Mobile Suit Gundam: Char's Counterattack is the first full-length Gundam animated movie released in 1988. Char's Counterattack is the culmination of the original saga begun in Mobile Suit Gundam and continued through Mobile Suit Zeta Gundam and Mobile Suit Gundam ZZ, marking the final conflict of the fourteen-year rivalry between Amuro Ray and Char Aznable, and the end of the Earth Federation/Zeon conflicts.
...The movie is noteworthy for having a rather unusual genesis. Originally, director Yoshiyuki Tomino was going to wrap up Amuro and Char's storyline in Gundam ZZ, but mid-way through production he was given the go-ahead to make a movie, forcing the plot of ZZ to be rewritten (details on its trope page). In the meantime Tomino wrote the novel Hi-Streamer, but when Sunrise gave him the green light, he went back and wrote a second novel, Beltorchika's Children, which he specifically wrote to be adapted into a movie. However, Sunrise instead chose to use Hi-Streamer, with the final film being a pretty straightforward adaptation of its second half. These two novels serve as the origin of the Hi-Nu Gundam (the finalized, \"perfect\" Nu Gundam) and Nightingale (a bigger, beefier Sazabi), which pop up in video games like Super Robot Wars, SD Gundam G Generation, and Gundam Vs Series.")
),
("https://www.animenewsnetwork.com/news/2007-02-20/hideaki-anno-releases-statement-about-new-evangelion-movies",
("Hideaki Anno Releases Statement About New Evangelion Movies"
, "2007-02-20"
, "Hideaki Anno"
, ""
, "Many different desires are motivating us to create the new \"Evangelion\" film.
The desire to portray my sincere feelings on film.
The desire to share, with an audience, the embodiment of image, the diversity of expressions, and the detailed portrayal of emotions that animation offers.
The desire to connect today's exhausted Japanese animation [industry] to the future.
The desire to fight the continuing trend of stagnation in anime.
The desire to support the strength of heart that exists in the world.
Finally, the desire to have these wishes be realized.
For these purposes, we used the best methods available to us to make another Evangelion film.
Many times we wondered, \"It's a title that's more than 10 years old. Why now?\"
\"Eva is too old\", we felt.
However, over the past 12 years, there has been no anime newer than Eva.
... As the creator of this project, [I assure you that] a very new-feeling Evangelion world has beeen constructed.
... Although it seems obvious, we aim to create a form of entertainment that anyone can look forward to; one that people who have never seen Evangelion can easily adjust to, one that can engage audiences as a movie for theatres, and one that produces a new understanding of the world.")
),
("https://www.khara.co.jp/2019/08/01/01/",
("『シン・ウルトラマン』映画化に関するお知らせ"
, "Studio Khara"
, "2019-08-01"
, ""
, "A new film production of \"SHIN ULTRAMAN\" was publicly announced today. The new movie will come to theaters in 2021.
Hideaki Anno will join a film team, Higuchi-Gumi led by Director Shinji Higuchi, taking charge of Produce and Screenplay. First draft script has been finished in February 5th, 2019. Anno will fully join the project after finishing his \"EVANGELION:3.0+1.0\" film.")
),
("https://www.amazon.com/Secret-History-Star-Wars/dp/0978465237",
("The Secret History of Star Wars"
, "Michael Kaminski"
, "2008-11-18"
, ""
, "Star Wars is one of the most important cultural phenomena of the Western world. The tale of Luke Skywalker, Han Solo, and the fall and redemption of Anakin Skywalker has become modern myth, an epic tragedy of the corruption of a young man in love into darkness, the rise of evil, and the power of good triumphing in the end. But it didn't start out that way. In this thorough account of one of cinema's most lasting works, Michael Kaminski presents the true history of how Star Wars was written, from its beginnings as a science fiction fairy tale to its development over three decades into the epic we now know, chronicling the methods, techniques, thought processes, and struggles of its creator. For this unauthorized account, he has pored through over four hundred sources, from interviews to original scripts, to track how the most powerful modern epic in the world was created, expanded, and finalized into the tale an entire generation has grown up with. [ISBN: 0978465237]"
)
),
("https://scholars-stage.blogspot.com/2010/08/notes-on-dynamics-of-human-civilization.html",
("Notes on the Dynamics of Human Civilization: The Growth Revolution"
, "Tanner Greer"
, "2018-08-04"
, ""
, "My interest lies in the dynamics of civilized societies: their material needs and limitations, the recurring patterns of geography, social organization, and cultural complexity upon which they are built, and the type of interactions that define their relationships with each other and the physical systems they depend on for survival—or in simpler words, the means by which human communities flourish and fall.
...Human civilization has gone through two stages. The first of these stages is the longest, beginning with the emergence of complex societies in the Near East c. 11,500 years ago and ending only at the beginning of the 19th century. I submit that every society of this period—from the first chiefdoms to the great empires of Rome and China—operated under the same basic structural constraints. The rules and limitations were the same; the differences were a matter of emphasis and scale. This changes at the turn of the 19th century. Humanity's third great period begins here (it has not yet ended). The rules by which the modern world operates are incredibly different from those of the old order. The transformation wrought by modernization was no less revolutionary than that wrought by the advent of complex society 11,000 years previous.
This revolution is widely recognized, but also grossly mischaracterized. The standard label for this transition is the \"Industrial Revolution\". This title is misleading. The industrialization of the world economy was the result, not the cause of modernization. The nature of this radical transformation is captured better by a different title: The Growth Revolution. Population, wealth, and energy production/consumption are three quantitative variables that can be estimated with some accuracy through much of human history. When displayed on a broad scale like this, a striking trend is seen in all three data sets: by 1820 all three begin an exponential climb upwards. This is the \"Growth Revolution.\" During this revolution human energy production and consumption, population size, wealth, technological capacity, and knowledge all began to increase at an exponential rate. This constant expansion of human resources is the defining feature of our time. Ours is an exponential age.
...500 years of growth on the part of the wealthiest static societies of the old order is equal to less than 7% of a single year's growth on the part of their modern equivalent!
...Many of the world's fallen civilizations met their doom by trying to exceed the inherit limits of static civilization.")
),
("https://scholars-stage.blogspot.com/2018/01/vengeance-as-justice-passages-i.html",
("Vengeance As Justice: Passages I Highlighted in My Copy of Eye for an Eye"
, "Tanner Greer"
, "2018-01-26"
, ""
, "These type of questions naturally lead to the topic of this book: lex talionis, the law of the talion, the principle of an eye for an eye, of justice through vengeance, retaliation sanctioned by culture and law. This understanding of justice is what propels the Icelandic sagas. But it wasn't just a Viking tick. \"Eye for an eye\" was standard practice just about everywhere a few thousand years ago, from the shores of Germainia and the fields of the Greek polis to the warring tribes of Canaan and the even more distant lands of the Kurus and the Zhou. We view this understanding of justice as backward and crude. We say things like \"an eye for an eye makes the whole world blind.\" Miller aims to convince us otherwise. We have a lot to learn from these talionic cultures, he argues, and our world could be made a more just place if we could humble ourselves enough to learn from them.I am not going to provide a precis of Miller's argument here. Like past editions of 'Passages I Highlighted' (see here) I will reserve myself to quoting the passages of this book I found most interesting. But to really give you a sense for Miller's argument, I think the best thing I can do is quote first from another one of his books, one that focuses specifically on Icelandic society. He begins that book by quoting a passage from an obscure saga. In only a paragraph, the saga lays out what lex talionis looked like in real life:
Some Norwegian merchants chopped off Skæring's hand. Gudmund was given self-judgment in the injury case. Haf Brandsson [Gudmund's second cousin] and Gudmund together adjudged compensation in the amount of thirty hundreds, which was to be paid over immediately. Gudmund then rode away from the ship. But the Norwegians confronted Haf, who had remained behind; they thought the judgment had been too steep and they asked him to do one of two things: either reduce the award or swear an oath. Haf refused to do either.
Some people rode after Gudmund and told him what had happened. He turned back immediately and asked Haf what was going on. Haf told him where matters stood. Gudmund said, \"Swear the oath, Haf, or else I will do it, but then they will have to pay sixty hundreds. The oath of either one of us will have the same price as Skæring's hand.\"
The Norwegians refused the offer. \"Then I shall make you another proposal,\" said Gudmund. \"I will pay Skæring the thirty hundreds that you were judged to pay, but I shall choose one man from amongst you who seems to me of equivalent standing with Skæring and chop off his hand. You may then compensate that man's hand as cheaply as you wish.\"
This did not appeal to the Norwegians and they decided to pay the original award immediately. Gudmund took Skæring with him when they left the ship. (G.dýri 26:212) [1]
Iceland was a country without a state. They had laws but no government to enforce them. If you were wronged, the responsibility to right the wrong rested with you and your kin. To prevent retaliatory feuds the Icelanders would often give the wronged party a chance to stand in judgement and mete out a punishment to pay for their mistakes and restore balance between the two groups. The saga passage you've just read is an excellent example of how the system worked. Miller's comments on it are worth pondering:
By the time the saga writer focuses attention on this incident it is not the hand that is the subject of the dispute but the legitimacy and justice of Gudmund's judgment. The Norwegians think the award excessive, and not without reason. More than a few men's lives at this time were compensated for with thirty hundreds or less. Gudmund, however, is able to justify astutely his over-reaching by giving these men of the market a lesson on the contingency of value and values. To the Norwegians the award should reflect the price of a middling Icelandic hand. Gudmund forces them to conceive of the award in a different way: it is not the price of buying Skæring's hand, but the price of preserving a Norwegian hand. By introducing the prospect of one of their hands to balance against Skæring's, he is able to remind the Norwegians that the thirty hundreds they must pay purchases more than Skæring's hand; it also buys off vengeance in kind. He is also able to force them to take into account the costs of personalizing the injury. Most people, he bets, are willing to pay more to save their own hands than they would be willing to pay to take someone else's. The justice of Gudmund's award thus depends on a redefinition of its significance. Rather than buying Skæring's hand, the Norwegians are preserving their own, and the price, they now feel, is well worth paying. Fellow feeling thus comes not in the form of imagining Skæring's anguish and pain as Skæring's, but in imagining the pain as their own. [2]
This is the logic of lex talionis. This is why \"an eye for an eye\" did not in fact make the whole world go blind. The principle of an eye for an eye, as Miller sees it, is \"the more ancient and deeper notion that justice is a matter of restoring balance, achieving equity, determining equivalence, making reparations... getting back to zero, to even.\" [3] Trading eyes for eyes is not so much about indiscriminate, unthinking violence as it is carefully calculated attempts to match punishment to crime. Talionic justice is a system built on deterrence—not only deterring criminals from committing crimes, but deterring vengeance seekers from exacting too heavy a price in retaliation for crimes committed against them.")
),
("https://scholars-stage.blogspot.com/2018/08/tradition-is-smarter-than-you-are.html",
("Tradition is Smarter Than You Are"
, "Tanner Greer"
, "2018-08-27"
, ""
, "Let's talk about Henrich first. One of the clearest presentations of his ideas is in his 2016 book The Secret of Our Success. The book is less a heavy scholarly tome than a poppified version of Henrich's research, but Henrich's decision to trade theoretical detail for accessibility is understandable (it is also why I don't feel bad quoting large blocks of text from the book in this post). Henrich advances the argument that brain-power alone is not enough to explain why humans are such a successful species. Humans, he argues, are not nearly as intelligent as we think they are. Remove them from the culture and environment they have learned to operate in and they fail quickly. His favorite example of this are European explorers who die in the middle of deserts, jungles, or arctic wastes even though thousands of generations of hunter-gatherers were able to survive and thrive in these same environments. If human success was due to our ability to problem solve, analyze, and rationally develop novel solutions to novel challenges, the explorers should have been fine. Their ghastly fates suggest that rationality may not be the key to human survival...Henrich has dozens of these examples. The common thread pulling them together is that the people whose survival is guaranteed by strict observance of these traditions have no real explanation for why they are following them. Henrich goes into this with more depth in discussion of his ethnographic work in Fiji, where women do not eat certain fish while pregnant.
... Henrich makes two arguments here, both relevant to contemporary debates in politics and philosophy. The first is that customs, traditions, and the like are subject to Darwinian selection. Henrich is not always clear on exactly what is being selected for—is it individuals who follow a tradition, groups whose members all follow the tradition, or the tradition itself?—but the general gist is that traditions stick around longest when they are adaptive. This process is \"blind.\" Those who follow the traditions do not know how they work, and in some cases (like religious rituals that build social solidarity) knowing the details of how they work might actually reduce the efficacy of the tradition. That is the second argument of note: we do not (and often cannot) understand just how the traditions we inherit help our survival, and because of that, it is difficult to artificially create replacements.
...Can any of this be put into action? I suspect many conservatives will think the answer to this question is obvious. Henrich and Scott have provided empirical support for maintaining \"Chesterton's fence.\" Chesterton asks us not destroy customs, tradition, and social structures that we cannot explain. Henrich and Scott question our ability to rationally explain them. Implicit in this is a strong defense of the local, the traditional, and the unchanging. The trouble with our world is that it is changing. Henrich focuses on small scale societies. These societies are not static. The changes they undergo are often drastic. But the distance between the life-style of a forager today and that of her ancestors five hundred years ago pales next to the gap that yawns between the average city-slicker and her ancestors five centuries past...Europeans, Japanese, Taiwanese, and South Koreans born today look forward to spending their teenage years in stage five societies. What traditions could their grandparents give them that might prepare them for this new world? By the time any new tradition might arise, the conditions that made it adaptive have already changed. This may be why the rationalist impulse wrests so strong a hold on the modern mind. The traditions are gone; custom is dying. In the search for happiness, rationalism is the only tool we have left.")
),
("https://scholars-stage.blogspot.com/2015/05/the-war-where-future-met-past.html",
("When Modern War Met an Antique Art"
, "Tanner Greer"
, "2015-05-08"
, ""
, "We associate ukiyo-e prints with traditional Japanese landscapes or pastoral settings, episodes from Japanese myths or historical epics, and scenes of courtesan life in Edo. It can be a bit bewildering when we see the same art style and production methods used to produce more modern images. This should not be too much of a surprise, however: the most famous of the great Japanese woodblock artists died only a few decades before Commodore Perry brought his black boats to Edo bay. Much of their era would disappear in the miraculous changes of the Meiji revolution, but as the prints included here show quite clearly, much of the old order lived on into the 20th century.
These prints all depict episodes from the Sino-Japanese War of 1894 or the Russo-Japanese War that was waged a decade later. Remarkably, none of these prints were designed to be great works of art; the great majority were carved and colored to accompany news reports from the front-lines, printed in newspapers or periodicals circulating in Japan on short notice. The artists never saw the battlefields they depicted, relying instead on common visual tropes, reporter's accounts (you can see a gaggle of such reporters in the bottom right corner of the print placed directly below), and their own imaginations to create these images. The prints are therefore less useful for understanding the tactics or battlefield conditions of these wars than they are for understanding the attitude of a Japanese public mobilized for external conquest for the first time in centuries.
As historical sources the prints are revealing. A comparison of the physical features of the Japanese and Chinese soldiers depicted testifies to how thoroughly the Japanese people had adopted the racialist ideology common in European circles at the time. The prints, like the wars themselves, also betray how eager the Japanese were to prove that they were the equals of the Western powers. Perhaps most interesting, however, is how exultantly they depict the wars of their day. Tactically, the Russo-Japanese War was not far removed from the Great War that soon followed it, but the way the Japanese portrayed their experience with industrial warfare could not be further removed from the collective horror Europeans felt when they fought in the trenches. These woodblock prints were some of the first artistic renderings of industrial age warfare; never again would a people forced to wage such a war render it so beautifully.
Copied below are the war prints I found most useful as historical windows or most visually arresting as works of art...")
),
("https://scholars-stage.blogspot.com/2014/12/isis-mongols-and-return-of-ancient.html",
("ISIS, the Mongols, and 'The Return of Ancient Challenges'"
, "Tanner Greer"
, "2014-12-18"
, ""
, "The most interesting parallel between ISIS and the forces of Chhingis Khan is actually not one Anderson makes explicitly. He sets up this comparison in his discussion of the ISIS command structure:
Use Mission Orders to Enhance Operational Security. Telling subordinates what to do, not how to do it, is a basic tenant of maneuver warfare; but it also allows Baghdadi to command and control his forces with an absolute minimum of cell phone and radio communications that are subject to American intercepts which can be provided to Iraqi security forces. Baghdadi makes extensive use of runners and motorcycle messengers to keep his opponents in the dark.
American commanders talk a good game about Maneuver Warfare, but many take advantage of technology and secure communications to micromanage. It is not unusual for an American Colonel to be tracking squad sized units on his computer; worse still, it is not unusual to require American squad and platoon sized units to submit detailed patrol plans three days in advance so they can be plotted into computers. Baghdadi can simply say; \"take this town and let me know when you have it\". It doesn't make him a good guy, but he is a very effective military leader. Contrast this with Maliki and Karzai who will move or fire a commander who appears so competent or popular that he might become a competitor for power (emphasis added) [9].
And here is where things get interesting. I don't think it is possible to isolate one, single variable that can account for the epochal success of the Mongol military machine. But if I was forced to try and boil down the secret of the Mongol Empire to a sentence or two it would sound a lot like the one Anderson has written here. In contrast to both the kingdoms the Mongols destroyed and every other nomadic confederation that preceded or followed his empire, Chinggis Khan possessed the complete loyalty of his troops and his generals. The men under his command were absolutely, and to their enemies, terrifyingly, united. Chinggis Khan could wage simultaneous wars on opposite sides of the known world, erode the internal cohesion of every kingdom his envoys visited, and paralyze enemy defenses with a flood of independently commanded units only because of the fearsome unity and loyalty of his forces.
While none of the Mongol's other foes imploded so spectacularly, sowing dissension and division within the ranks of their enemies was an essential element of all Mongol campaigns. Whether they were fighting Hungarian monarchs on Pannonian plains or Song Dynasty navies on the Yangtze, the Mongols were masters at turning their enemies against each other. The same could not be said about the Mongol's rivals. No one ever managed to turn a Mongol. For the first three generation of the empire there were no secession crises, no infighting, and few traitors. Powerful commanders deferred to their leaders, even when, as Juvainyi hints, doing so meant to demotion or punishment. [11] This is really quite extraordinary when you consider the kind of positions these commanders were placed in. Consider the case of Muqali, one of the greatest but least known of the Mongol generals. While Chinggis was off fighting the Khawarezm Empire and other enemies in the West, Muqali was placed in charge of the war effort in Northern China. For six years he controlled all of Mongolia, Manchuria, and the North China plain and for six years he fought the Jin Empire without losing a single battle. He was a powerful and popular commander. But neither he nor his sons ever challenged the great Khan's authority. There is no evidence that Chhingis ever feared that they would. [12]
... The story of how Chinggis Khan created an empire whose many branches were unified in effort and whose many subjects were absolutely loyal to him is one of the most fascinating in world history. Unfortunately, it is only tangentially related to the topic at hand. A full investigation of that question must be reserved for a later post. For the purposes of this discussion what matters is that the conquests of the Mongol empire, the type of warfare it waged, and the methods it used to incorporate new peoples into its domains would not have been possible except for the unshakable unity of its commanders and warriors. In this the Mongols are very much like Abu Bakr al-Baghdadi and the warriors under his command.")
),
("https://scholars-stage.blogspot.com/2014/06/the-cross-section-ilusion.html",
("The Cross Section Illusion"
, "Tanner Greer"
, "2014-06-07"
, ""
, "If you are concerned with American obesity rates and turn to the cross sectional data to try and figure out what is going on, it is easy to reach a flawed conclusion. The correlation between education and obesity, for example, seems quite clear. The poorer and less educated an American is, the more likely he or she is to be obese. Looking at this data it seems reasonable to suggest that something about poverty is making people more obese—perhaps cruddy processed food is the only thing America's poor and less educated can afford to buy, or maybe the poor live in urban areas where people do not exercise. These hypotheses are plausible... until you look at the time series. It then becomes apparent that the rich and educated are gaining weight at the same rate as the poor. Poverty cannot explain this.
It is very difficult to make meaningful claims about causation—or even correlation!—on the basis of cross section data alone. Often times seemingly perfect, statistically significant correlations disappear when the same variables are viewed over a longer stretch of time. In other cases—as in this one—time series data reveals that the real story isn't about variance between two groups at all, but about the rate at which each group is changing. It is all too easy to be fooled by the Cross Section Illusion.")
),
("http://zenpundit.com/?p=52965",
("Announcing: The Thucydides Roundtable"
, "Tanner Greer et al"
, "2016-08-23"
, ""
, "I am proud to announce the upcoming Thucydides Roundtable, to be hosted at the group blog Zenpundit in October 2016.
Thucydides is a man of firsts. He has been called the father of realism, the first \"theorist of war\" in the Western tradition, the inventor of political science and international relations, the first man to ever attempt an objective and evidence based history of the world he lived in, and many other things besides. In the two thousand years since they were first written, his words have been used and abused by historians, poets, social scientists, and statesmen from one side of the Earth to the other. His chronicle of the thirty year war waged between his native Athens and her rival Sparta has just about everything in it. I really do mean everything. No great or enduring theme of the human experience is left untouched—war and international order of course make their appearance, but so do meditations on statesmanship, bargaining, courage, partisanship, justice, ethics, ambition, greed, honor, religion, culture, history, and so much more. His History of the Peloponnesian War is not just the story of a quarrel between Athenians and Lacedaemonians in the 5th century BC. It is a story about all of mankind.
Or at least this is what Thucydides hoped it would be.
I invite you to discover for yourself if Thucydides' ambition was realized by reading his work with us. We will officially kick off the roundtable discussion at Zenpundit in mid-October. In the weeks to come we will publish the full list of official participants as well as the Roundtable's official rules of engagement. Until then, I encourage you to go out and purchase the Landmark Thucydides to get a head start on the reading. It's a big book, but one well worth reading.")
),
("https://scholars-stage.blogspot.com/2016/10/everybody-wants-thucydides-trap.html",
("Everybody Wants a Thucydides Trap"
, "Tanner Greer"
, "2016-10-30"
, ""
, "We don't come to Thucydides' History with preexisting knowledge of the war. Our only guide to Thucydides is Thucydides himself. We thus must read with utmost care. If we do not, we risk mistaking Thucydides' judgments about the war for the events of the war itself.
Nowhere is more careful attention demanded than Thucydides' treatment of the Megarian Decree. Like all Greeks of the age, the Athenians had long memories. Their enmity for Megara began a generation earlier, when Athenian blood was lost as consequence of Megarian betrayal. The Megarian betrayal came during a day of war, Athen's first life-and-death struggle with the men of Sparta. The proximate causes of the this dispute were more recent, however. Thucydides reports that Athens \"accused the Megarians of pushing their cultivation into consecrated ground and the unenclosed land on their border, and of harboring runaway slaves.\" Thucydides' description of the Athenian response: a \"Megara Decree, excluding the Megarians from the use of Athenian harbors and of the market of Athens.\" (1.139.2)
...In face of these questions Pericles was dismissive:
\"I hope that none of you think that we shall be going to war for a trifle if we refuse to revoke the Megara decree, which appears in front of their complaints, and the revocation of which is to save us from war, or let any feeling of self-reproach linger in your minds, as if you went to war for slight cause. Why, this trifle contains the whole seal and trial of your resolution. If you give way, you will instantly have to meet some greater demand, as having been frightened into obedience in the first instance; while a firm refusal will make them clearly understand that they must treat you more as equals. Make your decision therefore at once, either to submit before you are harmed, or if we are to go to war, as I for one think we ought, to do so without caring whether the ostensible cause be great or small, resolved against making concessions or consenting to a precarious tenure of our possessions. For all claims from an equal, urged upon a neighbor as commands before any attempt at legal settlement, be they great or be they small, have only one meaning, and that is slavery. [1.40.4, emphasis added]
The argument that Thucydides puts into Pericles' mouth is simple: the coming war is not really about the decree at all, but more fundamental questions of power and rank. Is Athens subordinate to Sparta? Or are the two polis equal in rank? That was the real question being decided by this war. Any \"ostensible cause\" to get things rolling would do—in this case that ostensible cause just happened to be the embargo of Megara.
...See this for what it is: Thucydides has omitted from his history a central cause of the war! This was not an oversight. It may have been the entire point of Book I. In Thucydidean terms, the Megarian decree was (as Thucydides has Pericles say) \"a trifle.\" It was an \"ostensible cause\" of the great war, but not its true one. A war of this magnitude could not be caused by trifles, and to drive home the point of just how trifling and irrelevant this causus belli was to the war's actual conduct, Thucydides crafts a narrative of the war that does not include it at all...A review of the origins and first moments of this war suggests that it was less a matter of growing fear and growing power, than a matter of tarnished honor and quests for glory. Athens' growing wealth was a necessary condition for the war, but it was hardly the only or the most important cause of it. Had Athens' quest for glory been less ambitious, had Sparta not tied herself to an ally hellbent on forcing her private wars and narrow interests onto the entire league of Spartan allies, and had the Greeks not been a people obsessed with insults, rank, and honor, this war may never have occurred. It was not an inevitable clash of fear and power that brought war to Hellas, but a very specific set of decisions made by a very specific set of leaders in the years before the war.")
),
("https://scholars-stage.blogspot.com/2016/12/men-of-honor-men-of-interest.html",
("Men of Honor, Men of Interest"
, "Tanner Greer"
, "2016-12-01"
, ""
, "The Plataeans and the Mytilenians both heard a case arguing for their death, as well as one arguing for their continued survival. In the Mytilenian case, both the defendant and the prosecution were represented by Athenians. In the case of Plataea, the Plataeans were forced to speak in their own defense, with the Thebans arguing for their death. The parallel is clear. It to the arguments we turn to find the contrast between the two hegemonic powers....What is this but to make greater enemies than you have already, and to force others to become so who would otherwise have never thought of it?
The Athenians were once a people of honor. \"For glory then and honor now\" was the rallying cry Pericles raised to lead his people to war (2.64.6). The Athenians began this entire drama chasing it. No longer. Athenian honor died long before the war's close. Athenian honor could not survive the plague. Then the beastly truth was revealed: honor meant nothing but scarred skin and blistered visage. Nobility brought no recompense but rotting flesh. Eat now, drink now, be merry now, for tomorrow men will die! And die, and, die, and die. Justice, integrity, honor—mere words. Where could those words be found? Buried deep in burning heaps of flesh! Abandoned in lonely, forgotten corners where none would see them croak away! Beneath blood, phlegm, pustule, and vomit! What has honor to do with Athens? Nothing. What is more, they knew it....Thucydides relates the speech of two men in the debate over Mytilene, one Cleon, son of Cleanetus, the 'most violent man in Athens.' The other Diodotus, son of Eucrates, a more measured sort who does not appear elsewhere in this history. Cleon argues for the Mytilene's extinction. Diodotus, for their salvation. They disagreed on almost every point. What sticks out, however, is what they did agree on. Both wanted everyone to know that their arguments had nothing whatsoever to do with justice, honor, or mercy.
Said Cleon:
...However, if, right or wrong, you determine to rule, you must carry out your principle and punish the Mytilenians as your interest requires; or else you must give up your empire and cultivate honesty without danger (3.37; 3.40).
In reply, Diodotus:
...However, I have not come forward either to oppose or to accuse in the matter of Mytilene; indeed, the question before us as sensible men is not their guilt, but our interests. Though I prove them ever so guilty, I shall not, therefore, advise their death, unless it be expedient; nor though they should have claims to indulgence, shall I recommend it, unless it be clearly for the good of the country
Behold the men of Athens! Dead to honor, to principle, to humanity. This was a people whose hearts had hardened. Nothing was left to Athens but the pursuit of power—and its cousin, profit. The only language they spoke was the language of naked interest. That language saved the Mytilenians. They were lucky. Interest is a fickle master. The men of Melos discovered just how twisted a master it can be. In time, so would the Athenians.")
),
("https://scholars-stage.blogspot.com/2016/11/history-is-written-by-losers.html",
(" History is Written by the Losers "
, "Tanner Greer"
, "2016-11-21"
, ""
, "In his roundtable post, \"Treason Makes the Historian,\" Lynn Rees lists a few of the type. Herodotus wrote his history only after his exile from Halicarnassus; Xenophon wrote his memoirs only after his faction was forced out of Athens. Polybius was once a general for the Archean League, but wrote his history as a hostage at Rome. The destruction of Judea was chronicled by a Josephus, a Jew.
These men abandoned their countries and people for the victors of the future. But Quislingdom was not the only losing path to historical fame. Tacitus's loyalty to Rome never wavered—but neither did his identification with Rome's Senatorial class, a group whose power was slowly stripped away as Tacitus wrote his chronicles. Sima Guang, the second most significant historian of Chinese history, only finished his massive Zizhi Tongjian after court rivalries had forced him to retire. The history of the Mongols was written almost entirely by their vanquished enemies. Ibn Khaldun was associated with so many failed regimes that it is a wonder he found time to write his history at all.
I am sure more examples can be found. The example most relevant to this roundtable is one Thucydides, son of Olorus. It is here in Book IV we finally learn a tad about the man behind the curtain:
The passage of Brasidas was a complete surprise to the people in the town; and the capture of many of those outside, and the flight of the rest within the wall, combined to produce great confusion among the citizens; especially as they did not trust one another.... Meanwhile the party opposed to the traitors proved numerous enough to prevent the gates being immediately thrown open, and in concert with Eucles, the general, who had come from Athens to defend the place, sent to the other commander in Thrace, Thucydides, son of Olorus, the author of this history, who was at the isle of Thasos, a Parian colony, half a day's sail from Amphipolis, to tell him to come to their relief. On receipt of this message he at once set sail with seven ships which he had with him, in order, if possible, to reach Amphipolis in time to prevent its capitulation, or in any case to save Eion (4.103).
Now pieces of Thucydides work start to click together. Few Spartans are mentioned by name; fewer still are Spartans mentioned by nams on multiple occasions. The exception is Brasidas. Brasidas, brave defender of Methone, and thus \"the first man in this war to receive the official honors of Sparta\" (2.25). Brasidas, whose strategems almost defeated the Athenians at sea (2.86-87). Brasidas, the daring leading who almost stormed the fort at Pylos (4.12). Brasidas, the savior of Megara (4.70-73). Brasidas, the only Spartan eloquent and wise enough to raise all of Thessaly into revolt (4.84). Brasidas, the general who defeated Thucydides.
Thucydides' obsession with Brasidas is easy to understand once his personal relation to Thucydides is made clear. His portrayal of Brasidas as daring, brilliant, charismatic, and clever beyond measure also begins to make sense—the greater Brasidas' past feats appear, the less damning Thucydides defeat at his hands becomes.")
),
("https://scholars-stage.blogspot.com/2015/10/pre-modern-battlefields-were-absolutely.html",
("Pre-Modern Battlefields Were Absolutely Terrifying"
, "Tanner Greer"
, "2015-10-25"
, ""
, "Why was cold steel a \"unique terror\" for troops in combat? On the face of it a sword does not seem any more frightening than the cannon-ball. Pop culture portrayals of small imperialist forces putting hordes of backward natives to flight with nothing but gun and powder suggest the opposite conclusion. Images of countless thousands led to the slaughter on the banks of the Somme or hills of Verdun only strengthen the impression. But those men who actually withstood both the bullet and the bayonet overwhelmingly preferred to face the former. A similar preference for arrows and cross-bows shot from afar over spear thrusts and sword strokes closer to home pervades the ancient and medieval sources.
To understand why this was so you must discard Hollywood notions of close combat. This is hard to do, for the notions are much older than Hollywood. The classical Chinese novels Outlaws of the Marsh and Romance of the Three Kingdoms speak of warriors who exchange five, ten, twenty, and even fifty \"rounds\" or \"clashes\" on the battlefield. The long duels of ancient India's great war epic, the Mahabharata, are matched only by the extended contests of its Greek counterpart, the Iliad. All of it is poppycock. Ancient battles did not descend into a series of extended melees when the two front lines collided. The silliness of the Hollywood style of battle becomes immediately apparent when you watch sparring competitions that use pre-modern weapons: [video link]
As you can see, most close quarter engagements are decided within seconds. To engage in hand to hand combat is to hang your life on a the balance of a few split second decisions. This is terrifying. It is all the more terrifying if the enemy force is as committed and disciplined as your own. If you survive the first encounter—that is, if you successfully kill the first man who attempts to kill you—there will be another, and then yet another to fill in his place. How long can you keep making instant life-or-death decisions before you make a mistake? The odds are not in your favor. The physical and mental strain of close quarters combat on those in the front lines is simply more than can be borne for any great stretch of time.")
),
("https://scholars-stage.blogspot.com/2015/01/the-radical-sunzi.html",
("The Radical Sun Tzu"
, "Tanner Greer"
, "2015-01-02"
, ""
, "Timeless as it may seem, however, the Sunzi was the product of problems experienced at a specific time and a specific place. It is my belief that we cannot really understand the Sunzi if we do not first understand the world from which it came—the world of the Warring States.[2] A few historians and scholars of Chinese thought have written this sort of analysis; the best of these attempts to place the Sunzi within its historical context are usually focused on the broad, macro-historical trends that divided the Spring and Autumn period that preceded the Sunzi from the Warring States period that gave birth to it. From this perspective the Sunzi and the other military manuals that followed it were the natural product of a world torn asunder by wars waged on an ever increasing scale between large infantry armies fighting in the name of territorial, bureaucratized states.[3] There is, however, more to the Sunzi's historical setting than the institutional history of ancient China. Just as important is the intellectual milieu of early Warring States times. The compilers of the Sunzi were not the first Chinese to write about war. When read as a response to these earlier voices, the Sunzi's vision of war and politics is nothing less than radical.
...Its revolutionary nature only becomes clear when we see what it was written in response to. The place to turn is the Zuo Zhuan, China's oldest narrative historical account and one of the few preserves of the old Spring and Autumn ethos. One of its better known dictums reads:
The great affairs of state are sacrifice and warfare.[5]
Meyer comments on the contrast between the two statements:
[In the Sunzi] all mention of sacrifice is eliminated, telegraphing the text's contention that martial matters must be viewed in purely material terms. Rather than \"warfare\", the \"military\" is held up as the great affair of state, implying (as the text goes on to elaborate) that there are uses for military power beyond the 'honorable' contest of arms. Moreover, the word that the Sunzi uses by reference to the \"military\", bing (兵), does not evoke the aristocratic charioteer but the common foot solider, who had become the backbone of the Warring States army.[6]
The Sunzi's insistence that military methods were more important to the state's survival than sacrifice was not merely radical—it was nonsensical. In the early Chinese world view, sacrifice and warfare could not be separated from each other. As with the Aztecs, Maya, and many other premodern peoples, for the Chinese of Zhou times, warfare was a sacrificial ritual.")
),
("/docs/iq/1957-shockley.pdf",
("On the Statistics of Individual Variations of Productivity in Research Laboratories"
, "William Shockley"
, "1957"
, "10.1109/JRPROC.1957.278364"
, "It is well-known that some workers in scientific research laboratories are enormously more creative than others. If the number of scientific publications is used as a measure of productivity, it is found that some individuals create new science at a rate at least 50 times greater than others. Thus differences in rates of scientific production are much bigger than differences in the rates of performing simpler acts, such as the rate of running the mile, or the number of words a man can speak per minute. On the basis of statistical studies of rates of publication, it is found that it is more appropriate to consider not simply the rate of publication but its logarithm. The logarithm appears to have a normal distribution over the population of typical research laboratories. The existence of a \"log-normal distribution\" suggests that the logarithm of the rate of production is a manifestation of some fairly fundamental mental attribute. The great variation in rate of production from one individual to another can be explained on the basis of simplified models of the mental processes concerned. The common feature in the models is that a large number of factors are involved so that small changes in each, all in the same direction, may result in a very large [multiplicative] change in output. For example, the number of ideas a scientist can bring into awareness at one time may control his ability to make an invention and his rate of invention may increase very rapidly with this number.")
),
("/docs/psychology/1993-lipsey.pdf",
("The Efficacy of Psychological, Educational, and Behavioral Treatment: Confirmation from Meta-Analysis"
, "Mark W. Lipsey, David B. Wilson"
, "1993"
, ""
, "Conventional reviews of research on the efficacy of psychological, educational, and behavioral treatments often find considerable variation in outcome among studies and, as a consequence, fail to reach firm conclusions about the overall effectiveness of the interventions in question. In contrast meta-analytic reviews show a strong, dramatic pattern of positive overall effects that cannot readily be explained as artifacts of meta-analytic technique or generalized placebo effects. Moreover, the effects are not so small that they can be dismissed as lacking practical or clinical significance. Although meta-analysis has limitations, there are good reasons to believe that its results are more credible than those of conventional reviews and to conclude that well-developed psychological, educational, and behavioral treatment is generally efficacious.")
),
("/docs/nootropics/2013-rojas.pdf",
("Neurological and psychological applications of transcranial lasers and LEDs"
, "Julio C.Rojas, F.Gonzalez-Lima"
, "2013"
, "10.1016/j.bcp.2013.06.012"
, "Transcranial brain stimulation with low-level light/laser therapy (LLLT) is the use of directional low-power and high-fluency monochromatic or quasimonochromatic light from lasers or LEDs in the red-to-near-infrared wavelengths to modulate a neurobiological function or induce a neurotherapeutic effect in a nondestructive and non-thermal manner. The mechanism of action of LLLT is based on photon energy absorption by cytochrome oxidase, the terminal enzyme in the mitochondrial respiratory chain. Cytochrome oxidase has a key role in neuronal physiology, as it serves as an interface between oxidative energy metabolism and cell survival signaling pathways. Cytochrome oxidase is an ideal target for cognitive enhancement, as its expression reflects the changes in metabolic capacity underlying higher-order brain functions. This review provides an update on new findings on the neurotherapeutic applications of LLLT. The photochemical mechanisms supporting its cognitive-enhancing and brain-stimulatory effects in animal models and humans are discussed. LLLT is a potential non-invasive treatment for cognitive impairment and other deficits associated with chronic neurological conditions, such as large vessel and lacunar hypoperfusion or neurodegeneration. Brain photobiomodulation with LLLT is paralleled by pharmacological effects of low-dose USP methylene blue, a non-photic electron donor with the ability to stimulate cytochrome oxidase activity, redox and free radical processes. Both interventions provide neuroprotection and cognitive enhancement by facilitating mitochondrial respiration, with hormetic dose-response effects and brain region activational specificity. This evidence supports enhancement of mitochondrial respiratory function as a generalizable therapeutic principle relevant to highly adaptable systems that are exquisitely sensitive to energy availability such as the nervous system.")
),
("/docs/radiance/2005-gusterson.pdf",
("A Pedagogy of Diminishing Returns: Scientific Involution across Three Generations of Nuclear Weapons Science"
, "Hugh Gusterson"
, "2005"
, ""
, "A generation of historians, sociologists, and anthropologists of science has learned from actor-network theory and the sociology of scientific knowledge (SSK) to focus on the building of scientific institutions and facts, and from Thomas Kuhn to expect a certain historical rhythm in the evolution of scientific fields of knowledge: first, a dynamic burst of creativity (the \"revolution\") as the foundational ideas of the new field are laid down; second, a period of \"normal science\" in which gaps are filled in as the new knowledge is institutionalized; and, finally, as puzzles emerge that cannot be fully explained by the established paradigm, a new burst of creativity as another generation redefines the fundamental precepts of the field.
In this essay, looking at three generations of nuclear weapons designers, I follow and then depart from the Kuhnian script. Although the first two generations of nuclear weapons scientists conformed perfectly to the Kuhnian storyline, the final story is not about the punctuated equilibrium of scientific revolution, but about a process of scientific involution as nuclear weapons science has simultaneously matured and withered in a way that is beautifully evoked in a blues ballad once sung for me by a group of weapons designers from the Lawrence Livermore National Laboratory:
Went down to Amarillo
Lookin' for my sweet '533
It was laying on a long white table
Looked cold and hard to me
Let it go, let it go, retire it
No city scrapers do we need
Take a 614 and modify it.
Call it the mod 11-E
Now you can search this whole world over
From Frisco to Albuquerque
You can mentor anyone that you want to
But you'll never find designers like me
Now when I'm gone, just put me way down
In a hole off the old Orange Road.
'ttach a cable to my device can
So I can run those legacy codes (fading)
So I can run those legacy codes
So I can run those legacy codes.5
...The 1970s and the 1980s, when nuclear testing moved underground, were a period of routinization: the institutional apparatus for nuclear weapons design and testing grew, its scientific achievements shrank, and the arteries of the weapons design bureaucracy hardened. Attempts to perfect a third-generation nuclear weapon—the x-ray laser—failed and were abandoned in an atmosphere of scandal and disgrace.11 The art of weapons design progressed, but by increments rather than great leaps: weapons designers learned to squeeze greater yields out of smaller quantities of plutonium so that nuclear weapons could be made lighter and smaller, weapons were made safer through the addition of Permissive Action Links (PALS) and the substitution of Insensitive High Explosive (IHE) for conventional explosives,12 and the supercomputer codes used to model the behavior of nuclear weapons were gradually refined. The names of the men (and now women) behind these achievements are largely unknown outside the nuclear weapons bureaucracy, and in some cases their achievements are only partially known within the weapons laboratories, thanks to the compartmentalizing effects of official secrecy in the weapons complex.13
Nuclear tests were forbidden after the end of the Cold War, and the practice and pedagogy of nuclear weapons science shifted again. Forced to largely abandon their nuclear test site in Nevada—a place where the desert sands encroach on the old bowling alley and cinema, now disused, as tourist buses disgorge camera-laden voyeurs to gawk at the nuclear craters—many of the old-timers elected to retire. Those that stayed have regrouped their forces in the virtual world of simulated testing, where they are attempting to train a new generation of scientists to maintain devices they cannot test. In some ways the scientific challenges of nuclear weapons design have shrunk to microscopic proportions: new designs are not built or deployed, and even the decision to substitute a new epoxy in an aging weapon can send a tremor of fear through design teams unsure if their weapons will still work. In other ways, the scientific challenges are suddenly magnified: how to design implosion, shock wave, and laser fusion experiments that will shed light on the performance of aging nuclear weapons in the absence of nuclear testing? How to use the physics knowledge of today to understand test data, long buried in dusty filing cabinets, from the 1950s and the 1960s? And how to convert old two-dimensional codes designed for Cray supercomputers into three-dimensional codes that can run on massively parallel systems now being designed?
")
),
("/docs/psychology/1963-gussow.pdf",
("A Preliminary Report of Kayak Angst Among the Eskimo of West Greenland: A Study in Sensory Deprivation"
, "Zachary Gussow"
, "1963"
, "10.1177/002076406300900103"
, "Sensory deprivation experiences and isolation phenomena belong to the broader field of environmental stress and, as such, research in this area is of importance to the anthropologist concerned with mental disorder. In one form or another sensory deprivation is a universal experience. It is present in such diverse events as research experiments, sleep, vision experiences, 'highway hypnosis' and kayak-angst. Sensory deprivation and isolation may be culturally required, recommended, unavoidable or even individually sought out. Reactions are variable and are dependent upon the interplay of a number of factors. Experiences may be occupationally linked, as in the confused and disoriented reactions reported by aviators flying solo or in positions cut off from the rest of the crew. Creative people who seek out retreats in order to work more efficiently and productively, as well as persons on the couch in psychoanalytic treatment are also experiencing sensory deprivation, though in a mild form.
In kayak-angst the Eskimo of West Greenland provide us with an instance of a group where severe sensory deprivation reactions are culturally typical for the adult male segment of the population and forms a part of their routinized, seasonal, if not everyday, round of life.
Kayak-angst (kayak-phobia, kayak-dizziness) is well known throughout all districts of West Greenland. It is also known to occur among the Polar Eskimo and in East Greenland, though an intensive search of the literature, extensive correspondence, and interviews with eastern Canadian Eskimos has failed so far to document it for other Eskimo groups. Kayak-angst is scarcely mentioned in English written accounts, with the exception of brief references in Freuchen, Birket-Smith and a few others. On the other hand there is a considerable body of material in the Scandinavian languages, much of it gathered by Danish physicians. The condition was reported as early as 1806* and in 1949 Dr. Av M Ch. Ehrstrom diagnosed 24 cases in one of the northern districts. Kenneth I. Taylor, a student of anthropology with considerable kayak experience informs me (private communication) that as recently as 1959 he met three such individuals in Northwest Greenland. In 1900, Meldorf estimated that 10% of all men in the Julianhaab district over the age of 18 suffered from kayak-angst. Others have regarded it as the 'national disease' of the West Greenland Eskimo.
Material for the present paper is based on an analysis of 13 cases out of the 60 kayak-angst individuals medically examined and interviewed by Bertelsen in 1905.
Kayak-Angst Syndrome
Typically, kayak-angst afflict male hunters out alone on a calm, 'mirroring' slightly wavy sea or lake, close to or at a distance from shore, either while paddling or sitting quietly. Under these conditions of sea, and especially with the sun directly overhead or in his eyes, there develops a lowering in the level of consciousness brought on by the absence of external reference points at a time when the hunter is involved in a visually 'fixed' or staring position demanding minimal or repetitive movements. A lesser number report they are equally affected in storms, windy or rough weather. Some claim not to have attacks when in the company of others and consequently will never hunt alone. A few report attacks when others are around, though claim they are less severe at this time. On the other hand some report that the presence of others increases their anxiety. One man was afraid their kayaks might collide, particularly in storms. Another said he felt at ease only in the company of men he trusted.")
),
("/docs/lithium/2014-mauer.pdf",
("Standard and trace-dose lithium: A systematic review of dementia prevention and other behavioral benefits"
, "Sivan Mauer, Derick Vergne, S. Nassir Ghaemi"
, "2014-06-11"
, "10.1177/0004867414536932"
, "Objective: Dementia is a major public health issue, with notably high rates in persons with mood illnesses. Lithium has been shown to have considerable neuroprotective effects, even in trace or low doses. The aim of this review is to summarize the current understanding of lithium benefits in trace or low doses in dementia prevention and for other behavioral or medical benefits.
Methods: A systematic review identified 24 clinical, epidemiological, and biological reports that met inclusion criteria of assessing lithium in standard or low doses for dementia or other behavioral or medical benefits.
Results: 5 out of 7 epidemiological studies found an association between standard-dose lithium and low dementia rates. 9 out of 11 epidemiological studies, usually of drinking water sources, found an association between trace-dose lithium and low suicide/homicide/mortality and crime rates. All four small randomized clinical trials of lithium for Alzheimer's dementia have found at least some clinical or biological benefits versus placebo. Only one small randomized clinical trial (RCT) of trace lithium has been conducted, assessing mood symptoms in former substance abusers, and found benefit with lithium versus placebo.
Conclusions: Lithium, in both standard and trace doses, appears to have biological benefits for dementia, suicide, and other behavioral outcomes. Further RCT research of trace lithium in dementia is warranted. [Keywords: Cognition, dementia, lithium, prevention, standard dose, trace]")
),
("/docs/eva/2008-gardner.pdf",
("Aum Shinrikyo and a Panic About Manga and Anime"
, "Richard A. Gardner"
, "2008"
, "10.4324/9781315703152-16"
, "In the midst of the accolades, it is important to recall that there have been moments in recent history when manga and anime have been regarded as potentially dangerous or as emblems of what is wrong with Japan.
Such was the case in the months following the release of sarin gas in several Tokyo subway lines by members of the religious group Aum Shinrikyo on the morning of March 20, 1995. As the extent of the Aum's crimes gradually became clear, Japanese journalists, scholars, intellectuals, and commentators of every sort attempted to explain the origin and rise of Aum, the reasons for the group's turn to violence, and what the appearance of such a group might mean about Japan. In the various theories and explanations presented, nearly every aspect of Japanese society, culture, and religion has been held to be at least partially accountable for the rise of Aum and the turn to violence by some of its members (see Gardner 1999, 221–222; 2002a, 36–42). In the efforts to explain Aum, considerable attention was given to the roles that manga and anime might have played. This resulted in what might be described as a panic about their possible negative influence on Japanese culture and society. Rather than attempting to explain precisely how manga and anime might have contributed to the rise of Aum and its vision of 'Harumagedon', or Armageddon, this chapter will simply present an overview of the ways in which both members of Aum and commentators on Aum understood the role of manga and anime in relation to Aum. Attention will be given, in particular, to how these perceptions were linked with broader concerns about the possible negative influence of various forms of media, technology, and 'virtual reality'.")
),
("/docs/statistics/bias/2013-ioannidis.pdf",
("What's to know about the credibility of empirical economics?"
, "John Ioannidis, Chris Doucouliagos"
, "2013"
, "10.1111/joes.12032"
, "The scientific credibility of economics is itself a scientific question that can be addressed with both theoretical speculations and empirical data. In this review, we examine the major parameters that are expected to affect the credibility of empirical economics: sample size, magnitude of pursued effects, number and pre-selection of tested relationships, flexibility and lack of standardization in designs, definitions, outcomes and analyses, financial and other interests and prejudices, and the multiplicity and fragmentation of efforts. We summarize and discuss the empirical evidence on the lack of a robust reproducibility culture in economics and business research, the prevalence of potential publication and other selective reporting biases, and other failures and biases in the market of scientific information. Overall, the credibility of the economics literature is likely to be modest or even low. [Keywords: Bias; Credibility; Economics; Meta-research; Replication; Reproducibility]")
),
("/docs/iq/smpy/2013-kell.pdf",
("Who Rises to the Top?: Early Indicators"
, "Harrison J. Kell, David Lubinski, Camilla P. Benbow"
, "2013-03-26"
, "10.1177/0956797612457784"
, "Youth identified before age 13 (n = 320) as having profound mathematical or verbal reasoning abilities (top 1 in 10,000) were tracked for nearly three decades. Their awards and creative accomplishments by age 38, in combination with specific details about their occupational responsibilities, illuminate the magnitude of their contribution and professional stature. Many have been entrusted with obligations and resources for making critical decisions about individual and organizational well-being. Their leadership positions in business, health care, law, the professoriate, and STEM (science, technology, engineering, and mathematics) suggest that many are outstanding creators of modern culture, constituting a precious human-capital resource. Identifying truly profound human potential, and forecasting differential development within such populations, requires assessing multiple cognitive abilities and using atypical measurement procedures. This study illustrates how ultimate criteria may be aggregated and longitudinally sequenced to validate such measures. [Keywords: cognitive abilities, creativity, human capital, intelligence, profoundly gifted, STEM]")
),
("/docs/psychology/1955-abramson.pdf",
("Lysergic Acid Diethylamide (Lsd-25): Xv. the Effects Produced By Substitution of a Tap Water Placebo"
, "H. A. Abramson, M. E. Jarvik, A. Levine, M. R. Kaufman, M. W. Hirsch"
, "1955"
, "10.1080/00223980.1955.9712991"
, "The purpose of this paper is to study the responses given to a questionnaire by subjects who received a tap water 'placebo' instead of lysergic acid diethylamide (LSD-25), and to relate the number of responses to other variables. These variables are: body weight, number of responses on a health questionnaire, arithmetic test scores, scores on the Wechsler-Bellevue Intelligence Scale, and Rorschach test responses.
...Figure 4 shows for each question the percentage and number of subjects out of 28 who gave a positive response at least once during the 0.5, 2.5, and 4.5-hour intervals. The questions appear in the figure in the order of decreasing percentages of response to them. The time of the response and the magnitude are disregarded in this tabulation. The question receiving the greatest percentage response was (Subject 24), \"Are your palms moist?\" As many as 60.7 per cent reported this symptom. Half of the subjects reported headache (Subject 13) , fatigue (Subject 44), and drowsiness (Subject 45). About 36 per cent reported anxiety (Subject 47). Illness (Subject 1), and dizziness (Subject 15) were reported by 28.6 per cent of the group and 25 per cent indicated a dream-like feeling (Subject 46), increased appetite (Subject 6), unsteadiness (Subject 16), a hot feeling (Subject 22) , heaviness of hands and feet (Subject 30), and weakness (Subject 43). There were 19 questions which received positive responses from between 10 and 22 per cent of the subjects. Less than 10 per cent of the group (or no more than two subjects) responded positively to the remaining questions, but each question received a positive response from at least one subject.
...The findings point out that a substance such as tap water, which is generally considered chemically and pharmacologically inactive, is capable of eliciting certain responses from certain subjects who believe they have received lysergic acid diethylamide. These observations emphasize once more the need for pIacebo controls in studies investigating the effects of drugs; without them changes which are produced merely by the situation and not by the drug are frequently falsely attributed to the action of the drug...Most subjects who respond to a placebo tend to do so most markedly during the first 0.5 hour after receiving the substance. At this time their anticipation of, and anxiety about, the effects of LSD-25 are probably greatest. Gradually the effects wear off, as the anticipation wears off. Individual differences exist in the time of peak effect, but this is the most common finding. The questions which elicited the greatest percentage response from the group were those related to anxiety (moist palms and feeling anxious) or to phenomena which commonly occur without the presence of any foreign agent (drowsiness, fatigue, and headache). The remaining questions received random responses. The fact that there is a wide range in the number of positive responses made to the questionnaire is of major interest.")
),
("/docs/statistics/bias/2008-scherer.pdf",
("Full publication of results initially presented in abstracts"
, "Roberta W. Scherer, Patricia Langenberg, Erik von Elm"
, "2007"
, "10.1002/14651858.MR000005.pub3"
, "Studies initially reported as conference abstracts that have positive results are subsequently published as full-length journal articles more often than studies with negative results.
Less than half of all studies, and about 60% of randomized or controlled clinical trials, initially presented as summaries or abstracts at professional meetings are subsequently published as peer-reviewed journal articles. An important factor appearing to influence whether a study described in an abstract is published in full is the presence of 'positive' results in the abstract. Thus, the efforts of persons trying to collect all of the evidence in a field may be stymied, first by the failure of investigators to take abstract study results to full publication, and second, by the tendency to take to full publication only those studies reporting 'significant' results. The consequence of this is that systematic reviews will tend to over-estimate treatment effects.
Background: Abstracts of presentations at scientific meetings are usually available only in conference proceedings. If subsequent full publication of abstract results is based on the magnitude or direction of study results, publication bias may result. Publication bias, in turn, creates problems for those conducting systematic reviews or relying on the published literature for evidence.
Objectives: To determine the rate at which abstract results are subsequently published in full, and the time between meeting presentation and full publication.
Search methods: We searched MEDLINE, EMBASE, The Cochrane Library, Science Citation Index, reference lists, and author files. Date of most recent search: June 2003. Selection criteria We included all reports that examined the subsequent full publication rate of biomedical results initially presented as abstracts or in summary form. Follow-up of abstracts had to be at least two years.
Data collection and analysis: Two reviewers extracted data. We calculated the weighted mean full publication rate and time to full publication. Dichotomous variables were analyzed using relative risk and random effects models. We assessed time to publication using Kaplan-Meier survival analyses.
Main results: Combining data from 79 reports (29,729 abstracts) resulted in a weighted mean full publication rate of 44.5% (95% confidence interval (CI) 43.9 to 45.1). Survival analyses resulted in an estimated publication rate at 9 years of 52.6% for all studies, 63.1% for randomized or controlled clinical trials, and 49.3% for other types of study designs.
'Positive' results defined as any 'significant' result showed an association with full publication (RR = 1.30; CI 1.14 to 1.47), as did 'positive' results defined as a result favoring the experimental treatment (RR =1.17; CI 1.02 to 1.35), and 'positive' results emanating from randomized or controlled clinical trials (RR = 1.18, CI 1.07 to 1.30).
Other factors associated with full publication include oral presentation (RR = 1.28; CI 1.09 to 1.49); acceptance for meeting presentation (RR = 1.78; CI 1.50 to 2.12); randomized trial study design (RR = 1.24; CI 1.14 to 1.36); and basic research (RR = 0.79; CI 0.70 to 0.89). Higher quality of abstracts describing randomized or controlled clinical trials was also associated with full publication (RR = 1.30, CI 1.00 to 1.71).
Authors' conclusions: Only 63% of results from abstracts describing randomized or controlled clinical trials are published in full. 'Positive' results were more frequently published than not 'positive' results.
")
),
("/docs/melatonin/2013-preckel.pdf",
("Morningness-eveningness and educational outcomes: the lark has an advantage over the owl at high school"
, "Franzis Preckel, Anastasiya A. Lipnevich, Katharina Boehme, Lena Brandner, Karsten Georgi, Tanja Könen, Katharina Mursin, Richard D. Roberts"
, "2012-01-02"
, "10.1111/j.2044-8279.2011.02059.x"
, "Background: Chronotype refers to individuals' preference for morning or evening activities. Its two dimensions (morningness and eveningness) are related to a number of academic outcomes.
Aims: The main goal of the study was to investigate the incremental validity of chronotype as a predictor of academic achievement after controlling for a number of traditional predictors. In so doing, a further aim was ongoing validation of a chronotype questionnaire, the Lark-Owl Chronotype Indicator.
Sample: The sample comprised 272 students attending 9th and 10th grades at five German high schools. Data was also obtained from 132 parents of these students.
Method: Students were assessed in class via self-report questionnaires and a standardized cognitive test. Parents filled out a questionnaire at home. The incremental validity of chronotype was investigated using hierarchical linear regression. Validity of the chronotype questionnaire was assessed by correlating student ratings of their chronotype with behavioural data on sleep, food intake, and drug consumption and with parent ratings of chronotype.
Results: Eveningness was a significant (negative) predictor of overall grade point average (GPA), math-science GPA, and language GPA, after cognitive ability, conscientiousness, need for cognition, achievement motivation, and gender were held constant. Validity evidence for the chronotype measure was established by significant correlations with parent-ratings and behavioural data.
Conclusions: Results point to the possible discrimination of adolescents with a proclivity towards eveningness at school. Possible explanations for the relationship between chronotype and academic achievement are presented. Implications for educational practice are also discussed.
")
),
("https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4959137/",
("The Unilateralist's Curse and the Case for a Principle of Conformity"
, "Nick Bostrom, Thomas Douglas, Anders Sandberg"
, "2016-01-26"
, "10.1080/02691728.2015.1108373"
, "In some situations a number of agents each have the ability to undertake an initiative that would have significant effects on the others. Suppose that each of these agents is purely motivated by an altruistic concern for the common good. We show that if each agent acts on her own personal judgment as to whether the initiative should be undertaken, then the initiative will be undertaken more often than is optimal. We suggest that this phenomenon, which we call the unilateralist's curse, arises in many contexts, including some that are important for public policy. To lift the curse, we propose a principle of conformity, which would discourage unilateralist action. We consider three different models for how this principle could be implemented, and respond to an objection that could be raised against it. [Keywords: The Winner's Curse, Disagreement, Rationality, Aumann, informative prior, shrinkage, bid shading]")
),
("/docs/psychology/2014-vyssoki.pdf",
("Direct Effect of Sunshine on Suicide"
, "Benjamin Vyssoki, Nestor D. Kapusta, Nicole Praschak-Rieder, Georg Dorffner, Matthaeus Willeit"
, "2014:09:10"
, "10.1001/jamapsychiatry.2014.1198"
, "Importance: It has been observed that suicidal behavior is influenced by sunshine and follows a seasonal pattern. However, seasons bring about changes in several other meteorological factors and a seasonal rhythm in social behavior may also contribute to fluctuations in suicide rates.
Objective*: To investigate the effects of sunshine on suicide incidence that are independent of seasonal variation.
Design, Setting, and Participants: Retrospective analysis of data on all officially confirmed suicides in Austria between January 1, 1970, and May 6, 2010 (n = 69 462). Data on the average duration of sunshine per day (in hours) were calculated from 86 representative meteorological stations. Daily number of suicides and daily duration of sunshine were differentiated to remove variation in sunshine and variation in suicide incidence introduced by season. Thereafter, several models based on Pearson correlation coefficients were calculated.
Main Outcomes and Measures: Correlation of daily number of suicides and daily duration of sunshine after mathematically removing the effects of season.
Results: Sunshine hours and number of suicides on every day from January 1, 1970, to May 6, 2010, were highly correlated (r = 0.4870; p < 10−9). After differencing for the effects of season, a mathematical procedure that removes most of the variance from the data, a positive correlation between number of suicides and hours of daily sunshine remained for the day of suicide and up to 10 days prior to suicide (rmaximum = 0.0370; p < 10−5). There was a negative correlation between the number of suicides and daily hours of sunshine for the 14 to 60 days prior to the suicide event (rminimum = −0.0383; p < 10−5). These effects were found in the entire sample and in violent suicides.
Conclusions and Relevance: Duration of daily sunshine was significantly correlated with suicide frequency independent of season, but effect sizes were low. Our data support the hypothesis that sunshine on the day of suicide and up to 10 days prior to suicide may facilitate suicide. More daily sunshine 14 to 60 days previously is associated with low rates of suicide. Our study also suggests that sunshine during this period may protect against suicide.
")
),
("/docs/nootropics/2015-hall.pdf",
("Genetics and the placebo effect: the placebome"
, "Kathryn T. Hall, Joseph Loscalzo, Ted J. Kaptchuk"
, "2015-05-01"
, "10.1016/j.molmed.2015.02.009"
, "- Predisposition to respond to placebo treatment may be in part a stable heritable trait.
- Candidate placebo response pathways may interact with drugs to modify outcomes in both the placebo and drug treatment arms of clinical trials.
- Genomic analysis of randomized placebo and no-treatment controlled trials are needed to fully realize the potential of the placebome.
Placebos are indispensable controls in randomized clinical trials (RCTs), and placebo responses significantly contribute to routine clinical outcomes. Recent neurophysiological studies reveal neurotransmitter pathways that mediate placebo effects. Evidence that genetic variations in these pathways can modify placebo effects raises the possibility of using genetic screening to identify placebo responders and thereby increase RCT efficacy and improve therapeutic care. Furthermore, the possibility of interaction between placebo and drug molecular pathways warrants consideration in RCT design. The study of genomic effects on placebo response, 'the placebome', is in its infancy. Here, we review evidence from placebo studies and RCTs to identify putative genes in the placebome, examine evidence for placebo-drug interactions, and discuss implications for RCTs and clinical care.
")
),
("/docs/radiance/1995-mackenzie.pdf",
("Tacit Knowledge, Weapons Design, and the Uninvention of Nuclear Weapons"
, "Donald MacKenzie, Graham Spinardi"
, "1995"
, "10.1086/230699"
, "'Tacit Knowledge', embodied in people rather than words, equations, or diagrams, plays a vital role in science. The historical record of the development and spread of nuclear weapons and the recollections of their designers suggest that tacit knowledge is also crucial to nuclear weapons development. Therefore, if design ceases, and if there is no new generation of designers to whom that tacit knowledge can be passed, then in an important (though qualified) sense nuclear weapons will have been uninvented. Their renewed development would thus have some of the characteristics of reinvention rather than simply copying. In addition, knowledge may be lost not only as a result of complete disarmament, but also as a consequence of likely measures such as a nuclear test ban.")
),
("/docs/genetics/2015-rottensteiner.pdf",
("Physical activity, fitness, glucose homeostasis, and brain morphology in twins"
, "Mirva Rottensteiner, Tuija Leskinen, Eini Niskanen, Sari Aaltonen, Sara Mutikainen, Jan Wikgren, Kauko Heikkilä, Vuokko Kovanen, Heikki Kainulainen, Jaakko Kaprio, Ina Tarkka, Urho Kujala"
, "2015"
, "10.1249/MSS.0000000000000437"
, "Purpose: The main aim of the present study (FITFATTWIN) was to investigate how physical activity level is associated with body composition, glucose homeostasis, and brain morphology in young adult male monozygotic twin pairs discordant for physical activity.
Methods: From a population-based twin cohort, we systematically selected 10 young adult male monozygotic twin pairs (age range, 32–36 yr) discordant for leisure time physical activity during the past 3 yr. On the basis of interviews, we calculated a mean sum index for leisure time and commuting activity during the past 3 yr (3-yr LTMET index expressed as MET-hours per day). We conducted extensive measurements on body composition (including fat percentage measured by dual-energy x-ray absorptiometry), glucose homeostasis including homeostatic model assessment index and insulin sensitivity index (Matsuda index, calculated from glucose and insulin values from an oral glucose tolerance test), and whole brain magnetic resonance imaging for regional volumetric analyses.
Results: According to pairwise analysis, the active twins had lower body fat percentage (p = 0.029) and homeostatic model assessment index (p = 0.031) and higher Matsuda index (p = 0.021) compared with their inactive co-twins. Striatal and prefrontal cortex (subgyral and inferior frontal gyrus) brain gray matter volumes were larger in the nondominant hemisphere in active twins compared with those in inactive co-twins, with a statistical threshold of p < 0.001.
Conclusions: Among healthy adult male twins in their mid-30s, a greater level of physical activity is associated with improved glucose homeostasis and modulation of striatum and prefrontal cortex gray matter volume, independent of genetic background. The findings may contribute to later reduced risk of type 2 diabetes and mobility limitations.")
),
("/docs/statistics/causality/2017-allamee.pdf",
("Percutaneous coronary intervention in stable angina (ORBITA): a double-blind, randomised controlled trial"
, "Rasha Al-Lamee, David Thompson, Hakim-Moulay Dehbi, Sayan Sen, Kare Tang, John Davies, Thomas Keeble, Michael Mielewczik, Raffi Kaprielian, Iqbal S Malik, Sukhjinder S Nijjer, Ricardo Petraco, Christopher Cook, Yousif Ahmad, James Howard, Christopher Baker, Andrew Sharp, Robert Gerber, Suneel Talwar, Ravi Assomull, Jamil Mayet, Roland Wensel, David Collier, Matthew Shun-Shin, Simon A Thom, Justin E Davies, Darrel P Francis"
, "2017-11-02"
, "10.1016/S0140-6736(17)32714-9"
, "Summary: Background Symptomatic relief is the primary goal of percutaneous coronary intervention (PCI) in stable angina and is commonly observed clinically. However, there is no evidence from blinded, placebo-controlled randomised trials to show its efficacy.
Methods>/em>: ORBITA is a blinded, multicentre randomised trial of PCI versus a placebo procedure for angina relief that was done at five study sites in the UK. We enrolled patients with severe (≥70%) single-vessel stenoses. After enrolment, patients received 6 weeks of medication optimisation. Patients then had pre-randomisation assessments with cardiopulmonary exercise testing, symptom questionnaires, and dobutamine stress echocardiography. Patients were randomised 1:1 to undergo PCI or a placebo procedure by use of an automated online randomisation tool. After 6 weeks of follow-up, the assessments done before randomisation were repeated at the final assessment. The primary endpoint was difference in exercise time increment between groups. All analyses were based on the intention-to-treat principle and the study population contained all participants who underwent randomisation. This study is registered with ClinicalTrials.gov, number NCT02062593.
Findings: ORBITA enrolled 230 patients with ischaemic symptoms. After the medication optimisation phase and between Jan 6, 2014, and Aug 11, 2017, 200 patients underwent randomisation, with 105 patients assigned PCI and 95 assigned the placebo procedure. Lesions had mean area stenosis of 84.4% (SD 10.2), fractional flow reserve of 0.69 (0.16), and instantaneous wave-free ratio of 0.76 (0.22). There was no significant difference in the primary endpoint of exercise time increment between groups (PCI minus placebo 16.6 s, 95% CI -8.9 to 42.0, p=0.200). There were no deaths. Serious adverse events included four pressure-wire related complications in the placebo group, which required PCI, and five major bleeding events, including two in the PCI group and three in the placebo group.
Interpretation: In patients with medically treated angina and severe coronary stenosis, PCI did not increase exercise time by more than the effect of a placebo procedure. The efficacy of invasive procedures can be assessed with a placebo control, as is standard for pharmacotherapy.")
),
("https://medium.com/@vanya_cohen/opengpt-2-we-replicated-gpt-2-because-you-can-too-45e34e6d36dc",
("OpenGPT-2: We Replicated GPT-2-1.5b Because You Can Too"
, "Aaron Gokaslan, Vanya Cohen"
, "2019-08-22"
, ""
, "Recently, large language models like BERT¹, XLNet², GPT-2³, and Grover⁴ have demonstrated impressive results generating new content and multiple tasks. Since Open-AI has not released their largest model [GPT-2-1.5b] at this time, we seek to replicate the model to allow others to build on our pretrained model and further improve it. You can access the model and generate text using our Google Colab.
...We demonstrate that many of the results of the paper can be replicated by two masters students...Because our replication efforts are not unique, and large language models are the current most effective means of countering generated text, we believe releasing our model is a reasonable first step towards countering the potential future abuse of these kinds of models.
We base our implementation off of the Grover model⁴ and modify their codebase to match the language modeling training objective of GPT-2. Since their model was trained on a similarly large corpus, much of the code and hyperparams proved readily reusable. We did not substantially change the hyperparameters from Grover.
From start to finish, we estimate that we use under $500,000 in cloud compute for all of our experiments including searching for hyper-parameters and testing various cleaning methods on our datasets. The cost of training the model from scratch using our code is about $50,000.
...Despite the differences in our training distribution, we do report similar perplexities over most datasets.")
),
("https://scholars-stage.blogspot.com/2014/09/what-edward-luttwak-doesnt-know-about.html",
("What Edward Luttwak Doesn't Know About Ancient China (Or a Short History of Han-Xiongnu Relations), pt. 1"
, "Tanner Greer"
, "2014-10-04"
, ""
, "A few weeks ago a friend passed along one of the least correct essays I have ever had the misfortune to read. It was written by Edward Luttwak...In it Luttwak suggests contemporary Chinese foreign policy follows a pattern first seen in the foreign relations of the Han Dynasty two millennia ago:
Formidable mounted archers and capable of sustained campaigning (a primary objective of the Steppe State), the Xiongnú ravaged and savaged and extorted tribute from the perpetually less martial, and certainly cavalry-poor Han until the latter finally felt able to resist again. Even then, 147 years of intermittent warfare ensued until Huhanye (呼韓邪), the paramount Chanyu (Qagan, Khan) of the Xiongnú, personally and formally submitted to the emperor Han Xuandi in 51 BCE, undertaking to pay homage, to leave a son at court as a hostage, and to deliver tribute, as befitted a vassal. That was a very great downfall from the familial status of earlier Chanyus of the epoch of Xiongnú predominance, who were themselves recognized as emperors, whose sons and heirs could have imperial daughters in marriage, and who from 200 BCE had received tribute from the Han, instead of the other way around. It is this successful transformation of a once superior power first into an equal (signified by imperial marriages) and then into a subservient client-state that seems to have left an indelible residue in China's tradition of statecraft.
..if Edward Luttwak wants to talk about how the echoes of the Han-Xiongnu war can be heard in modern China's foreign policy, I am all ears. Long term readers of The Stage know that there are few conversation starters I would find more thrilling to hear. Too many contemporary controversies cannot be understood until we step back and look at world affairs from the long view of history. But there is a catch in all this: the history has to be correct. It must accord to the facts. If one uses the past to interpret the present then your reading must be based on events that actually happened. This cannot be said for Mr. Luttwak's essay. The story he tells simply did not happen.
Luttwak's descriptions of the heqin policy's aim is basically correct. It was designed to corrupt the Xiongnu and slowly 'Sinicize' them. It was designed, through the power of Confucian family norms, to subordinate the Xiongnu ruler to Han Emperor.
What Luttwak neglects to mention is that the policy was a complete and utter failure.")
),
("https://scholars-stage.blogspot.com/2014/09/what-edward-luttwak-doesnt-know-about_6.html",
("What Edward Luttwak Doesn't Know About Ancient China (Or a Short History of Han-Xiongnu Relations), pt. 2"
, "Tanner Greer"
, "2014-10-06"
, ""
, "If the 'peace marriage' (heqin) system Luttwak describes did not do the Xiongnu in, what did?
...The logistics machine the Han created to defeat the Xiongnu is one of the marvels of the ancient world [3]. Each of the Han's campaigns was a feat worthy of Alexander the Great. But Alexander only pushed to India once. The Han launched these campaigns year after year for decades [4]. The sheer expanse of the conflict is staggering; Han armies ranged from Fergana to Manchuria, theaters 3,000 miles apart. Each campaign required the mobilization of tens of thousands of men and double the number of animals. Chang Chun-shu has tallied the numbers:
\"In the many campaigns in the Western regions (Hexi, Qiang, and Xiyu) and the Xiongnu land, the Han sent a total force of over 1.2 million cavalrymen, 800,000 foot soldiers, and 10.5 million men in support and logistic roles. The total area of lad seized in Hexi alone was 426,700 square kilometers. In developing this region the Han spent 100 billion in cash per year, compared to the regular annual government revenue of 12 billion. In the process the Han government moved from the interior over 1 million people to populate and develop the Hexi river. Thus the Han conquest of the land west of the Yellow River was the greatest expansion in Chinese history.\" [5]
The demands of the war forced the Han to restructure not only the Chinese state, but all of Chinese society. [6] The Han's willingness to radically restructure their society to meet the immense financial and logistic demands of an eighty year conflict is one of the central reasons they emerged victorious from it.
...The Han followed the same basic strategy. The aim of generals like Wei Qing and Huo Qubing was to kill every single man, woman and child they came across and by doing so instill such terror in their enemies that tribes would surrender en masse upon their arrival. By trapping the Xiongnu into one bloody slug match after another the Han forced them into a grinding war of attrition that favored the side with the larger population reserves. The Xiongnu were unprepared for such carnage in their own lands; within the first decade of the conflict the Han's sudden attacks forced the Xiongnu to retreat from their homeland in the Ordos to the steppes of northern Mongolia. Then came a sustained—and successful—effort to apply the same sort of pressure on the Xiongnu's allies and vassals in Turkestan and Fergana. By sacking oasis towns and massacring tribes to the east, the Han were able to terrorize the peoples of Turkestan into switching their allegiance to China or declare their independence from the Xiongnu.
The Xiongnu were left isolated north of the Orkhorn. Under constant military pressure and cut off from the goods they had always extorted from agrarian peoples in China and Turkestan, the Xiongnu political elite began to fracture. A series of succession crises and weak leaders ensued; by 58 BC the Xiongnu's domain had fallen into open civil war. It was one of the aspiring claimants to the title of Chanyu that this conflict produced who traveled to Chang'an, accepted the Han's suzerainty, and ended eighty years of war between the Han and the Xiongnu [8].
How did the Chinese transform an enemy whose realm stretched thousands of miles across Inner Asia into a mere tributary vassal? They did it through flame and blood and terror. Any narrative of Han-Xiongnu relations that passes over these eighty years of grueling warfare is a distorted depiction of the times.")
),
("https://scholars-stage.blogspot.com/2014/03/smallpox-on-steppe.html",
("Smallpox on the Steppe"
, "Tanner Greer"
, "2014-03-08"
, ""
, "...The Manchus, before the founding of the Qing, also rarely encountered smallpox, but they knew of its danger. Mongols and Manchus who had not been exposed to the disease were exempted from coming to Beijing to receive titles of succession. The main response of the Mongols and Manchus to those who did fall ill was quarantine. Li Xinheng commented that if anyone in a tribe caught smallpox, his relatives abandoned him in a cave or distant grassland. 70 to 80 percent of those infected died. The German traveler Peter Simon Pallas, who visited the Mongols three times front 1768 to I771, commented that smallpox was the only disease they greatly feared. It occurred very seldom, but spread rapidly when it struck: \"If someone catches it, they abandon him in his tent; they only approach front the windward side to provide food. Children who catch it are sold to the Russians very cheaply.\" The Mongols whom Pallas visited lived far from the Chinese border, but they knew well that smallpox was highly contagious and nearly fatal.
The Chinese discovery of variolation—a method of inoculation—was of great aid in reducing the severity of attacks. The Kangxi emperor himself was selected as heir in part because he had survived the disease in childhood; his father had died of it. In 1687 he inaugurated regular inoculation of the royal family, and his successor extended mandatory inoculation to all Manchu children. The Manchus adopted this Chinese medical practice in order to protect themselves against the virulent strains that were absent from the steppe. Only Manchus who had survived the disease were allowed to be sent to the Mongolian steppe. Mongols close to the Manchu and Chinese border gradually grew immune, but those farther away suffered great losses in the nineteenth century when Chinese penetration increased. [1]
... For several millenia historians have tried to explain the generally superior strength and endurance of steppe warriors, often focusing on the demands of life in the saddle or the nomads' protein-rich diets as the explanation for their vitality. A more powerful explanation may be the absence of the debilitating and deadly diseases of settled life among the peoples of the steppe.")
),
("https://scholars-stage.blogspot.com/2014/04/meditations-on-maoism-ye-fus-hard-road.html",
("Meditations on Maoism—Ye Fu's Hard Road Home"
, "Tanner Greer"
, "2014-04-14"
, ""
, "Americans-and particularly American conservatives-are sometimes accused of failing to confront their country's past honestly. Ye Fu's challenge—and in many respects all of China's—was not honestly facing his past, but simply finding it. Ye Fu was born the great grandson of a ranking Nationalist commander, the grand son of a landlord, and the son of two parents who zealously joined the revolution only to be discarded by later 'struggles of the Proletariat'. Ye Fu was only dimly aware of this heritage growing up. It was not until his father's funeral, when he first stepped foot on his ancestral lands, that he had either the chance or a reason to find the truth of his family's past. This became a quest that drove and consumed him and is a recurring motif that unites his most poignant essays.
...Thus the true details of his father's life and heritage were revealed: a grandfather who had climbed from the peasantdom of his birth to the hallowed class of landlord only a few years before the revolution overtook the village (he earned the title by being the only one in the village rich enough to employ a single field hand); a son who zealously hunted down landlords for the Party, unaware that his own family 50 miles to the east suffered the same persecution he so earnestly delivered; the suicide of his father and the destruction of the clan's eldest generation in its entirety, both brothers and wives, within a single night.
\"Hundreds of millions of lives were shoveled into the trenches of the 20th century\", Ye Fu reflects. [4] Historians estimate that the death toll of these land reform campaigns is in the range of two to three million. [5] But for Ye Fu those ditches are not those of the nameless millions. These were ditches dug by his father and filled by his grandfather. The tragedies of the 20th century are his tragedies. He was born from the ditches—though he would not discover this gruesome truth until he was a grown man.
He who reads Ye Fu's meditations on these mournful roots leaves with the strong—but unexpected—impression that the true tragedy of modern Chinese history is not found in its colossal death toll. For Ye Fu the real tragedy is what all these dead represented. The first to die were those most committed to the old order. They were the upholders of traditional propriety, keepers of the ancestral shrine, and symbols of basic human decency. These men and women often lived far below their ideals, profiting from a system rightly seen as exploitative, but as long they lived so did the ideal. Their deaths meant the destruction of their entire society. With them passed old structures of power and control, but also the old values and traditions these social arrangements had embodied and enshrined. The life defined by decorum, trust, filial piety, and kindness lost its place as the ideal of Chinese civilization, replaced by a new model that honored cruelty, deception, and revolutionary ardor.")
),
("https://scholars-stage.blogspot.com/2019/01/reflections-on-chinas-stalinist.html",
("Reflections on China's Stalinist Heritage I: A Tyrant's Toolkit"
, "Tanner Greer"
, "2019-01-17"
, ""
, "One of the extraordinary things about reading Mao's speeches from this period is the fluidity of who was considered an ally and who was considered an enemy. Mao framed his campaigns as a struggle between \"the people\" and \"the enemy,\" but who fit into each group differed drastically based off of the Party's perceptions of who was a credible threat to The Cause and who was not. As Mao put it:
To understand these two different types of contradictions correctly, we must first be clear on what is meant by \"the people\" and what is meant by \"the enemy\". The concept of \"the people\" varies in content in different countries and in different periods of history in a given country. Take our own country for example. During the War of Resistance Against Japan, all those classes, strata and social groups opposing Japanese aggression came within the category of the people, while the Japanese imperialists, their Chinese collaborators and the pro-Japanese elements were all enemies of the people. During the War of Liberation, the U.S. imperialists and their running dogs—the bureaucrat-capitalists, the landlords and the Kuomintang reactionaries who represented these two classes—were the enemies of the people, while the other classes, strata and social groups, which opposed them, all came within the category of the people. At the present stage, the period of building socialism, the classes, strata and social groups which favour, support and work for the cause of socialist construction all come within the category of the people, while the social forces and groups which resist the socialist revolution and are hostile to or sabotage socialist construction are all enemies of the people.[5]
Thus a particular group could at one point be an honored part of \"the people,\" at another point an ally in a \"united front,\" and later a despised \"enemy\" of the regime. How the regime treated you depended very much on how threatening Party leaders believed you might be to the regime and its cause.
Today The Cause has flipped—officially—from socialist revolution to national rejuvenation. The Party works under the same schema but has shifted the \"people\" that Mao identified with specific economic classes to the nation at large.[6] Mass mobilization campaigns have been retired. But struggle and united front campaigns have not. Xi's great corruption purge, the Uyghur labor camps of Xinjiang, the attack on Christians across China—these all follow the same methods for crushing and coercing \"enemies\" developed by Mao and the Party in the early '40s. \"One Country, Two Systems,\" interference campaigns in the Chinese diaspora, the guided, gilded tours given to Musk and his ilk—these all follow the same methods for corrupting and controlling \"allies\" developed by Mao and the Party that same decade. The tools have never changed. The only thing that has changed is the Party's assessment of who is an \"enemy\" and who is part of the \"people.\"
There is one threat, however, that the Communist legacy has poorly prepared the Party to face. Stalin and Mao conceived of their projects in cultural terms—they were not just attempting to stamp out dangerous people, but dangerous ideas. To that end both Stalin and Mao cut their countries off from the world they had no control over. If your end goal is socialist revolution this might be tenable. But if your end goal is national rejuvenation—that is, a future where China sits at the top of a global order, more wealthy and powerful than any other—then engagement with the outside world must be had. It means foreigners coming to China in great numbers, and Chinese going abroad in numbers no smaller. It means a much more accurate conception of the way the rest of the world works among the minds of the Chinese people. It means contemplating paths for China that do not involve being ruled by a dictatorial party-state.
This tension lies at the root of the Party's problems with the West. Countries like America threaten the Party with their mere existence. Consider what these countries do: they allow dissidents from authoritarian powers shelter. Their societies spawn (even when official government policy is neutral on the question) movement after movement devoted to spreading Western ideals and ideas to other lands and peoples. They are living proof that a country does not need a one-party state to become powerful and wealthy. These things pose a threat to the Communist Party of China. The Party itself is the first to admit it. [7]")
),
("https://scholars-stage.blogspot.com/2019/03/reflections-on-chinas-stalinist.html",
("Reflections on China's Stalinist Heritage II: Just How Totalitarian is Modern China?"
, "Tanner Greer"
, "2019-03-07"
, ""
,"Under the Khmer Rouge, making love was an explicitly political act. Marriage was a political decision. Refusing to sleep with your husband was an act of political rebellion. The first claim of the totalitarian is that everything is political.
In my view, a totalitarian system must meet two minimum requirements:
- In this system all human action is considered political action.
- The system is ruled by a Party which claims commanding authority to direct all political action—and thus all human action—for its cause.
The great tragedies of 20th century history occurred as the totalitarian leaders attempted to translate their claim of authority over all human action into actual control over the same.
This view of totalitarian society crystallized in my mind some years ago, when I first read Liang Heng's memoir of his youthful escapades as a Red Guard in the Cultural Revolution. A professor had asked me to review it. In that brief review I noted:
In Mao's China the personal was always political. And not just the personal—everything anyone did was political. Maoism was a political ideology that asked its members to give everything they were, had, and did to the socialist cause. This intellectual framework implies that everything one does should be layered with political meaning. A child's prank, a lover's kiss, and a friend's embrace were all political acts. The clothes one wore, the way one walked, the letters one wrote, and the words one spoke all had political valence. It was with this in mind Liang Shan warned: \"Never give your opinion on anything, even if you're asked directly\" (76).
Such caution is inevitable in a world where there is no distinction between the personal and the political. Politics is the division of power, politicking the contest for it. In a system where the most intimate and private actions have political meaning, these actions will be used by those who seek power. These naked contests for control leave no room for good and evil—good becomes what those with power declare it. \"One day you are red, one day you are black, and one day you are red again\" (76), Liang Shan instructed, and he was correct. This struggle stretched from factions warring within the walls of Zhongnanhai to the village black class child currying for favor.
The problem is not competition: that is an ingrained aspect of human life. The special tragedy of the Maoist system was that it spared nothing from the pursuit of power. There was no aspect of life that could be cordoned off as a refuge from the storm. [2]
")
),
("https://scholars-stage.blogspot.com/2017/07/everything-is-worse-in-china.html",
("Everything is Worse in China"
, "Tanner Greer"
, "2017-07-19"
, ""
, "Here I will just share one of my strongest reactions to the book—a thought that occurred again and again as I drifted through its pages. Esolen presents a swarm of maladies sickening American society, ranging from a generation of children suffocated by helicopter parenting to a massive state bureaucracy openly hostile too virtuous living. My reaction to each of his carefully drawn portraits was the same: this problem is even worse in China.
Are you worried about political correctness gone awry, weaponized by mediocrities to defame the worthy, suffocating truth, holding honest inquiry hostage through fear and terror? That problem is worse in China.
Do you lament the loss of beauty in public life? Its loss as a cherished ideal of not just art and oratory but in the building of homes, chapels, bridges, and buildings? Its disappearance in the comings-and-goings of everyday life? That problem is worse in China.Do you detest a rich, secluded, and self-satisfied cultural elite that despises, distrusts, and derides the uneducated and unwashed masses not lucky enough to live in one of their chosen urban hubs? That problem is worse in China. Are you sickened by crass materialism? Wealth chased, gained, and wasted for nothing more than vain display? Are you oppressed by the sight of children denied the joys of childhood, guided from one carefully structured resume-builder to the next by parents eternally hovering over their shoulders? Do you dread a hulking, bureaucratized leviathan, unaccountable to the people it serves, and so captured by special interests that even political leaders cannot control it? Are you worried by a despotic national government that plays king-maker in the economic sphere and crushes all opposition to its social programs into the dust? Do you fear a culture actively hostile to the free exercise of religion? Hostility that not only permeates through every layer of society, but is backed by the awesome power of the state?
These too are all worse in China.
...All of this should lighten the tone of gloom and doom that pervades the traditionalist critique of modern America. The reference point of these writers is the American (or less usually, the European) past. Look instead at the present! It could be so much worse for those of our ilk. In some countries, it is.")
),
("https://scholars-stage.blogspot.com/2019/05/the-utterly-dysfunctional-belt-and-road.html",
("The Utterly Dysfunctional Belt and Road"
, "Tanner Greer"
, "2019-05-08"
, ""
, "The always excellent Stella Zhang directed me to a newish paper by political scientists Lee Jones and Zeng Jinhan on the domestic politics of China's Belt and Road. Long term readers will remember that I am bearish on Xi's grand dream. Here is how I described the central problems with the scheme for Foreign Policy:
There is also a gap between how BRI projects are supposed to be chosen and how they actually have been selected. Xi and other party leaders have characterized BRI investment in Eurasia as following along defined \"economic corridors\" that would directly connect China to markets and peoples in other parts of the continent. By these means the party hopes to channel capital into areas where it will have the largest long-term benefit and will make cumulative infrastructure improvements possible.
This has not happened: one analysis of 173 BRI projects concluded that with the exception of the China-Pakistan Economic Corridor (CPEC) \"there appears to be no significant relationship between corridor participation and project activity... [suggesting that] interest groups within and outside China are skewing President Xi's signature foreign policy vision.\"
This skew is an inevitable result of China's internal political system. BRI projects are not centrally directed. Instead, lower state bodies like provincial and regional governments have been tasked with developing their own BRI projects. The officials in charge of these projects have no incentive to approve financially sound investments: by the time any given project materializes, they will have been transferred elsewhere. BRI projects are shaped first and foremost by the political incentives their planners face in China: There is no better way to signal one's loyalty to Xi than by laboring for his favored foreign-policy initiative. From this perspective, the most important criteria for a project is how easily the BRI label can be slapped on to it.....
The problems China has had with the BRI stem from contradictions inherent in the ends party leaders envision for the initiative and the means they have supplied to reach them. BRI projects are chosen through a decentralized project-management system and then funded through concessional loans offered primarily by PRC policy banks. This is a recipe for cost escalation and corruption. In countries like Cambodia, a one-party state ruled by autocrats, this state of affairs is viable, for there is little chance that leaders will be held accountable for lining their pockets (or, more rarely, the coffers of their local communities) at the entire nation's expense. But most BRI countries are not Cambodia. In democracies this way of doing things is simply not sustainable, and in most BRI countries it is only so long before an angry opposition eager to pin their opponents with malfeasance comes to power, armed with the evidence of misplaced or exploitative projects. [1]
The key points to take away from my account is that the failures of the BRI seem to factor back to a few central points: first, that project selection is mostly driven by the priorities of folks working in SOEs, provincial governments, and a plethora of different policy banks. The central government in Beijing has difficulty directing their efforts. Secondly, that these people do not have a good understanding of the countries in which they are investing, and face little incentive to gain this understanding. This leads to the sort of corruption and 'predatory' funding that has given BRI its poisonous reputation in countries long exposed to it.
Jones and Zeng agree with this general picture, but provide a far more detailed account of what is happening 'behind the scenes' when BRI projects are chosen and funded. The process they describe is not unique to the Belt and Road. It starts as Communist high leadership paints bold words in the sky:
Foreign-policy steering happens through several important mechanisms. The first is top leaders' major speeches, which are usually kept vague to accommodate diverse interests and agendas. Rather than 'carefully-worked out grand strategies', they are typically 'platitudes, slogans, catchphrases, and generalities', offering 'atmospheric guidance' that others must then interpret and implement. Examples include: Deng's tao guang yang hui, whose meaning is 'debateable'; Hu's 'harmonious world'—'more of a narrative than a grand strategy'; and Xi's 'new type of great power relations.' As discussed below, Xi's vague 2013 remarks on the 'silk road economic belt' (SREB) and 'maritime silk road' (MSR) exemplify this tendency. [2]
But bold words are not policy. The Party often has difficulty transforming grand visions into detailed policy proposals. This is sometimes quite intentional—in a closed system like the People's Republic, it may be better to have politicos arguing over how to make the Core's vision possible, instead of whether the Core's vision is worth making possible in the first place.
")
),
("https://scholars-stage.blogspot.com/2019/04/the-inner-life-of-chinese-teenagers.html",
("The Inner Life of Chinese Teenagers"
, "Tanner Greer"
, "2019-04-19"
, ""
, "The second point probably deserves more space than I was able to give in the LA Review of Books. Consider, for a moment, the typical schedule of a Beijing teenager:
She will (depending on the length of her morning commute) wake up somewhere between 5:30 and 7:00 AM. She must be in her seat by 7:45, 15 minutes before classes start. With bathroom breaks and gym class excepted, she will not leave that room until the 12:00 lunch hour and will return to the same spot after lunch is ended for another four hours of instruction. Depending on whether she has after-school tests that day, she will be released from her classroom sometime between 4:10 and 4:40. She then has one hour to get a start on her homework, eat, and travel to the evening cram school her parents have enrolled her in. Math, English, Classical Chinese—there are cram schools for every topic on the gaokao. On most days of the week she will be there studying from 6:00 to 9:00 PM (if the family has the money, she will spend another six hours at these after-school schools on Saturday and Sunday mornings). Our teenager will probably arrive home somewhere around 10:00 PM, giving her just enough time to spend two or three hours on that day's homework before she goes to bed. Rinse and repeat, day in and day out, for six years. The strain does not abate until she has defeated—or has been defeated by—the gaokao.
This is well known, but I think the wrong aspects of this experience are emphasized. Most outsiders look at this and think: see how much pressure these Chinese kids are under. I look and think: how little privacy and independence these Chinese kids are given!
To put this another way: Teenage demands for personal space are hardly unique to China. What makes China distinctive is the difficulty its teenagers have securing this goal. Chinese family life is hemmed in narrow bounds. The urban apartments that even well-off Chinese call their homes are tiny and crowded. Few have more than two bedrooms. Teenagers are often forced to share their bedroom with a grandparent. So small was the apartment of one 16-year-old I interviewed that she slept, without apparent complaint, in the same bed as her parents for her entire first year of high school. Where can a teenager like her go, what door could she slam, when she was angry with her family? Within the walls of her home there was no escape from the parental gaze.
A Chinese teen has few better options outside her home. No middle-class Chinese teenager has a job. None have cars. The few that have boyfriends or girlfriends go about it as discreetly as possible. Apart from the odd music lesson here or there, what Americans call \"extra-curricular activities\" are unknown. One a recent graduate of a prestigious international high school in Beijing once explained to me the confusion she felt when she was told she would need to excel at an after-school activity to be competitive in American university admissions:
\"In tenth grade our home room teacher told us that American universities cared a lot about the things we do outside of school, so from now on we would need to find time to 'cultivate a hobby.' I remember right after he left the girl sitting at my right turned to me and whispered, 'I don't know how to cultivate a hobby. Do you?'\"")
),
("https://scholars-stage.blogspot.com/2013/02/ominous-parallels-what-antebellum.html",
("Ominous Parallels: What Antebellum America Can Teach Us About Our Modern Political Regime"
, "Tanner Greer"
, "2013-02-26"
, ""
, "Many people point to the hyper-partisanship of national Democratic and Republican parties as the greatest challenge facing 21st century America. When seen through the lens of another vapidly partisan political system—that of Jacksonian America—we see that the real danger is not noisy partisanship, but the iniquity it hides: for them it was slavery; for us, plutarchy.
...As in the antebellum, today's hyperpartisanship has its uses. The issues are real enough, and the cultural divide between each party's demographic \"base\" is wide. Politicians take advantage of this with over-the-top rhetoric, turning all issues into a cultural crusade against the radicalism of the progressive left or the bigotry of entrenched conservatism. The accuracy of these attacks is unimportant. The antebellum party system allowed Southerners to define themselves as 'Whigs' or 'Democrats' instead of 'slavers'. The current system serves its purpose just as well, allowing plutarchs to define themselves not in terms of power or privilege, but as part of a culturally cohesive group that represents 'real' America. With partisan issues taking the fore, politicians, lobbyists, and corporate big wigs can plunder the American economy and strip American citizens of their liberties in a decidedly bipartisan fashion. [9] And thus the greatest structural faultline in America's body-politic and the most dangerous challenge to the integrity of her republican institutions and the liberties of her citizenry continues onward without public comment. And all of this without a gag rule.
If the comparison of the antebellum Republic's political regime with its ailing modern descendent seems a bit chilling—well, it is. The last time America's sins broke through the partisan politics designed to hide them the result was the most destructive war of her history. It is an ominous precedent.")
),
("https://scholars-stage.blogspot.com/2015/09/shakespeare-in-american-politics.html",
("Shakespeare in American Politics"
, "Tanner Greer"
, "2015-09-30"
, ""
, "...A good place to start is with the Webster-Hayne debate of 1830. Of all American oratory, only the Lincoln-Douglass debates can claim greater fame than the debate Daniel Webster and Robert Hayne held on the antebellum Senate floor. At that time there was a resolution before the Senate calling for all new federal land surveys to be postponed until all of the existing land already surveyed was sold. This struck the ire of the westerners, who pushed for federal land to be given to new settlers without charge or delay...These allusions to Shakespeare only occupy a normal portion of the two men's debate—no more than a few paragraphs out of ninety or so pages of text. Nevertheless, the use of Macbeth's script in the debate is telling. Neither Webster nor Hayne thought it was a waste of their time to debate the finer points of Shakespeare's plays in the halls of the Senate. The reader senses that Webster, in particular, did so in a positively gleeful fashion.
What has happened here? How have we gone from long discussions of Shakespearean drama on the senate floor to the shallow repetition of disembodied sentence fragments? The answers to this question tell us much about the American body politic:
1) The decline of public speaking as a vital part of American culture. Oratory is something of a lost art in modern America. It is hard to imagine just how vital it was to public life for most of America's history. In Webster's day public speaking was a central part of entertainment, education, civic life, and religious practice. He was elected in the midst of the 2nd Great Awakening, when American religious life was dominated by camp meetings and church members were expected to preach and testify one to another. It was a time when every township had a lyceum at its center, and intellectual life was dominated by those who traveled the lyceum circuit. Collections of speeches like The Columbian Orator were the most common type of schoolbook in the antebellum era, while most American men actively participated in town assemblies and party caucuses. The mastery of proper political rhetoric was an essential social skill.
Add all this together and you are left with a population that found immense pleasure in listening to, reenacting, and reading the speeches of others. It was a prized art, and when masters like Webster or Lincoln displayed their talents, people flocked together to listen to them. There was thus a great deal of patience for the sort of rhetorical flourish inherit in the long discussions of Shakespeare seen above. Today's Americans will not sit still and listen to a political speech for longer than ten minutes. The medium through which politicians communicate to the masses really doesn't let them. Radio shows and news channels rely on the soundbite. If a politician's message cannot be squeezed into a seven second slot it will not be heard.")
),
("https://scholars-stage.blogspot.com/2015/10/awareness-vs-action-two-modes-of.html",
("Awareness vs. Action: Two Modes of Protest in American History"
, "Tanner Greer"
, "2015-10-07"
, ""
, "...Daniel Walker Howe devotes several pages to the origins of the [Temperance] movement in his excellent book What God Hath Wrought: The Transformation of America, 1814–1848. It is worth quoting from them at length:
Americans in the early nineteenth century quaffed alcohol in prodigious quantities. In 1825, the average American over fifteen years of age consumed seven gallons of alcohol a year, mostly in the form of whiskey and hard cider. (The corresponding figure at the start of the twenty-first century was less than two gallons, most of it from beer and wine.) Workers typically took a midmorning break and a mid-afternoon break, both accompanied by alcohol, as well as liquor with every meal. To entertain guests meant to ply them with several kinds of alcohol until some fell down. All social classes drank heavily; college students, journeyman printers, agricultural laborers, and canal-diggers were especially notorious. Schoolchildren might face an inebriated teacher in the classroom. Although socially tolerated, drunkenness frequently generated violence, especially domestic violence, and other illegal behavior. In such a society, intemperance represented a serious issue of public health, comparable to the problems of drug abuse experienced in later generations.
Making temperance a Christian cause constituted an innovation, for traditional Christianity had not discouraged drinking. Indeed, Beecher recalled, ministerial conferences during his youth had been occasions for heavy convivial drinking. Unlike a later generation of crusaders, Beecher never thought the legal prohibition of alcohol a practical solution; he relied purely on changing public attitudes. This was no mean feat. To take stand against the strong social pressures to drink took real courage, especially for young men. To help them, temperance workers paid reformed alcoholics to go on speaking tours, published temperance tracts, put on temperance plays, and drove the \"water wagon\" through towns encouraging converts to jump on. Publicists and organizers like Beecher struck a nerve with the public. The temperance cause resonated among people in all walks of life, rural and urban, white and black. Although it began in the Northeast, temperance reached the South and West and exerted powerful and lasting influence there. At first the temperance advocates restricted themselves to encouraging moderation (hence the name \"temperance\"); in this phase they condemned only distilled liquors, not beer and wine. At the grassroots level, however, it became apparent that total abstinence made a more effective appeal. Beecher endorsed this shift in Six Sermons on Intemperance (1825). Those who signed a temperance pledge were encouraged to put a T after their names if willing to take the extra step of pledging total abstinence; from this derives our word \"teetotaler.\"
The campaign to alter age old habits and attitudes proved amazingly successful: consumption of alcohol, especially of hard liquor, declined steadily and dramatically after 1830, falling to 1.8 gallons per person over fifteen by the late 1840s. [2]
A few things to note about this account: temperance societies were organized and worked at the level of towns, congregations, families, and individuals, not entire states or nations. The information they passed along was not intended to make people aware of the danger of drinking, but to inspire or scare them into acting on this knowledge. They created communities who could help individuals who were struggling to do this. They were most successful when they secured individual commitments to action.
It was also incredibly successful.
This became the standard template for American civic associations until the late 19th century.")
),
("https://scholars-stage.blogspot.com/2019/06/passages-i-highlighted-in-my-copy-of.html",
("Passages I Highlighted in My Copy of Only Yesterday: An Informal History of the 1920s"
, "Tanner Greer"
, "2019-06-24"
, ""
, "Last week's post, \"If You Were to Write a History of 21st Century America, What Would It Look Like?\", asked what a 21st century version of Frederick Lewis Allen's Only Yesterday: An Informal History of the 1920s might look like. Here is how I described the book in that post:
There are many things to love about this book. Allen wrote his history of the 1920's in a jaunty, breezy style. When you pick his book up it is hard to put it down. Allen's tone is fair, his judgements sharp, and prose delectably entertaining. The most notable thing about this history of the 1920s, however, is its publication date: Allen wrote the book in 1930. He saw it published in 1931.
I often wish Allen had more imitators. Allen's book shines as a social history. The genius of writing such a history directly after the events took place is that the historian can narrate not just what happened in a period, but what it felt like to live through it. Names have not receded into history; the little things of daily existence are still remembered, and often still in use. Judgements of past events have not been too clouded by the downstream effects they had three or four decades down the line. There is an immediacy to Only Yesterday that I have never found in any other work of history (though I have found it in several works of fiction).
While Allen gives due coverage to economic and political affairs (the League of Nations debates, the Teapot Dome scandal, and the crash of '29 each get their own chapter length narrations), the majority of Allen's book is what we would today call \"social history.\" Allen spends about equal time describing the fads for crossword puzzles and mahjong (yes, you read that last one right) as he does the entire administration of Calvin Coolidge..."
)
),
("https://scholars-stage.blogspot.com/2019/04/on-quests-for-transcendence.html",
("Questing for Transcendence"
, "Tanner Greer"
, "2019-04-29"
, ""
, "Will Wilkinson explored one possibility in an essay he wrote a few years ago on American country music. Wilkinson begins with the observation that American conservatives (i.e., the consumers of country music) tend to be low on \"openess\" in the Big-5 personality scale. Folks who rate high on openness are the sort attracted to novelty: world travels, new drugs, and so forth. Country music, he suggests, captures the emotional lives of a different group of people:
Emotional highlights of the low-openness life are going to be the type celebrated in \"One Boy, One Girl\": the moment of falling in love with \"the one,\" the wedding day, the birth one's children (though I guess the song is about a surprising ultrasound). More generally, country music comes again and again to the marvel of advancing through life's stations, and finds delight in experiencing traditional familial and social relationships from both sides. Once I was a girl with a mother, now I'm a mother with a girl. My parents took care of me, and now I take care of them. I was once a teenage boy threatened by a girl's gun-loving father, now I'm a gun-loving father threatening my girl's teenage boy. Etc. And country is full of assurances that the pleasures of simple, rooted, small-town, lives of faith are deeper and more abiding than the alternatives.
My conjecture, then, is that country music functions in part to reinforce in low-openness individuals the idea that life's most powerful, meaningful emotional experiences are precisely those to which conservative personalities living conventional lives are most likely to have access. And it functions as a device to coordinate members of conservative-minded communities on the incomparable emotional weight of traditional milestone experiences....
But why would you want your kids to grow up with the same way of life as you and your grandparents? My best guess (and let me stress guess) is that those low in openness depend emotionally on a sense of enchantment of the everyday and the profundity of ritual. Even a little change, like your kids playing with different toys than you did, comes as a small reminder of the instability of life over generations and the contingency of our emotional attachments. This is a reminder low-openness conservatives would prefer to avoid, if possible. What high-openness liberals feel as mere nostalgia, low-openness conservatives feel as the baseline emotional tone of a recognizably decent life. If your kids don't experience the same meaningful things in the same same way that you experienced them, then it may seem that their lives will be deprived of meaning, which would be tragic. And even if you're able to see that your kids will find plenty of meaning, but in different things and in different ways, you might well worry about the possibility of ever really understanding and relating to them. The inability to bond over profound common experience would itself constitute a grave loss of meaning for both generations. So when the culture redefines a major life milestone, such as marriage, it trivializes one's own milestone experience by imbuing it was a sense of contingency, threatens to deprive one's children of the same experience, and thus threatens to make the generations strangers to one another. And what kind of monster would want that?
Country music is a bulwark against cultural change, a reminder that \"what you see is what you get,\" a means of keeping the charge of enchantment in \"the little things\" that make up the texture of the every day, and a way of literally broadcasting the emotional and cultural centrality of the conventional big-ticket experiences that make a life a life.[3]
...Yet there is one segment of society that seems to get it. In the years since my [Mormon missionary] service, I have been surprised to find that the one group of people who consistently understands my experience are soldiers....both many ex-missionaries (known as \"RMs\" or \"Return Missionaries\" in Mormon lingo) and many veterans have such trouble adapting to life when they return to their homes. This comparison occurred to me first several years ago, when I read a Facebook comment left by a man who had served as a Marine mechanic in Afghanistan...I did not save the comment at the time, but I remember it well enough to reproduce a paraphrase here:
\"I do not know if I want to live any more. I served in Afghanistan from [various dates of various deployments] and am now working as a salesman for [a prominent American company]. I despise this world I am in now—everything is so selfish and so self centered. In Afghanistan every single decision I made had a purpose; every single thing I did was for something bigger than myself. Everything I did, I did to save lives. Every deed helped accomplish our mission. Here in America no one does anything except for themselves. We work to earn a buck—what is the point to living like this? There is not a day that goes by that I don't wish I was back in that hellhole. There what I did mattered. Here it is all meaningless.\"
")
),
("https://scholars-stage.blogspot.com/2016/01/america-will-always-fail-at-regional.html",
("America Will Always Fail At Regional Expertise"
, "Tanner Greer"
, "2016-01-"
, ""
, "I have argued before that any potential American foreign policy or 'grand strategy' that requires statesmen with a nuanced understanding of a foreign region's cultures, politics, and languages to implement it is doomed to fail. Regional acumen is a rare trait, and one I greatly admire. But it is rare for a reason. Regional acumen just does not scale—or at least, Americans do not know how to scale it. I have said this before. But it was reinforced tonight when I stumbled—quite by accident—across this old New York Times Magazine personal by Lydia Kiesling. In it she describes her experience learning Uzbek with a FLAS grant from the Department of Education.
...This article gets to the heart of why America will always lack the kind of language and area expertise needed to succeed in the kinds of things the American people (or American leaders) often demand the United States government do. Uzbek is an obscure language. But it is an obscure language at the center of the national security concerns that have bedeviled the United States over the last decade and a half. To give a brief picture:
- There are about three million Uzbeks who live in Afghanistan. Uzbeks were an essential part of the Northern Alliance's resistance against the Taliban, and Uzbek leaders became an important part of the government established by NATO forces once the Taliban was driven from power. This is still true. Afghanistan's current vice-president, Abdul Rashid Dostum, is an Uzbek.
- Uzbekistan is the central hub of central Asia. One of the greatest defeats of our Afghan campaign happened not on the battlefield, but at the diplomats' table. Uzbekistan's decision to withdraw American basing and supply rights was nothing short of a disaster, forcing the United States to be even more dependent on Pakistan (our true enemy in the region) for logistic support.
- Uzbek and Uyghur are a hair's breadth away from mutually intelligible. Xinjiang's low intensity Uyghur insurgency is he single greatest security concern of China, America's greatest rival.
This is a language that matters. What happens to the woman who spent a year of her life studying it? She was rejected from the CIA (or wherever) on background technicalities, and has not used her language since. Or to be more precise, she has used it twice. Twice in four years. Twice.
This gets to the heart of America's problem with regional acumen. Area expertise simply doesn't pay. You may count the number of private sector jobs currently on the market that demand Uzbek fluency on two hands. And even if there were a multitude of jobs that required proficiency in Uzbek and English, there are undoubtedly several hundred—perhaps several thousand—Uzbekistanis who speak English better than Ms. Kiesling speaks Uzbek, and who will work for less pay to boot.
")
),
("https://scholars-stage.blogspot.com/2015/02/the-education-of-american-strategist.html",
("American Policy Makers Do Not Read Books"
, "Tanner Greer"
, "2015-02-18"
, ""
, "If the American strategist of 2015 has a deep base of historical, cultural, and scientific knowledge to draw on to guide the decisions he makes this is because he acquired this knowledge base before he was a senior policy maker. You can actually see hints of this in the survey data—Avey and Desch asked policy makers to list the living international relations scholars they thought had the greatest influence on actual policy making. Along with scholars-turned-officials (e.g. Henry Kissinger, Zbigniew Brzezinski, Anne-Marie Slaughter) and public intellectuals (e.g. Francis Fukuyama, Fareed Zakaria) were a list of men whose scholarly apogee was twenty to thirty years ago, back when our policy makers were undergrads! (Funnily enough many of these men—Samuel Huntington, Albert Wohlstetter, Hans Morgenthau—are not only past their scholarly prime, but are no longer alive!) Those who rose to prominence after 1995 barely register. [3]
One of the lessons we can draw from this is that the books and material we expect American students to read and master in the early stages of their life will have an outsized influence on the knowledge they will possess in their old age. Today's strategists survive off of what they learned when they were in school forty years ago. [4] Absent dramatic changes in the life style of government officials or unforeseen technological developments, the policy-makers crafting strategy in 2040 will be working off of the knowledge base they are building from the books they are reading right now.")
),
("https://scholars-stage.blogspot.com/2018/03/you-dont-have-people.html",
("You Do Not Have the People"
, "Tanner Greer"
, "2018-03-"
, ""
, "These numbers are taken from a November NBC News/Gen Forward poll, a survey that questions 18–35 year olds across the nation on the political issues of the day. Respondents are asked to list what they believe are the three most important issues facing America. [3] There are a lot of interesting things one can say about this data, but for our purposes here I would focus your attention on the two rows labeled \"foreign policy\" and \"military strength.\" There is one big thing you will notice about these two figures: they are miniscule. Respondents are largely satisfied with America's place in the world. In their minds, police brutality, education, crime, taxes, racism, the economy, immigration, climate change, health care, gun control and the national budget are all more critical problems than anything involving foreign affairs.
Millennials do not stand in for all of America. Older generations care more for foreign policy than the Millennial and Generation Z cohorts do, though other polls suggest that their priorities also lie in the domestic sphere. But I focus in on this group for a reason: the opinions of this generation will have an outsized influence on our defense policies. In the case of war, these are the people who will actually be called to sacrifice their time and lives for the sake of American interests. Their willingness to suffer for the sake of the public interest sets the upper bounds for what is militarily possible in a time of conflict. Their attitude in peace will be even more important. Armament programs are decade long affairs. Proper sized navies are generation-length projects. Great power rivalries take decades to unfold. Who will be responsible for maintaining this effort? These guys. The millennial generation is already the largest cohort in this republic's history (given current fertility rates there will likely be none larger). Were they not so politically desensitized, they would also already possess the power to decide most elections in the country. When the last of the boomers die out, by sheer power of numbers alone, these men and women will rule the roost. Their perception of America's role in the world, and the threats she faces, will determine America's future.
The take-away: more important than developing new weapon systems, devising new treaties, or crafting new strategies will be convincing the American people that they can and should bear the costs of doing any of that. Nothing is more important than winning the public opinion war. If we lose there, nothing else really matters.
... If we lived in an age when public trust in elites and the institutions they manned was stronger, many of the worries I voice could be dispensed with. That is simply not where we are at. Unfortunately, the Trump administration's disregard for public opinion on the Korea issue is but an extreme expression of a tendency that blights the entire field. We are uncomfortable with democratic accountability, unwilling to subject ourselves to public debate, and uninterested in the constraints public opinion and popular politics place on the policies we craft. This complacency is not excusable. It is not sustainable. We cannot defend the cause of freedom without the support of the people. To try and do this is to risk terrible disaster.")
),
("https://scholars-stage.blogspot.com/2018/07/what-cyber-war-will-look-like.html",
("What Cyber-War Will Look Like"
, "Tanner Greer"
, "2018-07-06"
, ""
, "In a report Cancian wrote for the Center for Strategic and International Studies on how great powers adapt to tactical and strategic surprise, Cancian sketched out twelve \"vignettes\" of potential technological or strategic shocks to make his abstract points a bit more concrete. Here is how Cancian imagines an \"asymmetric cyber-attack\" launched by the PRC against the United States Military:
The U.S. secretary of defense had wondered this past week when the other shoe would drop. Finally, it had, though the U.S. military would be unable to respond effectively for a while.
The scope and detail of the attack, not to mention its sheer audacity, had earned the grudging respect of the secretary. Years of worry about a possible Chinese \"Assassin's Mace\"—a silver bullet super-weapon capable of disabling key parts of the American military—turned out to be focused on the wrong thing.
The cyber attacks varied. Sailors stationed at the 7th Fleet's homeport in Japan awoke one day to find their financial accounts, and those of their dependents, empty. Checking, savings, retirement funds: simply gone. The Marines based on Okinawa were under virtual siege by the populace, whose simmering resentment at their presence had boiled over after a YouTube video posted under the account of a Marine stationed there had gone viral. The video featured a dozen Marines drunkenly gang-raping two teenaged Okinawan girls. The video was vivid, the girls' cries heart-wrenching the cheers of Marines sickening And all of it fake. The National Security Agency's initial analysis of the video had uncovered digital fingerprints showing that it was a computer-assisted lie, and could prove that the Marine's account under which it had been posted was hacked. But the damage had been done.
There was the commanding officer of Edwards Air Force Base whose Internet browser history had been posted on the squadron's Facebook page. His command turned on him as a pervert; his weak protestations that he had not visited most of the posted links could not counter his admission that he had, in fact, trafficked some of them. Lies mixed with the truth. Soldiers at Fort Sill were at each other's throats thanks to a series of text messages that allegedly unearthed an adultery ring on base.
The variations elsewhere were endless. Marines suddenly owed hundreds of thousands of dollars on credit lines they had never opened; sailors received death threats on their Twitter feeds; spouses and female service members had private pictures of themselves plastered across the Internet; older service members received notifications about cancerous conditions discovered in their latest physical.
Leadership was not exempt. Under the hashtag #PACOMMUSTGO a dozen women allegedly described harassment by the commander of Pacific command. Editorial writers demanded that, under the administration's \"zero tolerance\" policy, he step aside while Congress held hearings.
There was not an American service member or dependent whose life had not been digitally turned upside down. In response, the secretary had declared \"an operational pause,\" directing units to stand down until things were sorted out.
Then, China had made its move, flooding the South China Sea with its conventional forces, enforcing a sea and air identification zone there, and blockading Taiwan. But the secretary could only respond weakly with a few air patrols and diversions of ships already at sea. Word was coming in through back channels that the Taiwanese government, suddenly stripped of its most ardent defender, was already considering capitulation. [2]
")
),
("https://mbio.asm.org/content/3/2/e00036-12",
("The Black Queen Hypothesis: Evolution of Dependencies through Adaptive Gene Loss"
, "J. Jeffrey Morris, Richard E. Lenski, Erik R. Zinser"
, "2012-03-23"
, "10.1128/mBio.00036-12"
, "Reductive genomic evolution, driven by genetic drift, is common in endosymbiotic bacteria. Genome reduction is less common in free-living organisms, but it has occurred in the numerically dominant open-ocean bacterioplankton Prochlorococcus and “Candidatus Pelagibacter,” and in these cases the reduction appears to be driven by natural selection rather than drift. Gene loss in free-living organisms may leave them dependent on cooccurring microbes for lost metabolic functions. We present the Black Queen Hypothesis (BQH), a novel theory of reductive evolution that explains how selection leads to such dependencies; its name refers to the queen of spades in the game Hearts, where the usual strategy is to avoid taking this card. Gene loss can provide a selective advantage by conserving an organism’s limiting resources, provided the gene’s function is dispensable. Many vital genetic functions are leaky, thereby unavoidably producing public goods that are available to the entire community. Such leaky functions are thus dispensable for individuals, provided they are not lost entirely from the community. The BQH predicts that the loss of a costly, leaky function is selectively favored at the individual level and will proceed until the production of public goods is just sufficient to support the equilibrium community; at that point, the benefit of any further loss would be offset by the cost. Evolution in accordance with the BQH thus generates “beneficiaries” of reduced genomic content that are dependent on leaky “helpers,” and it may explain the observed nonuniversality of prototrophy, stress resistance, and other cellular functions in the microbial world.")
)
, ("https://papers.tinbergen.nl/19059.pdf",
("Cannabis Prices on the Dark Web"
, "Jakub Cerveny, Jan C. van Ours"
, "2019-08-13"
, ""
, "This paper examines prices of cannabis sold over the anonymous internet marketplace AlphaBay. We analyze cannabis prices of 500 listings from about 140 sellers, originating from 18 countries. We find that both listing characteristics and country characteristics matter. Cannabis prices are lower if sold in larger quantities, so there is a clear quantity discount. Cannabis prices increase with perceived quality. Cannabis prices are also higher when the seller is from a country with a higher GDP per capita or higher electricity prices. The internet based cannabis market seems to be characterized by monopolistic competition where many sellers offer differentiated products with quality variation causing a dispersion of cannabis prices and sellers have some control over the cannabis prices.")
)
, ("/docs/modafinil/2019-kredlow.pdf",
("The Efficacy of Modafinil as a Cognitive Enhancer: A Systematic Review and Meta-Analysis"
, "M. Alexandra Kredlow, Ani Keshishian, Sarah Oppenheimer, Michael W. Otto"
, "2019-08-19"
, "10.1097/JCP.0000000000001085"
, "Background: Animal models and human studies have identified the potential of modafinil as a cognitive enhancing agent, independent of its effects on promoting wakefulness in sleep-deprived samples. Given that single-dose applications of other putative memory enhancers (eg, D-cycloserine, yohimbine, and methylene blue) have shown success in enhancing clinical outcomes for anxiety-related disorders, we conducted a meta-analytic review examining the potential for single-dose effects for modafinil on cognitive functioning in non–sleep-deprived adults.
Methods: A total of 19 placebo-controlled trials that examined the effects of single-dose modafinil versus placebo on the cognitive domains of attention, executive functioning, memory, or processing speed were identified, allowing for the calculation of 67 cognitive domain–specific effect sizes.
Results: The overall positive effect of modafinil over placebo across all cognitive domains was small and significant (g = 0.10; 95% confidence interval, 0.05–0.15; p < 0.001). No significant differences between cognitive domains were found. Likewise, no significant moderation was found for modafinil dose (100 mg vs 200 mg) or for the populations studied (psychiatric vs nonpsychiatric).
Conclusions: In conclusion, the available evidence indicates only limited potential for modafinil to act as a cognitive enhancer outside sleep-deprived populations.
")
)
, ("https://www.nature.com/articles/s41467-019-11786-6",
("A critique of pure learning and what artificial neural networks can learn from animal brains"
, "Anthony M. Zador"
, "2019-08-21"
, "10.1038/s41467-019-11786-6"
, "Artificial neural networks (ANNs) have undergone a revolution, catalyzed by better supervised learning algorithms. However, in stark contrast to young animals (including humans), training such networks requires enormous numbers of labeled examples, leading to the belief that animals must rely instead mainly on unsupervised learning. Here we argue that most animal behavior is not the result of clever learning algorithms—supervised or unsupervised—but is encoded in the genome. Specifically, animals are born with highly structured brain connectivity, which enables them to learn very rapidly. Because the wiring diagram is far too complex to be specified explicitly in the genome, it must be compressed through a “genomic bottleneck”. The genomic bottleneck suggests a path toward ANNs capable of rapid learning.
...As the name implies, ANNs were invented in an attempt to build artificial systems based on computational principles used by the nervous system5. In what follows, we suggest that additional principles from neuroscience might accelerate the goal of achieving artificial mouse, and eventually human, intelligence. We argue that in contrast to ANNs, animals rely heavily on a combination of both learned and innate mechanisms. These innate processes arise through evolution, are encoded in the genome, and take the form of rules for wiring up the brain6. Specifically, we introduce the notion of the “genomic bottleneck”—the compression into the genome of whatever innate processes are captured by evolution—as a regularizing constraint on the rules for wiring up a brain. We discuss the implications of these observations for generating next-generation machine algorithms.
...In this view, supervised learning in ANNs should not be viewed as the analog of learning in animals. Instead, since most of the data that contribute an animal’s fitness are encoded by evolution into the genome, it would perhaps be just as accurate (or inaccurate) to rename it “supervised evolution.” Such a renaming would emphasize that “supervised learning” in ANNs is really recapitulating the extraction of statistical regularities that occurs in animals by both evolution and learning. In animals, there are two nested optimization processes: an outer “evolution” loop acting on a generational timescale, and an inner “learning” loop, which acts on the lifetime of a single individual. Supervised (artificial) evolution may be much faster than natural evolution, which succeeds only because it can benefit from the enormous amount of data represented by the life experiences of quadrillions of individuals over hundreds of millions of years.")
),
("https://blog.openai.com/better-language-models/"
, ("Better Language Models and Their Implications"
, "OpenAI"
, "February 14, 2019"
, ""
, "We’ve trained a large-scale unsupervised language model which generates coherent paragraphs of text, achieves state-of-the-art performance on many language modeling benchmarks, and performs rudimentary reading comprehension, machine translation, question answering, and summarization—all without task-specific training.")
),
("https://blog.openai.com/language-unsupervised/"
, ("Improving Language Understanding with Unsupervised Learning"
, "OpenAI"
, "June 11, 2018"
, ""
, "We’ve obtained state-of-the-art results on a suite of diverse language tasks with a scalable, task-agnostic system, which we’re also releasing. Our approach is a combination of two existing ideas: transformers and unsupervised pre-training. These results provide a convincing example that pairing supervised learning methods with unsupervised pre-training works very well; this is an idea that many have explored in the past, and we hope our result motivates further research into applying this idea on larger and more diverse datasets.")
),
("https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf"
, ("Language Models are Unsupervised Multitask Learners"
, "Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever"
, "2019"
, "radford2019language"
, "Natural language processing tasks, such as question answering, machine translation, reading comprehension, and summarization, are typically approached with supervised learning on taskspecific datasets. We demonstrate that language models begin to learn these tasks without any explicit supervision when trained on a new dataset of millions of webpages called WebText. When conditioned on a document plus questions, the answers generated by the language model reach 55 F1 on the CoQA dataset - matching or exceeding the performance of 3 out of 4 baseline systems without using the 127,000+ training examples. The capacity of the language model is essential to the success of zero-shot task transfer and increasing it improves performance in a log-linear fashion across tasks. Our largest model, GPT-2, is a 1.5B parameter Transformer that achieves state of the art results on 7 out of 8 tested language modeling datasets in a zero-shot setting but still underfits WebText. Samples from the model reflect these improvements and contain coherent paragraphs of text. These findings suggest a promising path towards building language processing systems which learn to perform tasks from their naturally occurring demonstrations.")
),
("https://paperswithcode.com/task/language-modelling"
, ("Language Modelling State-of-the-art leaderboards"
, "paperswithcode.com"
, ""
, ""
, "Language modeling is the task of predicting the next word or character in a document.")
),
("https://gpt2.apps.allenai.org/?text=Joel%20is"
, ("LM Explorer (alpha)"
, "Allen Institute For Artificial Intelligence"
, ""
, ""
, "This demonstration uses the public 345M 117M parameter OpenAI GPT-2 language model to generate sentences.
Enter some initial text and the model will generate the most likely next words. You can click on one of those words to choose it and continue or just keep typing. Click the left arrow at the bottom to undo your last choice.")
),
("https://nv-adlr.github.io/MegatronLM"
, ("MegatronLM: Training Billion+ Parameter Language Models Using GPU Model Parallelism"
, "NVIDIA ADLR"
, "August 13, 2019"
, ""
, "Larger language models are dramatically more useful for NLP tasks such as article completion, question answering, and dialog systems. Training the largest neural language model has recently been the best way to advance the state of the art in NLP applications. Two recent papers, BERT and GPT-2, demonstrate the benefits of large scale language modeling. Both papers leverage advances in compute and available text corpora to significantly surpass state of the art performance in natural language understanding, modeling, and generation. Training these models requires hundreds of exaflops of compute and clever memory management to trade recomputation for a reduced memory footprint. However, for very large models beyond a billion parameters, the memory on a single GPU is not enough to fit the model along with the parameters needed for training, requiring model parallelism to split the parameters across multiple GPUs. Several approaches to model parallelism exist, but they are difficult to use, either because they rely on custom compilers, or because they scale poorly or require changes to the optimizer.
In this work, we implement a simple and efficient model parallel approach by making only a few targeted modifications to existing PyTorch transformer implementations. Our code is written in native Python, leverages mixed precision training, and utilizes the NCCL library for communication between GPUs. We showcase this approach by training an 8.3 billion parameter transformer language model with 8-way model parallelism and 64-way data parallelism on 512 GPUs, making it the largest transformer based language model ever trained at 24x the size of BERT and 5.6x the size of GPT-2. We have published the code that implements this approach at our GitHub repository.")
),
("https://www.poetryfoundation.org/poems/49303/howl"
, ("Howl"
, "Allen Ginsberg"
, "1955 - 1956"
, ""
, "For Carl Solomon
I
I saw the best minds of my generation destroyed by madness, starving hysterical naked,
dragging themselves through the negro streets at dawn looking for an angry fix,
angelheaded hipsters burning for the ancient heavenly connection to the starry dynamo in the machinery of night,
who poverty and tatters and hollow-eyed and high sat up smoking in the supernatural darkness of cold-water flats floating across the tops of cities contemplating jazz,
who bared their brains to Heaven under the El and saw Mohammedan angels staggering on tenement roofs illuminated,
who passed through universities with radiant cool eyes hallucinating Arkansas and Blake-light tragedy among the scholars of war,
who were expelled from the academies for crazy & publishing obscene odes on the windows of the skull, ...")
),
("http://antinegationism.tumblr.com/post/182901133106/an-eternal-howl"
, ("An Eternal Howl"
, ""
, ""
, ""
, "Prompt:
“Moloch! Solitude! Filth! Ugliness! Ashcans and unobtainable dollars! Children screaming under the stairways! Boys sobbing in armies! Old men weeping in the parks!
Moloch! Moloch! Nightmare of Moloch! Moloch the loveless! Mental Moloch! Moloch the heavy judger of men!
Moloch the incomprehensible prison! Moloch the crossbone soulless jailhouse and Congress of sorrows!
Moloch whose buildings are judgment! Moloch the vast stone of war! Moloch the stunned governments!
Moloch whose mind is pure machinery! Moloch whose blood is running money! Moloch whose fingers are ten armies! Moloch whose breast is a cannibal dynamo!
Moloch whose ear is a smoking tomb!
Moloch whose eyes are a thousand blind windows!
Moloch whose skyscrapers stand in the long streets like endless Jehovahs!
Moloch whose factories dream and croak in the fog!
Moloch whose smoke-stacks and antennae crown the cities …”
Response:
like a pile of wood!
Moloch whose huge flawless towers cry like song in the daytime!
Moloch whose buildings implode like a living Iometer of History!
Moloch whose bridges sag violently like a lattice apple falling on the stream!
Moloch whose court are the host of billions of millions of nerves of passion and anger still raging up and down every dollar in the world!
Moloch the shadow world long, Americanized and red in red!
Moloch is cruel always and everywhere.
Moloch is perfect to human purposes!
Moloch is kept beyond height blind. Moloch the incorporeal skull of man!
Moloch the flag of equality!
Moloch the endless ever-splitting price of hell!
Moloch the worldly bathing anchor in fungicide money!
Moloch the hideous empire in feeble lines! Moloch the death of the dreamless things! Moloch the glorious command of justice! Moloch the bloody trail!")
),
("https://twitter.com/robertskmiles/status/1104008764997419009"
, ("Rob Miles on Twitter"
, "robertskmiles"
, "Mar 8, 2019"
, ""
, "
")
),
("https://medium.com/@ysaw/gpt-2-writes-a-shelley-poem-bc0c19fe4ee3"
, ("GPT-2 Writes a Shelley Poem"
, "Stephen Woods"
, "Feb 20, 2019"
, ""
, "(seed text was Ozymandias)
The sea hath never parted from the rocky shores,
That doth not rise again the sea, and its long, tumbled,
As if the waters have broken by its side.
And as the ocean came up to sea,
And the sea was broken by the wreck,
And the sea sank to the Sea of the Dead
By the wad of blood. It would have slain the Sea of the Dead
But it would not: its last breath, And it did.
This sea in the sea hath a Sea of waggon,
And a Sea of waggon of blood; For all what hath not come
With it hath fallen, And as a waggon of blood the waggon
And the blood is flowing out of that waggon.
So, then, are the works of Zeus,
And the work of Zeus, O Great Creator, whose designs
With the work of the great King are he wrought
In their midst. . . . .
In the desert have the mighty Gods
And the gods themselves come.”
A serpent of darkness rises among the hills
In a forest on the land of the gods.
A mighty bird that flies out a bird-hoast,
And flies out a fly, from behind its wing.
And there the sky is filled with white, and it is broken through.
And like this, we know the mighty Man
Of the clouds from which he fled upon the land of the gods,
The mighty serpent that the king sent for them,
And he brought them to that man; and he said:
“I know you, O mighty Man from the earth!”
And what do you say? You knew him when you saw in the dream,
And you saw from under one of his arms a mighty serpent
That a mighty man can lift up, and drive
He that was in the way and lifted up; and he led him to be a god,
And he he led him down the great mountain which I have prepared.
Let his tongue speak, tell thee, O man: “I know thee.
Here thou dost see, O great King, that is the very power of the Gods”
Let His voice say, to thee, “that is the very power of the Gods”
Let His voice say to thee, “that is the voice of the whole creation”")
),
("https://slatestarcodex.com/2019/02/19/gpt-2-as-step-toward-general-intelligence/"
, ("GPT-2 As Step Toward General Intelligence"
, "Scott Alexander"
, "Feb 19, 2019"
, ""
, "A machine learning researcher writes me in response to yesterday’s post, saying:
I still think GPT-2 is a brute-force statistical pattern matcher which blends up the internet and gives you back a slightly unappetizing slurry of it when asked.
I resisted the urge to answer “Yeah, well, your mom is a brute-force statistical pattern matcher which blends up the internet and gives you back a slightly unappetizing slurry of it when asked.”
But I think it would have been true.
A very careless plagiarist takes someone else’s work and copies it verbatim: “The mitochondria is the powerhouse of the cell”. A more careful plagiarist takes the work and changes a few words around: “The mitochondria is the energy dynamo of the cell”. A plagiarist who is more careful still changes the entire sentence structure: “In cells, mitochondria are the energy dynamos”. The most careful plagiarists change everything except the underlying concept, which they grasp at so deep a level that they can put it in whatever words they want – at which point it is no longer called plagiarism.
GPT-2 writes fantasy battle scenes by reading a million human-written fantasy battle scenes, distilling them down to the concept of a fantasy battle scene, and then building it back up from there. I think this is how your mom (and everyone else) does it too. GPT-2 is worse at this, because it’s not as powerful as your mom’s brain. But I don’t think it’s doing a different thing. We’re all blending experience into a slurry; the difference is how finely we blend it.
...")
),
("https://twitter.com/peterkz_swe/status/1098668851640848384"
, ("Peter Krantz on Twitter"
, "@peterkz_swe"
, "Feb 21, 2019"
, ""
, "
")
),
("https://github.com/kylemcdonald/gpt-2-poetry"
, ("gpt-2-poetry"
, "Kyle McDonald"
, "Mar 4, 2019"
, ""
, "I used download-urls.py to quickly download the HTML from poetryfoundation.org based on the urls in romantic-urls.txt.
Then I used Parse Poetry.ipynb to parse the HTML and extract the title, author, and poem. There are some glitches here with newlines being rendered in some places they shouldn't, and not being rendered in places where they should. This notebook saves a bunch of text files to output/ that include metadata as the first few lines.
Then I used Generate GPT-2.ipynb to generate poems based on random chunks from the poems and the seed words. This notebook saves files to poems.json and generated.json. To run this notebook, first get GPT-2 running, and drop the notebook in the gpt-2/src/ directory.
Both Python notebooks import from utils which I have separately pushed here.
Finally, I load generated.json and poems.json with JavaScript in index.html and display the results.")
),
("https://medium.com/merzazine/fridai-water-water-everywhere-as-read-by-artificial-intelligence-d02bb3d2b156"
, ("FridAI: ‘Water, water, everywhere’, as read by Artificial Intelligence"
, "Merzmensch Kosmopol"
, "Mar 15, 2019"
, ""
, "Samuel Taylor Coleridge once introduced to the world that desolated ship journey in his “The Rime of the Ancient Mariner”:
Water, water, everywhere,
And all the boards did shrink;
Water, water, everywhere,
Nor any drop to drink.
Ulysses, Noah and Job, so many allusions are hidden in this masterpiece about “a sadder and a wiser man”. And so I wanted to know, which journey will be chosen by GPT-2, a Deep Learning entity, developed by OpenAI to write texts.
And it wrote me a poem.
My input was the four lined stanza, as cited above. And here is the poetic vision by Artificial Intelligence:
Water, water, everywhere,
And all the boards did shrink;
Water, water, everywhere,
Nor any drop to drink.
Water, water, everywhere,
And all the boards did shrink;
Water, water, everywhere,
No balm in his hair:
Water, water, everywhere,
And all the boards did shrink.
Water, water, everywhere,
Yet we like its rarity.
Water, water, everywhere,
And all the boards did shrink.
Water, water, everywhere.
Yes, the rarity of the water (everywhere) is striking. Even if the hair is suffering without balm. Probably because you cannot drink a drop.
But the poem was not over. AI was embraced by inspiration.
...
")
),
("http://yudhanjaya.com/2019/04/the-poetry-machine/"
, ("The Poetry Machine"
, "Yudhanjaya Wijeratne"
, "Apr 12, 2019"
, ""
, "I’ve always admired the translations of Chinese poetry – I’m no expert on the field, but there are two poets named Du Fu and Li Bai that I really like. They were legendary masters from the Great Tang Dynasty, and (if the translations are accurate), they had a phenomenal talent for freezing a moment and capturing that particular slice of time with their words; their poems read like a string of Polaroids stretched across a riverbank.
Here, for example, is a Du Fu poem. Among other things, there’s a certain simplicity here: one strong emotion resonates through, and unlike much of the English verse I grew up with, it’s firmly in the present tense:A LONG CLIMB
In a sharp gale from the wide sky apes are whimpering,
Birds are flying homeward over the clear lake and white sand,
Leaves are dropping down like the spray of a waterfall,
While I watch the long river always rolling on.
I have come three thousand miles away. Sad now with autumn
And with my hundred years of woe, I climb this height alone.
Ill fortune has laid a bitter frost on my temples,
Heart-ache and weariness are a thick dust in my wine.
Which I suppose is why this appeals to me – there’s a rare clarity here, even if the translation might be inaccurate.
So the Tang poets seemed like the right place to start with for my experiment with machine-generated art (and besides, the excellent GWERN already did the usual English[1]). Right now, I’ve snuck away for a few hours from a my statistical models to peek at the code I set to run this morning.
Among those of us who work with machine learning, the work I’ve put into this whole project is trivial: a tiny dataset, a cup of coffee, a few lines of Python code, and a single cigarette while I waited for OpenAI’s transformer-based generation model [2] to download.")
),
("https://twitter.com/rossgoodwin/status/1124901310677913600"
, ("Ross Goodwin on Twitter"
, "@rossgoodwin"
, "May 4, 2019"
, ""
, "
")
),
("https://iforcedabot.com/what-can-a-fake-news-detector-do/"
, ("Testing The Limits of Grover The Neural Fake News Detector. Can It Write Fiction? Can It Write Riddles?"
, "Jonathan Fly"
, "May 31, 2019"
, ""
, "Grover is a neural network modeled after GPT-2 as a state-of-the-art detector for Neural Network fake news. Grover is also a state-of-the-art generator of fake news and they provide a web interface. Since Grover is modeled after the full-size 1.5B GPT-2 – not the smaller version the public has access to – this is a bit like getting a back door to the full-size GPT-2. This is very exciting! (Update: They just reduced the size of the public model to 345M — everything in this post come from the full size model. Glad I stayed up way too late hammering the real thing for samples… Update 2: It’s back up!)
Grover was trained on 5000 news domains indexed by Google News, not the internet generally like GPT-2. As you would expect Grover excels at writing fake news:Scientists Recommend Against Vaccination: \"The Evidence Is Now Clear: Vaccines Cause Autism and Cancer\"
After a 15-year study, scientists in Britain are recommending that the British government refrain from administering vaccines. The study, written by Mike Gunton, professor of epidemiology and professor of genetic medicine at the University of Liverpool, claims that the chances of the MMR vaccine, a vaccine for measles, mumps and rubella, causing autism in children are “strongly possible.” And while Gunton and his team say their findings only apply to the MMR vaccine, they believe there are “many similar disorders” linked to vaccines and there is “strong evidence” vaccines cause autism and leukemia. Gunton told the Telegraph that no effort should be made to give vaccines to children younger than 3 months of age. The vaccine is highly controversial, and parents have been choosing to opt out of the MMR vaccination in recent years. This year, the British government’s vaccination program chose not to distribute the MMR vaccine, citing the study as the reason.
You don’t have to fish to get coherent fake news of Grover, it’s absolutely great at it.")
),
("https://medium.com/@NPCollapse/replicating-gpt2-1-5b-86454a7f26af"
, ("Replicating GPT2–1.5B"
, "Connor Leahy"
, "Jun 6, 2019"
, ""
, "In this post, I want to quickly talk about the technical and organizational questions around my recent replication of GPT2–1.5B. Please read my main post for the full story. I will try to keep this post brief.
The important facts
Code: https://github.com/ConnorJL/GPT2
Samples: https://github.com/ConnorJL/GPT2/tree/master/samples
The code should run out of the box on GPUs and TPUs (and CPUs, if you’re really desperate). I used the parameters specified in 1.5B.json and trained it on a preemptible v3–512 TPU pod (which is actually more powerful than the machine OpenAI used) for around a week (with interruptions). Code and instructions for generating the dataset are also included in the repo.
You can download my models with the script in the repo. Currently I have a weaker version of 117M, and a model I call PrettyBig which is slightly larger than OpenAI’s 345M, which means it is technically the largest GPT2 model currently publicly available.
I will be releasing 1.5B to the public on July 1st, if, and only if, no one shows me a convincing reason not to. When I do, it will be downloadable just like my other models.")
),
("https://medium.com/@NPCollapse/addendum-evaluation-of-my-model-e6734b51a830"
, ("Addendum: Evaluation of My Model"
, "Connor Leahy"
, "Jun 12, 2019"
, ""
, "As a mercifully short addendum, I’d like to quickly address a few questions about my model. Please read my update post to hear my important updated beliefs on this situation, because I believe the details of how powerful my model is or not are not actually very important to the overall situation.
As described in my technical post, my model is not identical to OpenAI’s, because I simply didn’t have all the details of what they did. The truth is also that the samples and metrics I have shown aren’t 100% accurate. For one, my metric code is flawed, I made several rookie mistakes in setting up accurate evaluation (let train and eval data mix, used metrics whose math I didn’t understand etc), and the model I used to generate the samples is in fact not the final trained model, but one about halfway through the training. I didn’t take my time to evaluate the strength of my model, I simply saw I had the same amount of hardware as OpenAI and code as close to the paper as possible and went with it. The reason for this is a simple human flaw: I got cold feet once I realized what I was sitting on and acted rashly. I made a mistake, I did something stupid, that’s all there is to it.
Thanks to help from OpenAI it is now safe to say that my model is not as powerful as OpenAI’s. The metric results for WikiText2, LAMBADA and PTB are (lower is better):
GPT2: 18.67 / 8.63 / 36.51
Mine: 43.79 / 109.47 / 202.29
Although I used the same amount of hardware (or more), the differences in my training setup and hyperparameters made a significant difference. Which is an unfortunate reality to anyone familiar with reproducing deep learning papers. I don’t think my model in its current state is even as dangerous as 117M in its text generating abilities. But I believe to have found the quirks in my setup that have held the model back, and they are easy to fix. I am very tempted to continue tinkering with the model and seeing if I can improve it…but I will be holding back for now.")
)
]