I myself have been seduced by this idea. \u2026 Trouble is, we\u2019re mostly deluded about this.  Now, I don\u2019t deny that we should collectively work to build a desirable future \u2026 What I am concerned about, however, is the degree to which we can actually control our destiny. While I am not an outright technological determinist, I am pretty damn close. As our technologies increase in power and sophistication, and as unanticipated convergent effects emerge from their presence, we will increasingly find ourselves having to deal with the consequences. \u2026For example, consider the remedial ecology and geoengineering concepts. \u2026. Breaking down toxic wastes and removing carbon from the atmosphere was not anything anybody would have desired a century ago. \u2026The Cold War \u2026 we have no reason to believe that a similar arrangement couldn\u2019t happen again, especially when considering \u2026 nuclear proliferation and \u2026 nanoweapons and robotic armadas. \u2026 We are slaves to technological adaptationism. \u2026 In order to avoid our extinction, \u2026 we may be compelled to alter our social structures, values, technological areas of inquiry and even ourselves in order to adapt. As to whether or not such a future is desirable by today\u2019s standards is an open question.Bravo George.  These are hard truths; not the sort that throngs of enthusiastic futurists will applaud in keynote speeches. I\u2019d say it isn\u2019t so much that \u201ctechnologies increase in power and sophistication\u201d as that coordination is hard. \u00a0Yes it can be hard to anticipate how changes, including new tech changes, will interact. \u00a0But even when we can anticipate changes we find it very hard to coordinate to act on such warnings. \u00a0Only the most extreme warnings will move us, and we have little interest in funding efforts to find warnings to consider.\n\n@@@\n\n"}
{"prompt": "Date: August 16, 2010 6:00 am \nTitle: Dvorsky Matures\nFuturist George Dvorsky:A popular notion amongst futurists \u2026 is \u2026 that we can proactively engineer the kind of future we want to live in. \u2026 I myself have been seduced by this idea. \u2026 Trouble is, we\u2019re mostly deluded about this.  Now, I don\u2019t deny that we should collectively work to build a desirable future \u2026 What I am concerned about, however, is the degree to which we can actually control our destiny. While I am not an outright technological determinist, I am pretty damn close. As our technologies increase in power and sophistication, and as unanticipated convergent effects emerge from their presence, we will increasingly find ourselves having to deal with the consequences. \u2026For example, consider the remedial ecology and geoengineering concepts. \u2026. Breaking down toxic wastes and removing carbon from the atmosphere was not anything anybody would have desired a century ago. \u2026The Cold War \u2026 we have no reason to believe that a similar arrangement couldn\u2019t happen again, especially when considering \u2026 nuclear proliferation and \u2026 nanoweapons and robotic armadas. \u2026 We are slaves to technological adaptationism. \u2026 In order to avoid our extinction, \u2026 we may be compelled to alter our social structures, values, technological areas of inquiry and even ourselves in order to adapt. As to whether or not such a future is desirable by today\u2019s standards is an open question.Bravo George.  These are hard truths; not the sort that throngs of enthusiastic futurists will applaud in keynote speeches. I\u2019d say it isn\u2019t so much that \u201ctechnologies increase in power and sophistication\u201d as that coordination is hard. \u00a0Yes it can be hard to anticipate how changes, including new tech changes, will interact. \u00a0But even when we can anticipate changes we find it very hard to coordinate to act on such warnings. \u00a0Only the most extreme warnings will move us, and we have little interest in funding efforts to find warnings to consider.\n\n###\n\n", "completion": " So futurists would do well to follow economists\u2019 usual analysis strategy: make your best guess about what things will be like if we do nothing to change them, and then try to sign the gains from moving parameters in particular directions away from that best guess. As I said in June:When our ability to influence the future is quite limited, then our first priority\u00a0must be to make a best guess of what the future will actually be like, if we exert no influence. This best guess should not be a wishful assertion of our far values, it should be a near-real description of how we would actually bet, if the asset at risk in the bet wer something we really cared about strongly. And yes, that description may well be \u201ccynical.\u201d \u00a0With such a cynical would-bet best guess, one should then spend most of one\u2019s efforts asking which\u00a0small variations on this scenario one would most prefer, and what kinds of actions could most usefully and reliably move the future toward these preferred scenarios. (Econ marginal analysis can help here.) \u00a0And then one should start doing such things.Once you can guess which directions are \u201cup\u201d, you can work to push outcomes in such directions. \u00a0Even if you can\u2019t push very far, you may still do the best you can, and perhaps make an important difference.\n\n@@@\n\n"}
{"prompt": "Date: April 24, 2008 8:00 am\n\n###\n\n", "completion": " Title: Early Scientists Chose Influence Over Credit\n\n@@@\n\n"}
{"prompt": "Date: April 24, 2008 8:00 am \nTitle: Early Scientists Chose Influence Over Credit\n\n###\n\n", "completion": " Last June I wrote:\n\n@@@\n\n"}
{"prompt": "Date: November 17, 2020 1:45 pm\n\n###\n\n", "completion": " Title: Easy Conspiracy Tests\n\n@@@\n\n"}
{"prompt": "Date: November 17, 2020 1:45 pm \nTitle: Easy Conspiracy Tests\n\n###\n\n", "completion": " The most obvious kind of conspiracies to expect in the world are ones between your local organized crime, police, and political powers. These powers should each see each other as rivals to their dominance. So to reduce such threats they should should seek to either weaken each other,\u00a0 or to ally with each other. There are rumors that such alliances are common around the world, and there is clear data that they have often happened in the past.\u00a0So this is no mere theoretical conspiracy theory, to be dismissed by claiming that too many people would know to keep it a secret. This sort of conspiracy is not only verifiably common, it also has a quite credible threat of punishing those who too publicly expose it.Given that this seems to usually be a real possibility, what sort of evidence might speak to it? Here are some indicators that, if true about your area, are at least weak evidence against such a local alliance:\n\n@@@\n\n"}
{"prompt": "Date: May 10, 2007 6:00 am\n\n###\n\n", "completion": " Title: Eclipsing Nobel\n\n@@@\n\n"}
{"prompt": "Date: May 10, 2007 6:00 am \nTitle: Eclipsing Nobel\n\n###\n\n", "completion": " Listening to older bigshot academics talking among themselves, I find they talk surprisingly often about the Nobel prize \u2013 who deserves it, who is being considered, who is lobbying how to win, who should have won but didn\u2019t, and so on.\u00a0 Their lust is obvious; the influence of the Nobel prize on elite academic incentives is far out of proportion to the money involved.\u00a0 \u00a0 It is surprising to see academia so influenced by one rich man from a century ago, rather than by rich men today.\u00a0 Prizes once mattered much more than they do today, and I expect a comeback:\u00a0 sometime in the next few decades I expect someone to pay a billion or two in an attempt to displace the Nobel prize.\u00a0 Compared to the usual academic money-influence ratio, this would be quite a bargain.\u00a0 \u00a0To succeed, this new Post-Nobel prize should:\n\n@@@\n\n"}
{"prompt": "Date: April 16, 2009 2:30 pm\n\n###\n\n", "completion": " Title: Efficient Economist\u2019s Pledge\n\n@@@\n\n"}
{"prompt": "Date: April 16, 2009 2:30 pm \nTitle: Efficient Economist\u2019s Pledge\n\n###\n\n", "completion": " Tuesday\u2019s debate with Bryan Caplan was great fun; thanks Bryan for being such a gentlemanly and compatible discussion partner!\u00a0 I don\u2019t know when an official vid will be posted, but my amateur audio is here.\u00a0 In before and after audience polls, Liberty vs. Efficiency got 42-10 before, and 25-20 after.\u00a0 My argument and Bryan\u2019s many responses inspired me to compose this pledge:The Efficient Economist\u2019s PledgeI pledge to be an efficient economist, who helps clients find win-win deals to resolve social conflicts.I need not accept all clients, but for the clients I do accept, my suggested deals should, if accepted straight or as a starting point for negotiation, get them more of what they want, relative to no deal.\u00a0 I resist temptations to slant my advice to give hidden benefits to myself or my associates.\u00a0 I accept my client\u2019s situation and wants as they are, and unless asked do not preach to them on what they should want.\u00a0 When actions conflict with words, I mostly infer wants from actions, and avoid needlessly exposing contradictions.For individual clients, I suggest actions that try to best get them what they want. When I advise groups of clients together, I seek win-win deals for them all together.\u00a0 That is, I seek ways to suggest deals with a high chance of putting each client in a situation where, given their limited info, they should expect to benefit from the resulting deals. And I seek the best deals; it should not be easy to find other deals which all should expect to get them even more.\u00a0 When trading client expected gains against the chance each expects to gain, I consider how many are needed to clinch a deal.\n\n@@@\n\n"}
{"prompt": "Date: May 1, 2007 2:43 pm\n\n###\n\n", "completion": " Title: EH Hunt helped LBJ Kill JFK?\n\n@@@\n\n"}
{"prompt": "Date: May 1, 2007 2:43 pm \nTitle: EH Hunt helped LBJ Kill JFK?\n\n###\n\n", "completion": " An audio tape has been released of Watergate conspirator and longtime CIA operative E. Howard Hunt confessing on his deathbed to helping Lyndon B. Johnson assassinate John F. Kennedy.\u00a0 I have no special expertise on this topic, but this seems on its face hard evidence to dismiss. I would dearly love to see a betting market on this topic, but since almost a half century has already passed, we may well have to wait another half century or more to see a clear resolution.The topic is fascinating because such claims have long been dismissed by \u201cestablishment\u201d media and academia, yet a minority of passionate advocates keep the topic alive.\u00a0 There are plenty of potential biases each side can use to explain why the other side disagrees.\u00a0 \u00a0So at what odds would you bet?Added: The lack of media coverage of this is odd (exceptions here, here, here.)\n\n@@@\n\n"}
{"prompt": "Date: January 8, 2018 8:35 pm\n\n###\n\n", "completion": " Title: Elephant in the Brain Reviews\n\n@@@\n\n"}
{"prompt": "Date: January 8, 2018 8:35 pm \nTitle: Elephant in the Brain Reviews\n\n###\n\n", "completion": " Its now one week after the official hardback release date, and five weeks after the ebook release, of Elephant in the Brain. So I guess its time to respond to the text reviews that have appeared so far. Reviews have appeared at Amazon (9), Goodreads (8), and on individual blogs (5). Most comments expressed are quite positive. But there\u2019s a big selection effect whereby people with negative opinions say nothing, and so readers rationally attend more to explicitly negative comments. And thus so will I. This post is looong.Out of the 9 Amazon reviews, 6 gave 5-star reviews, and the 4 star review had no criticisms. The 3 star reviews were Robert Castro, who called it \u201cOK but nothing new \u2013 a new packaging of known ideas,\u201d and Krishna Kaliannanon, who says:Some interesting ideas in this book, but they could be written in a far more concise manner. Perhaps 100 pages instead of ~400.Another low review seems to have been withdrawn, but it said that our thesis is obvious; only hippies would think otherwise.Out of the 8 GoodReads reviews, half give the book 5 stars and half 4 stars. Of the 4-star reviews, one of them had no complaint. Daniel Frank saidTo the unacquainted, I don\u2019t think this book is delicate or persuasive enough to convince them of its valuable messages.ChickCounterfly saidIt\u2019s accessible for general audiences, and I would say some sections could\u2019ve been improved by going a bit deeper and being a bit more challenging.Thore Husfeldt saidThese insights are shocking and important, but also available in many other recent introductions to social and evolutionary psychology. \u2026 Things I didn\u2019t like: The book\u2019s main metaphor, the Elephant in the Brain, does not do as much useful work as the authors may think. \u2026 The style is surprisingly light and accessible. \u2026 This is probably a good idea because it may widen the potential readership, but I had to cringe at some of the formulations.\n\n@@@\n\n"}
{"prompt": "Date: January 8, 2018 8:35 pm \nTitle: Elephant in the Brain Reviews\nIts now one week after the official hardback release date, and five weeks after the ebook release, of Elephant in the Brain. So I guess its time to respond to the text reviews that have appeared so far. Reviews have appeared at Amazon (9), Goodreads (8), and on individual blogs (5). Most comments expressed are quite positive. But there\u2019s a big selection effect whereby people with negative opinions say nothing, and so readers rationally attend more to explicitly negative comments. And thus so will I. This post is looong.Out of the 9 Amazon reviews, 6 gave 5-star reviews, and the 4 star review had no criticisms. The 3 star reviews were Robert Castro, who called it \u201cOK but nothing new \u2013 a new packaging of known ideas,\u201d and Krishna Kaliannanon, who says:Some interesting ideas in this book, but they could be written in a far more concise manner. Perhaps 100 pages instead of ~400.Another low review seems to have been withdrawn, but it said that our thesis is obvious; only hippies would think otherwise.Out of the 8 GoodReads reviews, half give the book 5 stars and half 4 stars. Of the 4-star reviews, one of them had no complaint. Daniel Frank saidTo the unacquainted, I don\u2019t think this book is delicate or persuasive enough to convince them of its valuable messages.ChickCounterfly saidIt\u2019s accessible for general audiences, and I would say some sections could\u2019ve been improved by going a bit deeper and being a bit more challenging.Thore Husfeldt saidThese insights are shocking and important, but also available in many other recent introductions to social and evolutionary psychology. \u2026 Things I didn\u2019t like: The book\u2019s main metaphor, the Elephant in the Brain, does not do as much useful work as the authors may think. \u2026 The style is surprisingly light and accessible. \u2026 This is probably a good idea because it may widen the potential readership, but I had to cringe at some of the formulations.\n\n###\n\n", "completion": " So far, no one says they disagree with our main thesis, but some say our thesis is too obvious and unoriginal. Some say we should have been more academic and detailed, while other say we should have been more accessible and less detailed.The Google page rank of the blogs where reviews have appeared is mostly low. Four have rank 0, and one has rank 4. (For comparison, this blog Overcoming Bias has rank 6, and my personal website has rank 5. The Boston Globe, where an interview appeared, and the Wall Street Journal, where I\u2019m hoping to see a review soon, each have rank 8.) I\u2019ll go through these blog reviews in chronological order.The first blog review to appear was 1300 words long, by Kieran McCarthy, who had these words of praise:Thoroughly enjoyable and easily digestible read on a difficult subject. The book is an excellent survey of the literature.His criticism:What do we do with that information? \u2026 This question was the central focus in the book\u2019s last chapter and conclusion. This was also what I considered the weakest part of the book. The authors\u2019 primary answer to the question is \u201csituational awareness.\u201d \u2026 [But] if one of the main theses in the book is that self deception is strategic and lack of self awareness in terms of our motivations serves a critical evolutionary purpose, how is it that situational awareness of that self deception can also be strategic? \u2026 It would appear that the authors fell into their own trap\u2014wishing for a pretty benefit to ascribe to our awareness of our hidden motivations, when the rest of the book tells us that the opposite is true.I thought we were pretty clear to say that while awareness is a benefit, we don\u2019t know when it is a net benefit. And the main benefit is for policy specialists. Book quotes:Even when we simply acknowledge the elephant to ourselves, in private, we burden our brains with self-consciousness and the knowledge of our own hypocrisy. These are real downsides, not to be shrugged off. \u2026 Beyond what we can do in our personal lives, however, is what we can do when we\u2019re in positions to influence policy or help reform institutions. This is where an understanding of the elephant really starts to pay off. Maybe most laypeople don\u2019t need to understand their hidden motives, but those who make policy probably should.The second blog review was 1400 words, by Diarmuid. Key summaries:I found a lot of sense in what they wrote, but at the same time wondered whether or not this is the sort of thesis that is unduly influenced by the prevailing mores or the dominant view of human nature. By the end of the book, I was still not sure that I felt comfortable with the objectivity of the thesis, but acknowledge that it is a theory that resonates and an argument that has been well put together. \u2026 On the whole, I found it an enjoyable read, but would have preferred more from part one [on general theory] and less from part two [on specific life areas]. It was hard to shrug off the suspicion that there were many people out there who would just as eloquently and convincingly shred the arguments put forward in part two \u2013 they seemed to be more interpretative than factual.I find it hard to see people as on the whole as biased toward accepting our thesis; see the social desirability bias. On specific life areas, Diarmuid seems to think we both have too much and too little detail; too little to justify our claims, and too much to be interesting.The third blog review was much longer, at 9200 words, by Zvi Mowshowitz. Overall Zvi likes the book:I highly recommend the book, especially to those not familiar with Overcoming Bias and claims of the type \u201cX is not about Y.\u201d The book feels like a great way to create common knowledge around the claims in question, a sort of Hansonian sequence. For those already familiar with such concepts, it will be fun and quick read, and still likely to contain some new insights for you. \u2026\n\n@@@\n\n"}
{"prompt": "So far, no one says they disagree with our main thesis, but some say our thesis is too obvious and unoriginal. Some say we should have been more academic and detailed, while other say we should have been more accessible and less detailed.The Google page rank of the blogs where reviews have appeared is mostly low. Four have rank 0, and one has rank 4. (For comparison, this blog Overcoming Bias has rank 6, and my personal website has rank 5. The Boston Globe, where an interview appeared, and the Wall Street Journal, where I\u2019m hoping to see a review soon, each have rank 8.) I\u2019ll go through these blog reviews in chronological order.The first blog review to appear was 1300 words long, by Kieran McCarthy, who had these words of praise:Thoroughly enjoyable and easily digestible read on a difficult subject. The book is an excellent survey of the literature.His criticism:What do we do with that information? \u2026 This question was the central focus in the book\u2019s last chapter and conclusion. This was also what I considered the weakest part of the book. The authors\u2019 primary answer to the question is \u201csituational awareness.\u201d \u2026 [But] if one of the main theses in the book is that self deception is strategic and lack of self awareness in terms of our motivations serves a critical evolutionary purpose, how is it that situational awareness of that self deception can also be strategic? \u2026 It would appear that the authors fell into their own trap\u2014wishing for a pretty benefit to ascribe to our awareness of our hidden motivations, when the rest of the book tells us that the opposite is true.I thought we were pretty clear to say that while awareness is a benefit, we don\u2019t know when it is a net benefit. And the main benefit is for policy specialists. Book quotes:Even when we simply acknowledge the elephant to ourselves, in private, we burden our brains with self-consciousness and the knowledge of our own hypocrisy. These are real downsides, not to be shrugged off. \u2026 Beyond what we can do in our personal lives, however, is what we can do when we\u2019re in positions to influence policy or help reform institutions. This is where an understanding of the elephant really starts to pay off. Maybe most laypeople don\u2019t need to understand their hidden motives, but those who make policy probably should.The second blog review was 1400 words, by Diarmuid. Key summaries:I found a lot of sense in what they wrote, but at the same time wondered whether or not this is the sort of thesis that is unduly influenced by the prevailing mores or the dominant view of human nature. By the end of the book, I was still not sure that I felt comfortable with the objectivity of the thesis, but acknowledge that it is a theory that resonates and an argument that has been well put together. \u2026 On the whole, I found it an enjoyable read, but would have preferred more from part one [on general theory] and less from part two [on specific life areas]. It was hard to shrug off the suspicion that there were many people out there who would just as eloquently and convincingly shred the arguments put forward in part two \u2013 they seemed to be more interpretative than factual.I find it hard to see people as on the whole as biased toward accepting our thesis; see the social desirability bias. On specific life areas, Diarmuid seems to think we both have too much and too little detail; too little to justify our claims, and too much to be interesting.The third blog review was much longer, at 9200 words, by Zvi Mowshowitz. Overall Zvi likes the book:I highly recommend the book, especially to those not familiar with Overcoming Bias and claims of the type \u201cX is not about Y.\u201d The book feels like a great way to create common knowledge around the claims in question, a sort of Hansonian sequence. For those already familiar with such concepts, it will be fun and quick read, and still likely to contain some new insights for you. \u2026\n\n###\n\n", "completion": " The second half did an excellent job of pointing out the signaling, status and strategic motives behind these areas of life. In this regard, I bought most of the book\u2019s claims. Such motives are all around us and central to almost everything involving multiple people. \u2026 This adds up to [my] buying about 90% of claims. For a book making so many bold claims, that\u2019s very good.Out of the ten life areas we covered, Zvi accepts on average roughly 100% of our claims in 8 of the areas, but only about 50% in two areas: conversation and consumption. His doubts:I do not think, as I believe Robin does, that most product variety and customization is worthless aside from signaling. \u2026\u00a0The value of inconspicuous consumption \u2026 is vastly underrated. I often end up buying the package of conspicuous and inconspicuous consumption together, but there\u2019s no other way to get the half I want. Perhaps that also means I am the exception that proves the rule. I can believe most people instead throw away the other half. If your restaurant consumption is, as the book claims, \u2018more for showing off\u2019 than for personal use, you are doing it wrong. Same with (from the same chart) mobile phones and living room furniture. \u2026I think \u2018conversation is about info\u2019 is more importantly true than \u2018conversation is not (entirely) about info.\u2019 \u2026 Are the puzzles even accurate? People can and do keep track of conversational debt. If you tell me something valuable, I owe you, and vice versa. \u2026 Relevant things build upon previously said things in valuable ways, and are likely to be of higher value. If I talk about what we should have for dinner and you tell me the capital of Brazil, chances are that\u2019s both not something I especially care about right now and also not helping. Similarly suboptimal exchange, since info has relative value based on context and what different people care about at different times. \u2026 But yes, people would benefit greatly if we paid more attention to talking about more valuable topics, and exchanging more valuable information.These sound to me like Zvi claiming that he puts an unusually high value, compared to others, on product variety and conversation info. But our book tries to estimate average motives; we are happy to admit that individuals vary. It still seems to me that most people get a lot less value than they\u2019d admit out of product variety and conversation info. Conversation debts seem rare, and small talk topic relevance rules don\u2019t usually create much info value.The fourth blog review was 1500 words, and is the one on a 4-rank blog, by philosopher Tristan Haze. He starts with praise:A fantastic synthesis of subversive social scientific insight into hidden (or less apparent) motives of human behaviour, and hidden (or less apparent) functions of institutions. Just understanding these matters is an intellectual thrill, and helpful in thinking about how the world works. Furthermore \u2013 and I didn\u2019t sufficiently appreciate this point until reading the book, \u2026 better understanding the real function of our institutions can help us improve them and prevent us from screwing them up. Lots of reform efforts, I have been convinced (especially for the case of schooling), are likely to make a hash of things due to taking orthodox views of institutions\u2019 functions too seriously.But as you might expect from a philosopher, he has two nits to pick regarding our exact use of words.\n\n@@@\n\n"}
{"prompt": "The second half did an excellent job of pointing out the signaling, status and strategic motives behind these areas of life. In this regard, I bought most of the book\u2019s claims. Such motives are all around us and central to almost everything involving multiple people. \u2026 This adds up to [my] buying about 90% of claims. For a book making so many bold claims, that\u2019s very good.Out of the ten life areas we covered, Zvi accepts on average roughly 100% of our claims in 8 of the areas, but only about 50% in two areas: conversation and consumption. His doubts:I do not think, as I believe Robin does, that most product variety and customization is worthless aside from signaling. \u2026\u00a0The value of inconspicuous consumption \u2026 is vastly underrated. I often end up buying the package of conspicuous and inconspicuous consumption together, but there\u2019s no other way to get the half I want. Perhaps that also means I am the exception that proves the rule. I can believe most people instead throw away the other half. If your restaurant consumption is, as the book claims, \u2018more for showing off\u2019 than for personal use, you are doing it wrong. Same with (from the same chart) mobile phones and living room furniture. \u2026I think \u2018conversation is about info\u2019 is more importantly true than \u2018conversation is not (entirely) about info.\u2019 \u2026 Are the puzzles even accurate? People can and do keep track of conversational debt. If you tell me something valuable, I owe you, and vice versa. \u2026 Relevant things build upon previously said things in valuable ways, and are likely to be of higher value. If I talk about what we should have for dinner and you tell me the capital of Brazil, chances are that\u2019s both not something I especially care about right now and also not helping. Similarly suboptimal exchange, since info has relative value based on context and what different people care about at different times. \u2026 But yes, people would benefit greatly if we paid more attention to talking about more valuable topics, and exchanging more valuable information.These sound to me like Zvi claiming that he puts an unusually high value, compared to others, on product variety and conversation info. But our book tries to estimate average motives; we are happy to admit that individuals vary. It still seems to me that most people get a lot less value than they\u2019d admit out of product variety and conversation info. Conversation debts seem rare, and small talk topic relevance rules don\u2019t usually create much info value.The fourth blog review was 1500 words, and is the one on a 4-rank blog, by philosopher Tristan Haze. He starts with praise:A fantastic synthesis of subversive social scientific insight into hidden (or less apparent) motives of human behaviour, and hidden (or less apparent) functions of institutions. Just understanding these matters is an intellectual thrill, and helpful in thinking about how the world works. Furthermore \u2013 and I didn\u2019t sufficiently appreciate this point until reading the book, \u2026 better understanding the real function of our institutions can help us improve them and prevent us from screwing them up. Lots of reform efforts, I have been convinced (especially for the case of schooling), are likely to make a hash of things due to taking orthodox views of institutions\u2019 functions too seriously.But as you might expect from a philosopher, he has two nits to pick regarding our exact use of words.\n\n###\n\n", "completion": " I want to point out what I think are two conceptual shortcomings in the book. \u2026\u00a0The authors seem to conflate the concept of common knowledge with the idea of being \u201cout in the open\u201d or \u201con the record\u201d. \u2026 This seems wrong to me. Something may satisfy the conditions for being common knowledge, but people may still not be OK talking about it openly. \u2026 They write: \u2018Common knowledge is the difference between (\u2026) a lesbian who\u2019s still in the closet (though everyone suspects her of being a lesbian), and one who\u2019s open about her sexuality; between an awkward moment that everyone tries to pretend didn\u2019t happen and one that everyone acknowledges\u2019 (p, 55). If we stick to the proper recursive explanation of \u2018common knowledge\u2019, these claims just seem wrong.We agree that the two concepts are in principle distinct. In practice the official definition of common knowledge almost never applies, though a related concept of common belief does often apply. But we claim that in practice a lack of common belief is the main reason for widely known things not being treated as \u201cout in the open\u201d. While the two concepts are not co-extensive, one is the main cause of the other. Tristan\u2019s other nit:Classical decision theory has it right: there\u2019s no value in sabotaging yourself per se. The value lies in convincing other players that you\u2019ve sabotaged yourself. (p. 67).This fits the game of chicken example pretty well. But it doesn\u2019t really fit the turning-your-phone-off example: what matters there is that your phone is off \u2013 it doesn\u2019t matter if the person wanting the favour thinks that your phone malfunctioned and turned itself off, rather than you turning it off. \u2026 It doesn\u2019t really matter how the kidnapper thinks it came about that you failed to see them \u2013 they don\u2019t need to believe you brought the failure on yourself for the strategy to be good.Yes, yes, in the quote above we were sloppy, and should have instead said \u201cThe value lies in convincing other players that you\u2019ve been sabotaged.\u201d It matters less who exactly caused you to be sabotaged.The fifth and final blog review is another long one, at 4400 words, by Jess Riedel. He is overall positive:Although there is much I am not convinced by, I find the general framework deeply insightful, and his presentation to be more clear, analytical, and descriptive (rather than disruptively normative) than other accounts. \u2026 I highly recommend it. \u2026 Let me emphasize: the basic ideas of this book strike me as profound and probably mostly true.But he has many critiques.I like that Hanson and Simler emphasize up front that many of the selfish motives they discuss are unconscious. \u2026 I wish the book had attempted to operationally define consciousness in this context. \u2026 It\u2019s true that, in many circumstances, it\u2019s difficult to unambiguously distinguish between conscious and unconscious effects, and there are varying degrees of conscious awareness. \u2026 The authors mostly ignore\u2009 the further distinction between (a) the evolutionary goal of an adaptation in the ancestral environment and (b) the execution of that adaptation. \u2026\u2009 For instance, people (especially men) plausibly like to win arguments to signal intelligence or social domination, but when they spend hours arguing anonymously on the internet, they aren\u2019t gaining status or prestige. \u2026Yes for each motive one can distinguish both a degree of consciousness and also a degree of current vs past adaptation. But these topics were not essential for our main thesis, making credible claims on them takes a lot more evidence and argument, and we already had trouble with trying to cover too much material for one book.\n\n@@@\n\n"}
{"prompt": "I want to point out what I think are two conceptual shortcomings in the book. \u2026\u00a0The authors seem to conflate the concept of common knowledge with the idea of being \u201cout in the open\u201d or \u201con the record\u201d. \u2026 This seems wrong to me. Something may satisfy the conditions for being common knowledge, but people may still not be OK talking about it openly. \u2026 They write: \u2018Common knowledge is the difference between (\u2026) a lesbian who\u2019s still in the closet (though everyone suspects her of being a lesbian), and one who\u2019s open about her sexuality; between an awkward moment that everyone tries to pretend didn\u2019t happen and one that everyone acknowledges\u2019 (p, 55). If we stick to the proper recursive explanation of \u2018common knowledge\u2019, these claims just seem wrong.We agree that the two concepts are in principle distinct. In practice the official definition of common knowledge almost never applies, though a related concept of common belief does often apply. But we claim that in practice a lack of common belief is the main reason for widely known things not being treated as \u201cout in the open\u201d. While the two concepts are not co-extensive, one is the main cause of the other. Tristan\u2019s other nit:Classical decision theory has it right: there\u2019s no value in sabotaging yourself per se. The value lies in convincing other players that you\u2019ve sabotaged yourself. (p. 67).This fits the game of chicken example pretty well. But it doesn\u2019t really fit the turning-your-phone-off example: what matters there is that your phone is off \u2013 it doesn\u2019t matter if the person wanting the favour thinks that your phone malfunctioned and turned itself off, rather than you turning it off. \u2026 It doesn\u2019t really matter how the kidnapper thinks it came about that you failed to see them \u2013 they don\u2019t need to believe you brought the failure on yourself for the strategy to be good.Yes, yes, in the quote above we were sloppy, and should have instead said \u201cThe value lies in convincing other players that you\u2019ve been sabotaged.\u201d It matters less who exactly caused you to be sabotaged.The fifth and final blog review is another long one, at 4400 words, by Jess Riedel. He is overall positive:Although there is much I am not convinced by, I find the general framework deeply insightful, and his presentation to be more clear, analytical, and descriptive (rather than disruptively normative) than other accounts. \u2026 I highly recommend it. \u2026 Let me emphasize: the basic ideas of this book strike me as profound and probably mostly true.But he has many critiques.I like that Hanson and Simler emphasize up front that many of the selfish motives they discuss are unconscious. \u2026 I wish the book had attempted to operationally define consciousness in this context. \u2026 It\u2019s true that, in many circumstances, it\u2019s difficult to unambiguously distinguish between conscious and unconscious effects, and there are varying degrees of conscious awareness. \u2026 The authors mostly ignore\u2009 the further distinction between (a) the evolutionary goal of an adaptation in the ancestral environment and (b) the execution of that adaptation. \u2026\u2009 For instance, people (especially men) plausibly like to win arguments to signal intelligence or social domination, but when they spend hours arguing anonymously on the internet, they aren\u2019t gaining status or prestige. \u2026Yes for each motive one can distinguish both a degree of consciousness and also a degree of current vs past adaptation. But these topics were not essential for our main thesis, making credible claims on them takes a lot more evidence and argument, and we already had trouble with trying to cover too much material for one book.\n\n###\n\n", "completion": " I think Simler and Hanson are making this mistake, at least in part, when they eagerly attribute so many ineffective or dangerous medical treatments to the desire to demonstrate care. Yes, people use prestige to guide their choice of treatment, and they often neglect careful analytical signals, but we can\u2019t confidently conclude they value signaling their own prestige more than their own life. \u2026 This isn\u2019t to say that the hidden desire to appear caring doesn\u2019t drive billions of dollars of waste in medicine, it just means people also make honest mistakes pursuing conventional goals.Sure, given any goal and any behavior, one can invoke an error theory to explained that behavior as a mistaken attempt to achieve that goal. The problem is that according to the error theory these deviations should be random. Thus theories that can explain the behavior more systematically can get stronger evidential support. Our book tries to offer such systematic theories.Why are so many of these selfish human motivation kept unconscious in the first place, rather than simply being conscious and well hidden? \u2026 The obvious rebuttal here is that we should just have evolved to not have those leaky, difficult-to-suppress emotional responses, or for those responses not to have evolved in the first place.We see a reasonably strong consensus in the literature that it is very hard to design brains to block all possible paths by which conscious motives can leak. We accept that consensus.Laughter does not occur very often in competitive but physically safe games. \u2026 Other observations that don\u2019t really seem to fit with play-signaling: (1) Laughter is used by women to signal their romantic interest in men, and more generally by anyone to signal that they like and approve of someone else. (2) Laughter is mostly restricted to situations in which expectations are violated (a property observed in the literature reviewed by the authors), but there are other times we need to signal play, and instead we use smiling, relaxed body language, etc. (3) Laughter is used to indicate we can distinguish jokes from non-jokes quickly, signaling intelligence.Jokes may be empirically connected to violated expectations, but I don\u2019t think laughter more generally is. I don\u2019t see how the other points here are at odds with laughter as play signal.I think the authors are too eager to interpret everything in terms of hidden motives rather than, e.g., cognitive limitations. \u2026 referees almost never discuss a work\u2019s long-term potential for substantial social benefit. \u2026 But wouldn\u2019t judgment of long-term benefit be highly subjective (and idiosyncratic), whereas technical mastery is relatively objective? \u2026 Ensuring \u201cspit and polish\u201d \u2014 that each individual detail is precise and correct \u2014 strikes me as something that may hinder authors but aids the literature as a whole.Yes, one can make such excuses. But as a long-time academic I\u2019ll say that the theory that our apparent focus on impressiveness is all really a complex clever plan to maximize long term research progress just doesn\u2019t pass the laugh test.Blue jeans, for example, are a symbol of egalitarian values, in part because denim is a cheap, durable, low-maintenance fabric that make wealth and class distinctions harder to detect. So conspicuous consumption signals wealth, but not doing this signals egalitarian values. What would the authors not interpret as signaling? \u2026 I get it, social dynamics are hard and plausible deniability is central to a lot of signaling, so we shouldn\u2019t be surprised that there are many ambiguous layers, counter-signaling, etc. But we should also admit this allows a signaling explanation for most isolated observations, and we should be more modest and careful about our claims.Come on, these aren\u2019t aliens we are talking about. Isn\u2019t it really obvious that overall people pay a lot of attention to how others will interpret their clothing choices? Is there really any question about this?\n\n@@@\n\n"}
{"prompt": "I think Simler and Hanson are making this mistake, at least in part, when they eagerly attribute so many ineffective or dangerous medical treatments to the desire to demonstrate care. Yes, people use prestige to guide their choice of treatment, and they often neglect careful analytical signals, but we can\u2019t confidently conclude they value signaling their own prestige more than their own life. \u2026 This isn\u2019t to say that the hidden desire to appear caring doesn\u2019t drive billions of dollars of waste in medicine, it just means people also make honest mistakes pursuing conventional goals.Sure, given any goal and any behavior, one can invoke an error theory to explained that behavior as a mistaken attempt to achieve that goal. The problem is that according to the error theory these deviations should be random. Thus theories that can explain the behavior more systematically can get stronger evidential support. Our book tries to offer such systematic theories.Why are so many of these selfish human motivation kept unconscious in the first place, rather than simply being conscious and well hidden? \u2026 The obvious rebuttal here is that we should just have evolved to not have those leaky, difficult-to-suppress emotional responses, or for those responses not to have evolved in the first place.We see a reasonably strong consensus in the literature that it is very hard to design brains to block all possible paths by which conscious motives can leak. We accept that consensus.Laughter does not occur very often in competitive but physically safe games. \u2026 Other observations that don\u2019t really seem to fit with play-signaling: (1) Laughter is used by women to signal their romantic interest in men, and more generally by anyone to signal that they like and approve of someone else. (2) Laughter is mostly restricted to situations in which expectations are violated (a property observed in the literature reviewed by the authors), but there are other times we need to signal play, and instead we use smiling, relaxed body language, etc. (3) Laughter is used to indicate we can distinguish jokes from non-jokes quickly, signaling intelligence.Jokes may be empirically connected to violated expectations, but I don\u2019t think laughter more generally is. I don\u2019t see how the other points here are at odds with laughter as play signal.I think the authors are too eager to interpret everything in terms of hidden motives rather than, e.g., cognitive limitations. \u2026 referees almost never discuss a work\u2019s long-term potential for substantial social benefit. \u2026 But wouldn\u2019t judgment of long-term benefit be highly subjective (and idiosyncratic), whereas technical mastery is relatively objective? \u2026 Ensuring \u201cspit and polish\u201d \u2014 that each individual detail is precise and correct \u2014 strikes me as something that may hinder authors but aids the literature as a whole.Yes, one can make such excuses. But as a long-time academic I\u2019ll say that the theory that our apparent focus on impressiveness is all really a complex clever plan to maximize long term research progress just doesn\u2019t pass the laugh test.Blue jeans, for example, are a symbol of egalitarian values, in part because denim is a cheap, durable, low-maintenance fabric that make wealth and class distinctions harder to detect. So conspicuous consumption signals wealth, but not doing this signals egalitarian values. What would the authors not interpret as signaling? \u2026 I get it, social dynamics are hard and plausible deniability is central to a lot of signaling, so we shouldn\u2019t be surprised that there are many ambiguous layers, counter-signaling, etc. But we should also admit this allows a signaling explanation for most isolated observations, and we should be more modest and careful about our claims.Come on, these aren\u2019t aliens we are talking about. Isn\u2019t it really obvious that overall people pay a lot of attention to how others will interpret their clothing choices? Is there really any question about this?\n\n###\n\n", "completion": " The authors should spend more time drawing this out in each specific example, perhaps by quantifying simplicity, or by proposing novel experiments for which apologists would actually make contrary predictions. \u2026 A few chapters, especially the one discussing religion, were very thin on data. \u2026Count Jess as someone who wanted a longer book.Those are the reviews so far. Maybe soon I\u2019ll give a bigger picture view about the reaction to our book.\n\n@@@\n\n"}
{"prompt": "Date: September 19, 2021 9:20 am\n\n###\n\n", "completion": " Title: Elite Biases Make Policy Biases\n\n@@@\n\n"}
{"prompt": "Date: September 19, 2021 9:20 am \nTitle: Elite Biases Make Policy Biases\n\n###\n\n", "completion": " A 2014 paper predicted U.S. policy changes over four years for 1,779 issues, using the positions of four groups of influencers: business-based interest groups (55), mass-based interest groups (31), median public opinion (6), and elite public opinion (100), i.e. that of people at the 90th percentile of income. (I\u2019ve listed their relative influence in parenthesis. Criticism\u00a0says mid-class (not poor) influence is bigger.) While elite and median public opinion had a 0.78 correlation, the other pairs were uncorrelated. (A poll sets median influencer at 92% income percentile.)What this says is that, even in a democracy, the ~90th percentile rich have the most influence, business interest groups have about half as much, and mass interest groups have about a third as much. We less rich folks only get what we want, to the extent we do, mainly because these elites mostly agree with us, and because we sometimes influence mass interest groups.This median influencer household has income of $210K/yr and wealth of $1.2M, and households above this cut pay 70% of US Federal income taxes. This income is near the median doctor ($207K) and U.S. District Judge ($218K), more than the median full professor ($141K), lawyer ($139), lobbyist ($115K), judge ($109K), and CEO ($103K), and much more than the median federal civil servant ($64K) and high school teacher ($63K). (The median household made $64K, while the median CEO of the top 500 firms made $12.7M.)These elites who set policy get most of their status and income from labor, not capital, and they are quite comfortable with, and in fact love, large bureaucratic organizations. Their highest hopes tend to be of gaining positions in, getting promoted in, or creating, such organizations. When they have dreams for the world, they dream of new versions with higher mandates and bigger budgets. (Think socialism.)\n\n@@@\n\n"}
{"prompt": "Date: September 19, 2021 9:20 am \nTitle: Elite Biases Make Policy Biases\nA 2014 paper predicted U.S. policy changes over four years for 1,779 issues, using the positions of four groups of influencers: business-based interest groups (55), mass-based interest groups (31), median public opinion (6), and elite public opinion (100), i.e. that of people at the 90th percentile of income. (I\u2019ve listed their relative influence in parenthesis. Criticism\u00a0says mid-class (not poor) influence is bigger.) While elite and median public opinion had a 0.78 correlation, the other pairs were uncorrelated. (A poll sets median influencer at 92% income percentile.)What this says is that, even in a democracy, the ~90th percentile rich have the most influence, business interest groups have about half as much, and mass interest groups have about a third as much. We less rich folks only get what we want, to the extent we do, mainly because these elites mostly agree with us, and because we sometimes influence mass interest groups.This median influencer household has income of $210K/yr and wealth of $1.2M, and households above this cut pay 70% of US Federal income taxes. This income is near the median doctor ($207K) and U.S. District Judge ($218K), more than the median full professor ($141K), lawyer ($139), lobbyist ($115K), judge ($109K), and CEO ($103K), and much more than the median federal civil servant ($64K) and high school teacher ($63K). (The median household made $64K, while the median CEO of the top 500 firms made $12.7M.)These elites who set policy get most of their status and income from labor, not capital, and they are quite comfortable with, and in fact love, large bureaucratic organizations. Their highest hopes tend to be of gaining positions in, getting promoted in, or creating, such organizations. When they have dreams for the world, they dream of new versions with higher mandates and bigger budgets. (Think socialism.)\n\n###\n\n", "completion": " They can distinguish each other by their elite accomplishments, school credentials, org affiliations, and styles of talk, dress, etc. And their internal dynamics are dominated by status and gossip. That is, they are very social and join mutually-supporting coalitions which help get them the right jobs, party invites, speaking invites, etc. Via extensive gossip, they quickly form an apparent consensus on the policy issues of the day, on who is higher status among them, and on who should be ostracized and expelled from their ranks. Today these elite communities of gossip and status are integrated across the world.Simple as it is, this account of who most influences policy seems to me promising as the basis of a theory of policy bias. That is, the natural biases of the group who most influences policy may plausibly explain many of our overall policy biases.For example, policy set by elites may give elites too much benefit of the doubt, and defer too much to their status-gossip system. As elites tend to see their internal status-gossip processes as sufficient to discourage malfeasance and encourage excellence, they tend to see little need for other forms of track records, incentives, or accountability within elite professions and organizations, including government agencies. They see themselves as mostly good people, trying to do good things, who should be supported not hassled.As another example, when there are groups that elites see as more outside of themselves, as rivals competing with them for power, then elites may push for policies that control, suppress, and disrespect such rivals.The most obvious candidate for such a rival group is business. Even though these elites are richer than most of us, like most of us they focus more on those who are above them in status, relative to those who are below. Furthermore, the study above says that business is in fact their main rival for influence over policy. And while most business profits go to elites, elites don\u2019t think of themselves as having their main influence on the world via business; elites instead identify more with their roles as org leaders and elite gossipers.Furthermore, while elites see themselves as mostly well-meaning good people, they see business as transparently and dangerously selfish. Elites see businesses as tending to do what makes them more money, even when their leaders are ostracized and not invited to the right parties. Meaning that the usual pressures that work on most elites may not work on business and the super-rich. Thus elites support harsh, intrusive, and punitive business taxes, regulations, and legal liability. Yes when the super-rich are taxed, these elites are also taxed, but that may seem worth the price to take them down a peg or two. Most ordinary people miss this conflict by not distinguishing these two different kinds of \u201crich\u201d.Even though ordinary people seem to have little influence on policy, and mostly agree with elites on policy, elites are still wary of them as individuals.\u00a0After all, we outnumber them at least five to one, we might revolt, and they must rely on us to do most of the things that need doing. So as employees, we must be tracked, assigned, and incentivized. As consumers and investors, we must be regulated. As authors and voters, our thoughts must be shaped and channeled via teachers, censors, media, interest groups, and politicians. As potential criminals we need to be tracked and threatened with punishment. And the poorest of us need even more direct management, such as via social workers and parole officers. All of which not only keeps us under control, but asserts elite status via the fact of their managing such controls.\n\n@@@\n\n"}
{"prompt": "They can distinguish each other by their elite accomplishments, school credentials, org affiliations, and styles of talk, dress, etc. And their internal dynamics are dominated by status and gossip. That is, they are very social and join mutually-supporting coalitions which help get them the right jobs, party invites, speaking invites, etc. Via extensive gossip, they quickly form an apparent consensus on the policy issues of the day, on who is higher status among them, and on who should be ostracized and expelled from their ranks. Today these elite communities of gossip and status are integrated across the world.Simple as it is, this account of who most influences policy seems to me promising as the basis of a theory of policy bias. That is, the natural biases of the group who most influences policy may plausibly explain many of our overall policy biases.For example, policy set by elites may give elites too much benefit of the doubt, and defer too much to their status-gossip system. As elites tend to see their internal status-gossip processes as sufficient to discourage malfeasance and encourage excellence, they tend to see little need for other forms of track records, incentives, or accountability within elite professions and organizations, including government agencies. They see themselves as mostly good people, trying to do good things, who should be supported not hassled.As another example, when there are groups that elites see as more outside of themselves, as rivals competing with them for power, then elites may push for policies that control, suppress, and disrespect such rivals.The most obvious candidate for such a rival group is business. Even though these elites are richer than most of us, like most of us they focus more on those who are above them in status, relative to those who are below. Furthermore, the study above says that business is in fact their main rival for influence over policy. And while most business profits go to elites, elites don\u2019t think of themselves as having their main influence on the world via business; elites instead identify more with their roles as org leaders and elite gossipers.Furthermore, while elites see themselves as mostly well-meaning good people, they see business as transparently and dangerously selfish. Elites see businesses as tending to do what makes them more money, even when their leaders are ostracized and not invited to the right parties. Meaning that the usual pressures that work on most elites may not work on business and the super-rich. Thus elites support harsh, intrusive, and punitive business taxes, regulations, and legal liability. Yes when the super-rich are taxed, these elites are also taxed, but that may seem worth the price to take them down a peg or two. Most ordinary people miss this conflict by not distinguishing these two different kinds of \u201crich\u201d.Even though ordinary people seem to have little influence on policy, and mostly agree with elites on policy, elites are still wary of them as individuals.\u00a0After all, we outnumber them at least five to one, we might revolt, and they must rely on us to do most of the things that need doing. So as employees, we must be tracked, assigned, and incentivized. As consumers and investors, we must be regulated. As authors and voters, our thoughts must be shaped and channeled via teachers, censors, media, interest groups, and politicians. As potential criminals we need to be tracked and threatened with punishment. And the poorest of us need even more direct management, such as via social workers and parole officers. All of which not only keeps us under control, but asserts elite status via the fact of their managing such controls.\n\n###\n\n", "completion": " Mass-based interest groups mostly don\u2019t seem to scare elites as a whole, because usually such groups are dominated by elites at their top levels. It is only when a mass-based group seems to oppose elites as a whole that elites close ranks and warn against the dangers of such \u201cpopulism\u201d. While our society gives a lot of lip service to populism, populism is usually crushed aggressively whenever it actually seems threatening.So how does this theory do empirically? It seems to me that policy does tend to be overly trusting of elites and their status-gossip system, and overly punitive and disrespectful of rival groups. For example, policy pushes us to pick docs, lawyers, and other prestigious professionals based more on the prestige of their affiliations, and less on track records or incentives. Business does seem greatly overly regulated, and taxes seem overly punitive. And policy seems to rely too much on the consensus of elite gossip, relative to more accurate sources like experts or prediction markets.While roughly half of all regulation of individuals seems to be justified as protecting people from themselves, warnings seem just as helpful but would be far less controlling. Free speech (really free hearing) would be as effective at informing as is censorship. Pandemics could be more efficiently handled via law. And the poor could be helped more via simple cash transfers instead of expensive intrusive management of their lives.Our legal system has high costs of suing people (from not using lotteries) but no required liability insurance. This makes law available to elites to sue each other, and to punish business, but not available to ordinary people to sue elites or each other. Elites can protect themselves well from ordinary people via strong prosecutor powers of plea bargaining together with broad surveillance and huge numbers of crime laws on the books, and also judges who are elites and give elites the benefit of the doubt. Oh and living, shopping, and working in separate neighborhoods.And that\u2019s my simple theory of who runs society, and policy biases that naturally result from their rule.\n\n@@@\n\n"}
{"prompt": "Date: November 24, 2010 6:15 pm\n\n###\n\n", "completion": " Title: Elite Fertility Falls\n\n@@@\n\n"}
{"prompt": "Date: November 24, 2010 6:15 pm \nTitle: Elite Fertility Falls\n\n###\n\n", "completion": " An \u201906 essay says falling fertility often afflicted indulged elites:\u201cIf we could survive without a wife, citizens of Rome, all of us would do without that nuisance.\u201d So proclaimed the Roman general, statesman, and censor Quintus Caecilius Metellus Macedonicus, in 131 B.C. Still, he went on to plead, falling birthrates required that Roman men fulfill their duty to reproduce, no matter how irritating Roman women might have become. \u2026Throughout the broad sweep of human history, there are many examples of people, or classes of people, who chose to avoid the costs of parenthood. Indeed, falling fertility is a recurring tendency of human civilization. \u2026Societies with high fertility grew in strength and number and began menacing those with lower fertility. \u2026 That was the lesson King Pyrrhus learned in the third century B.C., when he marched his Greek armies into the Italian peninsula and tried to take on the Romans. \u2026Greece, after falling into a long era of population decline, eventually became a looted colony of Rome. Like today\u2019s modern, well-fed nations, both ancient Greece and Rome eventually found that their elites had lost interest in the often dreary chores of family life. \u201cIn our time all Greece was visited by a dearth of children and a general decay of population,\u201d lamented the Greek historian Polybius around 140 B.C., just as Greece was giving in to Roman domination. \u201cThis evil grew upon us rapidly, and without attracting attention, by our men becoming perverted to a passion for show and money and the pleasures of an idle life.\u201d (more; HT sestamibi)This supports the idea that farmers naturally return to foraging ways as they get rich.\u00a0I wonder how many \u201ccivilization collapses\u201d were due to fertility losing its social status.\n\n@@@\n\n"}
{"prompt": "Date: March 1, 2012 11:05 am\n\n###\n\n", "completion": " Title: Elites Excel At Hypocrisy\n\n@@@\n\n"}
{"prompt": "Date: March 1, 2012 11:05 am \nTitle: Elites Excel At Hypocrisy\n\n###\n\n", "completion": " A few days ago Tyler blogged a study dissing elites:Upper-class individuals were more likely to break the law while driving, relative to lower-class individuals. In follow-up laboratory studies, upper-class individuals were more likely to exhibit unethical decision-making tendencies, take valued goods from others, lie in a negotiation, [and] cheat to increase their chances of winning a prize. (more)While Tyler had doubts, I\u2019d guess this is mostly true. I\u2019m reminded of Freakonomics on \u201cWhat the Bagel Man Saw\u201d:The same people who routinely steal more than percent of his [honor system paid] bagels almost never stoop to stealing his money box. \u2026 Telecom companies have robbed him blind, and \u2026 law firms aren\u2019t worth the trouble. \u2026 Employees further up the corporate ladder cheat more than those down below. He reached this conclusion in part after delivering for years to one company spread out over three floors \u2014 an executive floor on top and two lower floors with sales, service and administrative employees. \u2026 \u201dI had idly assumed that in places where security clearance was required for an individual to have a job, the employees would be more honest than elsewhere. That hasn\u2019t turned out to be true.\u201d (more)I\u2019m also reminded of Charles Murray\u2019s wish that on marriage, hard work, religion, and (caught) crime, elites would more \u201cpreach what they practice.\u201d At least by the usual reading, elites are more moral on these key choices.\n\n@@@\n\n"}
{"prompt": "Date: March 1, 2012 11:05 am \nTitle: Elites Excel At Hypocrisy\nA few days ago Tyler blogged a study dissing elites:Upper-class individuals were more likely to break the law while driving, relative to lower-class individuals. In follow-up laboratory studies, upper-class individuals were more likely to exhibit unethical decision-making tendencies, take valued goods from others, lie in a negotiation, [and] cheat to increase their chances of winning a prize. (more)While Tyler had doubts, I\u2019d guess this is mostly true. I\u2019m reminded of Freakonomics on \u201cWhat the Bagel Man Saw\u201d:The same people who routinely steal more than percent of his [honor system paid] bagels almost never stoop to stealing his money box. \u2026 Telecom companies have robbed him blind, and \u2026 law firms aren\u2019t worth the trouble. \u2026 Employees further up the corporate ladder cheat more than those down below. He reached this conclusion in part after delivering for years to one company spread out over three floors \u2014 an executive floor on top and two lower floors with sales, service and administrative employees. \u2026 \u201dI had idly assumed that in places where security clearance was required for an individual to have a job, the employees would be more honest than elsewhere. That hasn\u2019t turned out to be true.\u201d (more)I\u2019m also reminded of Charles Murray\u2019s wish that on marriage, hard work, religion, and (caught) crime, elites would more \u201cpreach what they practice.\u201d At least by the usual reading, elites are more moral on these key choices.\n\n###\n\n", "completion": " My interpretation: elites excel at hypocrisy. Elites can better distinguish ideals which are mainly given lip service, from ideals that really matter personally. Elites can better see which laws and social norms are actually enforced with strong penalties, and those that can be violated with impunity. This ability comes in part from implicit cultural learning, and also from just raw IQ.  Homo hypocritus is alive and well \u2013 having good enough brains and social connections to manage hypocrisy well is still a core human capacity, as crucial for success in our world as it was for foragers.This theory suggests that weak culture, the parts without strong local teeth, matter more for lower classes. Upper classes give lip service to whatever they are supposed to endorse, and then mostly ignore it to do what helps them personally. It is the lower classes that are more likely to naively do what culture suggests. They are more likely to \u201conly marry for love\u201d or \u201cfollow your bliss\u201d or to think \u201cits all relative anyway.\u201d\n\n@@@\n\n"}
{"prompt": "Date: April 10, 2012 11:25 am\n\n###\n\n", "completion": " Title: Em Econ 101 Talk\n\n@@@\n\n"}
{"prompt": "Date: April 10, 2012 11:25 am \nTitle: Em Econ 101 Talk\n\n###\n\n", "completion": " Here are slides and\u00a0audio from my Friday talk. The abstract again:Em Econ 101 \u2013 My best guess for the next revolution on the scale of the industrial, or farming, or human revolutions, is artificial intelligence in the form of whole brain emulations, or \u201cems.\u201d Many have considered ems from technical and philosophical viewpoints, but I consider em economics. That is, I try to work out in as much social detail as possible a relatively-likely reference scenario set modestly far into a post-em world.Halycon had a very high quality audience \u2013 it was a special pleasure to speak there. The talk was also filmed \u2013 I\u2019ll post that here if/when there is a link.\n\n@@@\n\n"}
{"prompt": "Date: July 17, 2015 9:30 am\n\n###\n\n", "completion": " Title: Em Redistribution\n\n@@@\n\n"}
{"prompt": "Date: July 17, 2015 9:30 am \nTitle: Em Redistribution\n\n###\n\n", "completion": " I\u2019m in the last few weeks of finishing my book The Age of Em:\u00a0Work, Love, and Life When Robots Rule The Earth, about social outcomes in a world dominated by\u00a0brain emulations. As a teaser, let me share some hopefully non-obvious results about redistribution in the em world.There are many kinds of inequality. Inequality exists between different species, between generations born at different times, and between nations of the world at a time. Within a nation at a time, there is inequality both between families and within families. There is also inequality across the moments of the life of each person. In all of these cases, there is not only financial inequality, but also inequality in status, prestige, pleasure, lifespan, happiness, and more. There is also inequality between the size of families, firms, cities, or nations, even when individuals within those groupings are equal.Today, we have relatively little intentional redistribution between generations or between nations. Redistribution within the moments of a person\u2019s life happens, but that is mostly left to that person to choose and to fund. Similarly, redistribution between siblings is mostly achieved via differential treatment by parents. Instead, most concern today about inequality, and most debate about redistribution to address inequality, focuses on one very particular \u201cstandard\u201d kind of inequality.\n\n@@@\n\n"}
{"prompt": "Date: July 17, 2015 9:30 am \nTitle: Em Redistribution\nI\u2019m in the last few weeks of finishing my book The Age of Em:\u00a0Work, Love, and Life When Robots Rule The Earth, about social outcomes in a world dominated by\u00a0brain emulations. As a teaser, let me share some hopefully non-obvious results about redistribution in the em world.There are many kinds of inequality. Inequality exists between different species, between generations born at different times, and between nations of the world at a time. Within a nation at a time, there is inequality both between families and within families. There is also inequality across the moments of the life of each person. In all of these cases, there is not only financial inequality, but also inequality in status, prestige, pleasure, lifespan, happiness, and more. There is also inequality between the size of families, firms, cities, or nations, even when individuals within those groupings are equal.Today, we have relatively little intentional redistribution between generations or between nations. Redistribution within the moments of a person\u2019s life happens, but that is mostly left to that person to choose and to fund. Similarly, redistribution between siblings is mostly achieved via differential treatment by parents. Instead, most concern today about inequality, and most debate about redistribution to address inequality, focuses on one very particular \u201cstandard\u201d kind of inequality.\n\n###\n\n", "completion": " This standard inequality looks at differences in average individual financial incomes between the families of a nation, all at a given time. This type of inequality is actually one of the smallest. For example, in the U.S. today financial inequality between families is only one third the size of that inequality between siblings within families, and even that is much less than the inequality between individuals from different nations. We may focus our redistribution feelings on this standard inequality because it seems to us the most analogous to the inequality that forager sharing norms addressed. Alternatively, perhaps it is the most profitable type of redistribution for opportunistic rent-seekers.This history suggests that the em world will have little redistribution between em generations or city states, and also that each clan is mostly in charge of deciding how to address inequality within that clan. After all, em clan members are more similar and closer to each other than are human siblings, even if they may sometimes be more distant from each other than are typical human life moments. Also, clan members have rather complex relations with each other, making it hard pick a natural sub-clan unit to be the standard basis for counting inequality. So that leaves ems with comparing inequality between clans.A set of em clans can be unequal in two different ways. One way focuses on individual incomes, or perhaps individual happiness or respect, and says that a clan is better off if its individuals are on average better off. The other way focuses on the overall size and success of a clan. Here a clan is better off if it has more members, resources, or respect. Historically, most redistribution efforts have focused on average individual outcomes. For example, we have seen very little efforts to redistribute between human family clans based on family size. That is, we almost never take from families with many descendants in order to give to families that have few descendants. Nor do we take much from big nations, cities, or firms to give to smaller ones.Because most em wages are near subsistence levels, unregulated wages have less inequality than do wages today. So em clans naturally have less inequality of the standard sort that is the focus of today\u2019s redistribution. In contrast, em clans have enormous inequality in clan size, resources, and respect. However, history gives little reason to expect much redistribution to address this inequality. It is not very analogous to forager sharing, nor does it lend itself to profitable rent-seeking.Thus the main kind of redistribution that we have reason to expect in the em era is between the clans of a city, based on differences of average within-clan individual income. But we expect less inequality of this sort in the em world, and so expect less redistribution on this basis.Income taxes are today one of our main mechanisms for reducing the standard inequality that compares individual incomes between families within a nation. Over the last two centuries, big increases in the top marginal tax rates have mostly followed wars where over two percent of the population served in the military. For example, in the U.S. the top marginal tax rate jumped from 15% to 67% in 1917, during World War I. Controlling for this effect, top tax increases have not been correlated with wealth, democracy, or the political ideology of the party running the government. This weakly suggests that the local degree of individual income redistribution between the clans of an em city may depend on the local frequency of large expensive em wars.\n\n@@@\n\n"}
{"prompt": "This standard inequality looks at differences in average individual financial incomes between the families of a nation, all at a given time. This type of inequality is actually one of the smallest. For example, in the U.S. today financial inequality between families is only one third the size of that inequality between siblings within families, and even that is much less than the inequality between individuals from different nations. We may focus our redistribution feelings on this standard inequality because it seems to us the most analogous to the inequality that forager sharing norms addressed. Alternatively, perhaps it is the most profitable type of redistribution for opportunistic rent-seekers.This history suggests that the em world will have little redistribution between em generations or city states, and also that each clan is mostly in charge of deciding how to address inequality within that clan. After all, em clan members are more similar and closer to each other than are human siblings, even if they may sometimes be more distant from each other than are typical human life moments. Also, clan members have rather complex relations with each other, making it hard pick a natural sub-clan unit to be the standard basis for counting inequality. So that leaves ems with comparing inequality between clans.A set of em clans can be unequal in two different ways. One way focuses on individual incomes, or perhaps individual happiness or respect, and says that a clan is better off if its individuals are on average better off. The other way focuses on the overall size and success of a clan. Here a clan is better off if it has more members, resources, or respect. Historically, most redistribution efforts have focused on average individual outcomes. For example, we have seen very little efforts to redistribute between human family clans based on family size. That is, we almost never take from families with many descendants in order to give to families that have few descendants. Nor do we take much from big nations, cities, or firms to give to smaller ones.Because most em wages are near subsistence levels, unregulated wages have less inequality than do wages today. So em clans naturally have less inequality of the standard sort that is the focus of today\u2019s redistribution. In contrast, em clans have enormous inequality in clan size, resources, and respect. However, history gives little reason to expect much redistribution to address this inequality. It is not very analogous to forager sharing, nor does it lend itself to profitable rent-seeking.Thus the main kind of redistribution that we have reason to expect in the em era is between the clans of a city, based on differences of average within-clan individual income. But we expect less inequality of this sort in the em world, and so expect less redistribution on this basis.Income taxes are today one of our main mechanisms for reducing the standard inequality that compares individual incomes between families within a nation. Over the last two centuries, big increases in the top marginal tax rates have mostly followed wars where over two percent of the population served in the military. For example, in the U.S. the top marginal tax rate jumped from 15% to 67% in 1917, during World War I. Controlling for this effect, top tax increases have not been correlated with wealth, democracy, or the political ideology of the party running the government. This weakly suggests that the local degree of individual income redistribution between the clans of an em city may depend on the local frequency of large expensive em wars.\n\n###\n\n", "completion": " If ordinary humans are included straightforwardly in the redistribution systems of the em world, then the simple result to expect is transfers, not only away from richer humans, but also from humans to ems overall. After all, in purely financial terms typical ems are poorer than the poorest humans. Redistribution systems may perhaps correct for the fact that em subsistence levels are much lower than are human subsistence levels. But if so such systems may also encourage or even require recipients of aid to switch from being a human to being an em, in order to lower costs.During the em era, humans typically have industrial era incomes, which are much higher than subsistence level incomes. While many and perhaps most humans may pay to create a few ems, they tend to endow them with much higher than subsistence incomes. In contrast, a small number of successful humans manage to give rise to large em clans, and within these clans most members have near subsistence incomes. Thus transfers based on individual income inequality take from the descendants of less successful humans and give to descendants of more successful humans.\n\n@@@\n\n"}
{"prompt": "Date: October 8, 2014 4:20 pm\n\n###\n\n", "completion": " Title: Em Software Engineering Bleg\n\n@@@\n\n"}
{"prompt": "Date: October 8, 2014 4:20 pm \nTitle: Em Software Engineering Bleg\n\n###\n\n", "completion": " Many software engineers read this blog, and I\u2019d love to include a section on software engineering in my book on ems. But as my software engineering expertise is limited, I ask you, dear software engineer readers, for help.\u201cEms\u201d are future brain emulations. I\u2019m writing a book on em social implications. Ems would substitute for human workers, and once ems were common ems would do almost all work, including software engineering. What I seek are reasonable guesses on\u00a0the tools and patterns of work of em software engineers \u2013 how their tools and work patterns would differ from those today, and how those would vary with time and along some key dimensions.Here are some reasonable premises to work from:\n\n@@@\n\n"}
{"prompt": "Date: October 17, 2014 1:25 pm\n\n###\n\n", "completion": " Title: Em Software Results\n\n@@@\n\n"}
{"prompt": "Date: October 17, 2014 1:25 pm \nTitle: Em Software Results\n\n###\n\n", "completion": " After requesting your help, I should tell you what it added up to. The following\u00a0is an excerpt from my book draft, illustrated by this diagram:\n\n@@@\n\n"}
{"prompt": "Date: August 15, 2011 8:00 am\n\n###\n\n", "completion": " Title: Emotionally, Men Are Far, Women Near\n\n@@@\n\n"}
{"prompt": "Date: August 15, 2011 8:00 am \nTitle: Emotionally, Men Are Far, Women Near\n\n###\n\n", "completion": " Me theorizing two weeks ago:We should expect men to be more self-aware, transparent, and simple regarding their feelings about short-term sexual attractions, while women have more complex, layered, and opaque feelings on this subject. In contrast, women should be more more self-aware, transparent, and simple regarding their feelings about long-term pair-bonding, while men have more complex, layered, and opaque feelings on this subject. By being more opaque on sensitive subjects, we can keep ourselves from giving off clear signals of an inclination to betray. (more)Now add two more assumptions:\n\n@@@\n\n"}
{"prompt": "Date: August 24, 2009 6:00 am\n\n###\n\n", "completion": " Title: Empathy Faces Are For Show\n\n@@@\n\n"}
{"prompt": "Date: August 24, 2009 6:00 am \nTitle: Empathy Faces Are For Show\n\n###\n\n", "completion": " Our subconsciouses are like the rest of us; adeptly \u2018altruistic\u2019 when it benefits them, such as when watched. For an example of how well designed we are in this regard consider the automatic empathic expression of pain we make upon seeing someone hurt. When we aren\u2019t being watched, feeling other people\u2019s pain goes out the window:A 2-part experiment with 50 university students tested the hypothesis that motor mimicry is instead an interpersonal event, a nonverbal communication intended to be seen by the other\u2026.The victim of an apparently painful injury was either increasingly or decreasingly available for eye contact with the observer. Microanalysis showed that the pattern and timing of the observer\u2019s motor mimicry were significantly affected by the visual availability of the victim.That is Katja Grace, who now has a blog worth watching.\n\n@@@\n\n"}
{"prompt": "Date: September 17, 2007 6:00 am\n\n###\n\n", "completion": " Title: Epidemiology Doubts\n\n@@@\n\n"}
{"prompt": "Date: September 17, 2007 6:00 am \nTitle: Epidemiology Doubts\n\n###\n\n", "completion": " Sunday\u2019s New York Times Magazine: \n\n@@@\n\n"}
{"prompt": "Date: October 3, 2008 6:00 am\n\n###\n\n", "completion": " Title: Equally Shallow Genders\n\n@@@\n\n"}
{"prompt": "Date: October 3, 2008 6:00 am \nTitle: Equally Shallow Genders\n\n###\n\n", "completion": "   Women think they are different but they are not.\u00a0 When people about to start speed-dating are asked what they want in a partner, men rate physical attractiveness as far more important than earning prospects, while women rated attractiveness as only a bit more important than earnings.\u00a0 In actual speed-dating choices, however, men and women both rely on looks much more than earnings: \n\n@@@\n\n"}
{"prompt": "Date: June 21, 2007 6:00 am\n\n###\n\n", "completion": " Title: Ethics, Applied Vs. Meta\n\n@@@\n\n"}
{"prompt": "Date: June 21, 2007 6:00 am \nTitle: Ethics, Applied Vs. Meta\n\n###\n\n", "completion": " During my recent visit to Oxford I had occasion to talk to many philosophers who do applied ethics, and who do meta-ethics.\u00a0 They confirmed for me these two facts:\n\n@@@\n\n"}
{"prompt": "Date: September 18, 2010 8:00 am\n\n###\n\n", "completion": " Title: Evasive Erudition\n\n@@@\n\n"}
{"prompt": "Date: September 18, 2010 8:00 am \nTitle: Evasive Erudition\n\n###\n\n", "completion": " Alex lent me the book Status Anxiety by Alain de Botton. Botton exudes erudition, overflowing with fancy words and prestigious literary examples.  But he also illustrates a common problem with such erudition: Botton hardly has any analysis.This at least makes Botton easy to summarize.  First, he says it can be very stressful to worry about status.  Second, he says the situation is worse today because before folks weren\u2019t so overtly compared to people close to them, while today most folks work in large heavily-ranked organizations.  When anyone can grow up to be President, the fact that you didn\u2019t can make you feel worse.Third and finally, Bottom takes great comfort from the fact we have several competing status hierarchies, some of which \u201cquestion\u201d others.  Instead of trying to be rich, you can instead try to be a great artist, comedian, saint, or bohemian:Standing witness to hidden lives, novels may act as conceptual counterweights to dominant hierarchical realities. They can reveal that the maid now busying herself with lunch is a creatures of rare sensitivity and moral greatness, while the baron who laughs raucously and owns a silver mind has a heart both withered and acrid. \u2026A mature solution to status anxiety may be said to begin with the recognition that status is available from, and awarded by, a variety of different audiences \u2013 industrialists, bohemians, families, philosophers \u2013 and that our choice among them may be free and willed. However unpleasant anxiety over status must be, it is difficult to image a good life entirely free of them, for  the fear of failing and disgracing oneself in the eyes of others is an inevitable consequences of harboring ambitions. \u2026 Status anxiety may be defined as problematic only insofar as it is inspired by values that we uphold because we are terrified and preternaturally obedient, \u2026 because we have grown too imaginably timid to conceive of alternatives.\n\n@@@\n\n"}
{"prompt": "Date: September 18, 2010 8:00 am \nTitle: Evasive Erudition\nAlex lent me the book Status Anxiety by Alain de Botton. Botton exudes erudition, overflowing with fancy words and prestigious literary examples.  But he also illustrates a common problem with such erudition: Botton hardly has any analysis.This at least makes Botton easy to summarize.  First, he says it can be very stressful to worry about status.  Second, he says the situation is worse today because before folks weren\u2019t so overtly compared to people close to them, while today most folks work in large heavily-ranked organizations.  When anyone can grow up to be President, the fact that you didn\u2019t can make you feel worse.Third and finally, Bottom takes great comfort from the fact we have several competing status hierarchies, some of which \u201cquestion\u201d others.  Instead of trying to be rich, you can instead try to be a great artist, comedian, saint, or bohemian:Standing witness to hidden lives, novels may act as conceptual counterweights to dominant hierarchical realities. They can reveal that the maid now busying herself with lunch is a creatures of rare sensitivity and moral greatness, while the baron who laughs raucously and owns a silver mind has a heart both withered and acrid. \u2026A mature solution to status anxiety may be said to begin with the recognition that status is available from, and awarded by, a variety of different audiences \u2013 industrialists, bohemians, families, philosophers \u2013 and that our choice among them may be free and willed. However unpleasant anxiety over status must be, it is difficult to image a good life entirely free of them, for  the fear of failing and disgracing oneself in the eyes of others is an inevitable consequences of harboring ambitions. \u2026 Status anxiety may be defined as problematic only insofar as it is inspired by values that we uphold because we are terrified and preternaturally obedient, \u2026 because we have grown too imaginably timid to conceive of alternatives.\n\n###\n\n", "completion": " Philosophy, art, politics, religion, and bohemia \u2026 institute new kinds of hierarchies based on sets of values unrecognized by, and critical of, those of the majority. \u2026 They have helped to lend legitimacy to those who, in every generation, may be unable to unwilling to comply dutifully with the dominant notions of high status.But what exactly is the advantage of being in the top 4% for one of five key rankings, instead of the top 20% for a single common ranking. \u00a0Botton doesn\u2019t even consider this question. \u00a0Tyler suggests we prefer to fool ourselves by overemphasizing the importance of the rankings where we excel.  But why is this better than just fooling yourself about your common ranking, or how much ranking matters?I suspect what is really going on here is that Botton was anxious when he rated only moderately well on the \u201cmajority\u201d ranking, but was then relieved to see he ranked fantastically high on certain \u201cnon-majority\u201d rankings.  \u201cWhew,\u201d said Botton, \u201cThis makes my implicit overall ranking much better.\u201d \u00a0Alas such comfort isn\u2019t available to most folk.\n\n@@@\n\n"}
{"prompt": "Date: May 25, 2012 2:35 pm\n\n###\n\n", "completion": " Title: Experts Agree\n\n@@@\n\n"}
{"prompt": "Date: May 25, 2012 2:35 pm \nTitle: Experts Agree\n\n###\n\n", "completion": " Mental health diagnoses are evaluated in part by the consistency with which professionals assign diagnoses. Turns out, there is often a low correlation between the diagnoses different folks assign to a patient:The DSM-5 revision has been intensely controversial, with critics \u2026 charging that poorly drafted changes would lead to millions more people being given unnecessary and risky drugs.  The field trials used a statistic called kappa. This measures the consensus between different doctors assessing the same patient, with 1 corresponding to perfect diagnostic agreement, and 0 meaning concordance could just be due to chance. In January, leaders of the DSM-5 revision announced that kappas as low as 0.2 should be considered \u201cacceptable\u201d.\u201cMost researchers agree that 0.2 to 0.4 is really not in the acceptable range,\u201d says Dayle Jones of the University of Central Florida in Orlando, who is tracking DSM-5 for the American Counseling Association.One proposed diagnosis failed to reach even this standard. Some patients turning up in doctors\u2019 offices are both depressed and anxious, so mixed anxiety/depression was tested as a new category: the kappa for adults was less than 0.01.Attenuated psychosis syndrome, meanwhile, was intended to catch young people in the early stages of schizophrenia and other psychotic disorders. While field trials gave a kappa of 0.46, the variability was so large that Darrel Regier, APA\u2019s head of research, told the meeting that the result was \u201cuninterpretable\u201d. Both disorders are now headed for DSM-5\u2019s appendix \u2026The low kappas recorded for major depressive disorder and generalised anxiety disorder \u2013 0.32 and 0.2 respectively in the adult trials \u2013 raise serious questions. (more)\n\n@@@\n\n"}
{"prompt": "Date: May 25, 2012 2:35 pm \nTitle: Experts Agree\nMental health diagnoses are evaluated in part by the consistency with which professionals assign diagnoses. Turns out, there is often a low correlation between the diagnoses different folks assign to a patient:The DSM-5 revision has been intensely controversial, with critics \u2026 charging that poorly drafted changes would lead to millions more people being given unnecessary and risky drugs.  The field trials used a statistic called kappa. This measures the consensus between different doctors assessing the same patient, with 1 corresponding to perfect diagnostic agreement, and 0 meaning concordance could just be due to chance. In January, leaders of the DSM-5 revision announced that kappas as low as 0.2 should be considered \u201cacceptable\u201d.\u201cMost researchers agree that 0.2 to 0.4 is really not in the acceptable range,\u201d says Dayle Jones of the University of Central Florida in Orlando, who is tracking DSM-5 for the American Counseling Association.One proposed diagnosis failed to reach even this standard. Some patients turning up in doctors\u2019 offices are both depressed and anxious, so mixed anxiety/depression was tested as a new category: the kappa for adults was less than 0.01.Attenuated psychosis syndrome, meanwhile, was intended to catch young people in the early stages of schizophrenia and other psychotic disorders. While field trials gave a kappa of 0.46, the variability was so large that Darrel Regier, APA\u2019s head of research, told the meeting that the result was \u201cuninterpretable\u201d. Both disorders are now headed for DSM-5\u2019s appendix \u2026The low kappas recorded for major depressive disorder and generalised anxiety disorder \u2013 0.32 and 0.2 respectively in the adult trials \u2013 raise serious questions. (more)\n\n###\n\n", "completion": " Similarly low levels of agreement are found in academic peer review \u2013 referees judging papers submitted to journals, for example, rarely agree on whether the paper should be accepted. Yet, not only are academics and mental health professionals still considered experts, expert agreement remains one of the main ways the public uses to judge who is an expert.In the public eye, experts on X are people who tend to agree when outsiders ask them questions about X, such as the meaning of special words or phrases about X, or who is an expert on X. \u00a0After all, this is pretty much the only concrete data they have to go on. It helps if these experts also do some things that outsiders see as impressive, but this usually isn\u2019t necessary to be considered an expert.I have two observations:\n\n@@@\n\n"}
{"prompt": "Date: December 20, 2008 9:30 am\n\n###\n\n", "completion": " Title: Experts Are For Certainty\n\n@@@\n\n"}
{"prompt": "Date: December 20, 2008 9:30 am \nTitle: Experts Are For Certainty\n\n###\n\n", "completion": " Chris Dillow: It's a bad day for experts. The Times complains that economic forecasters are as blind as ancient soothsayers, whilst proof that Colin Stagg was innocent discredits Paul Britton's expertise as a forensic pyschologist.\u00a0 To point out that experts are wrong, however, is to misunderstand the purpose of them. Their function is not to provide knowledge, and still less clear thinking. Instead, it is to provide certainty. People hate dissonance, doubt and uncertainty. Experts help dispel these. \n\n@@@\n\n"}
{"prompt": "Date: February 4, 2021 11:00 am\n\n###\n\n", "completion": " Title: Experts Versus Elites\n\n@@@\n\n"}
{"prompt": "Date: February 4, 2021 11:00 am \nTitle: Experts Versus Elites\n\n###\n\n", "completion": " Consider a typical firm or other small organization, run via a typical management hierarchy. At the bottom are specialists, who do very particular tasks. At the top are generalists, who supposedly consider it all in the context of a bigger picture. In the middle are people who specialize to some degree, but who also are supposed to consider somewhat bigger pictures.On any particular issue, people at the bottom can usually claim the most expertise; they know their job best. And when someone at the top has to make a difficult decision, they usually prefer to justify it via reference to recommendations from below. They are just following the advice of their experts, they say. But of course they lie; people at the top often overrule subordinates. And while leaders often like to pretend that they select people for promotion on the basis of doing lower jobs well, that is also often a lie.Our larger society has a similar structure. We have elites who are far more influential than most of us about what happens in our society. As we saw early in the pandemic, the elites are always visibly chattering among themselves about the topics of the day, and when they form a new opinion, the experts usually quickly cave to agree with them, and try to pretend they agreed all along.As a book I recently reviewed explains in great detail, elites are selected primarily for their prestige and status, which has many contributions, including money, looks, fame, charm, wit, positions of power, etc. Elites like to pretend they were selected for being experts at something, and they like to pretend their opinions are just reflecting what experts have said (\u201cwe believe the science!\u201d). But they often lie; elite opinion often overrules expert opinion, especially on topics with strong moral colors. And elites are selected far more for prestige than expertise.\n\n@@@\n\n"}
{"prompt": "Date: February 4, 2021 11:00 am \nTitle: Experts Versus Elites\nConsider a typical firm or other small organization, run via a typical management hierarchy. At the bottom are specialists, who do very particular tasks. At the top are generalists, who supposedly consider it all in the context of a bigger picture. In the middle are people who specialize to some degree, but who also are supposed to consider somewhat bigger pictures.On any particular issue, people at the bottom can usually claim the most expertise; they know their job best. And when someone at the top has to make a difficult decision, they usually prefer to justify it via reference to recommendations from below. They are just following the advice of their experts, they say. But of course they lie; people at the top often overrule subordinates. And while leaders often like to pretend that they select people for promotion on the basis of doing lower jobs well, that is also often a lie.Our larger society has a similar structure. We have elites who are far more influential than most of us about what happens in our society. As we saw early in the pandemic, the elites are always visibly chattering among themselves about the topics of the day, and when they form a new opinion, the experts usually quickly cave to agree with them, and try to pretend they agreed all along.As a book I recently reviewed explains in great detail, elites are selected primarily for their prestige and status, which has many contributions, including money, looks, fame, charm, wit, positions of power, etc. Elites like to pretend they were selected for being experts at something, and they like to pretend their opinions are just reflecting what experts have said (\u201cwe believe the science!\u201d). But they often lie; elite opinion often overrules expert opinion, especially on topics with strong moral colors. And elites are selected far more for prestige than expertise.\n\n###\n\n", "completion": " When an academic wins a Nobel prize, they have achieved a pinnacle of expertise. At which point they often start to wax philosophic, and writing op-eds. They seem to be making a bid to become an elite. Because we all respect and want to associate with elites far more than with experts. Elites far less often lust after becoming experts, because we are often willing to treat elites as if they are experts. For example, when a journalist writes a popular book on science, they are often willing to field science questions when they give a talk on their book. And the rest of us are far more interested in hearing them talk on the subject than the scientists they write about.Consider talks versus panels at conferences. A talk tends to be done in expert mode, wherein the speaker sticks to topics on which they have acquired expert knowledge. But then on panels, the same people talk freely on most any topic that comes up, even topics where they have little expertise. You might think that audiences would be less interested in hearing such inexpert speculation, but in fact they seem to eat it up. My interpretation: on panels, people pose as elites, and talk in elite mode. Like they might do at a cocktail party. And audiences eagerly gather around panelists, just like they would gather around prestigious folks arguing at a cocktail party about topics on which they have little expertise.Consider news articles versus columnists. The news articles are written by news experts, in full expert mode. They are clearly more accurate on average than are columns. But columns writers take on an elite mode, where they pontificate on all issues of the day, regardless of how much they know. And readers love that.Consider boards of directors versus boards of advisors. Advisors are nominally experts, while directors are nominally elites. Directors are far more powerful, are lobbied far more strongly, and are paid a lot more too. Boards of advisors are usually not asked for advise, they are mainly there to add prestige to an organization. But prestige via their expertise, rather than their general eliteness.Even inside academic worlds, we usually pretend to pick leaders like journal editors, funding program managers, department chairs, etc. based mainly on their expert credentials. But they also lie; raw prestige counts for a lot more than they like to admit.Finally, consider that recently I went into clear expert mode to release a formal preprint on grabby aliens, which induced almost no (< 10) comments on this blog or Twitter, in contrast to far more comments when arguable-elites discuss it in panelist/elite mode: Scott Aaronson (205), Scott Alexander (108), and Hacker News (110). People are far more interested in talking with elites in elite mode on most topics, than in talking with the clear relevant experts in expert mode.All of which suggests that my efforts to replace choice via elite association with prediction markets and paying for results face even larger uphill battles than I\u2019ve anticipated.Added noon: This also helps explain why artists are said to \u201ccontribute to important conversations\u201d by making documentaries, etc. that express \u201cemotional truths.\u201d They present themselves as qualifying elites by virtue of their superior art abilities.See also: More on Experts Vs. Elites\n\n@@@\n\n"}