One of the worst examples of this “psychosis”, in terms of consequences, is the 1959-61 Great Chinese Famine which killed between 15 and 55 million people.
We should heavily discount negative feelings related to criticism, instead of taking them at face value (as showing that something is wrong and should be fixed, e.g. by getting rid of the source of the criticism). I think this can often manifest not as “I hate this criticism” but more like “This person is so annoying and lack basic social skills.”
There’s probably an effect where the less criticism we hear, the more sensitive we become to the remaining criticism, suggesting a slippery slope towards being surrounded by yes-men.
Remember that most CEOs had to work their way up to that position, and have seen sycophancy from the bottom and understand that it’s bad, but still fall prey to this problem.
Most organizational leaders have people they have to answer to and could be replaced if they perform badly. Why doesn’t this fix the problem? Trying to answer this myself, I found this paper which says:
In a series of studies, Westphal and Stern (2006, 2007; Stern and Westphal, 2010) showed that ingratiation by a manager or director toward the chief executive officer (CEO) of a large company has a strong, positive effect on the likelihood of receiving the CEO’s recommendation for a board appointment at another firm where the CEO serves as director.
I guess this is an instance of a more general phenomenon known as “board capture”, which helps explain why having a board doesn’t solve the whole problem. The paper also says:
Further analyses suggest that strategic persistence that results from high levels of flattery and opinion conformity directed at the CEO can result in the persistence of low firm performance and may ultimately increase the likelihood of the CEO’s dismissal.
So I guess the CEO being fireable does solve the problem to some extent.
AI written account of how Mao came to make the disastrous decision that killed tens of millions, for anyone curious. This matches my own understanding.
Of course. The episode you’re referring to is one of the most famous and tragic chapters of China’s Great Leap Forward (1958-1962). It wasn’t just a single moment but a nationwide frenzy of exaggeration, and Mao Zedong’s belief in these claims was a critical factor that fueled the disaster.
This phenomenon was centered around the creation of so-called “Sputnik Fields” (卫星田, Wèixīng Tián).
Here is a breakdown of the episode: the context, why it happened, Mao’s involvement, and the devastating consequences.
The Context: The Great Leap Forward
In 1958, Mao launched the Great Leap Forward, a campaign to rapidly transform China from an agrarian society into a socialist industrial power. The atmosphere was one of intense revolutionary fervor and political pressure. The core belief was that sheer willpower and the collectivized power of the masses could overcome any material or scientific obstacle.
The slogan of the day was “more, faster, better, cheaper.” Officials at every level were under immense pressure to report fantastic successes to prove their revolutionary credentials and avoid being labeled a “right-wing conservative.”
The “Sputnik Fields” and the “10,000 Jin” Claim
The term “Sputnik Field” was inspired by the Soviet Union’s recent launch of the Sputnik satellite in 1957. The name implied that China was achieving miraculous, space-age breakthroughs in agriculture.
The claims started in early 1958 and escalated rapidly:
First, a county reported a winter wheat yield of 2,105 jin per mu.
Soon after, another reported 3,500 jin per mu.
By the summer, the numbers had become astronomical. A commune in Henan province famously claimed a yield of 7,320 jin per mu.
This was quickly topped by claims of 10,000 jin per mu (万斤亩, wàn jīn mǔ), and eventually, the official People’s Daily newspaper reported a record-breaking rice yield of over 130,000 jin per mu in Macheng County, Hubei.
(For context: 1 mu is about 1/6th of an acre or 667 square meters. 1 jin is half a kilogram or 1.1 lbs. A good, realistic yield at the time was around 400-500 jin per mu. 10,000 jin per mu is equivalent to about 75,000 kg per hectare, a yield that is still physically impossible for rice or wheat today.)
How Were These “Miracles” Faked?
These incredible yields were elaborate hoaxes created for visiting officials and journalists. The most common method was to:
Select a small, visible plot of land—the “Sputnik Field.”
Just before the visit, cadres would secretly uproot mature crops (like rice or wheat) from many surrounding fields during the night.
They would then transplant and cram all these crops onto the single small plot, making it appear incredibly dense and fruitful.
The most iconic and notorious propaganda photo from this era shows several children standing on top of a field of wheat, seemingly held up by the dense stalks. In reality, the children were standing on a wooden bench hidden beneath the transplanted wheat.
Why Did Mao Believe It?
Mao’s conviction was not born out of simple gullibility but from a combination of factors:
1. Political Atmosphere and Information Bubble: Mao was surrounded by officials who told him what he wanted to hear. Reporting bad news was politically dangerous, so a tsunami of good news, however fake, flowed to the top. When he toured the countryside, he was only shown the carefully staged “Sputnik Fields.”
2. Ideological Zeal: Mao deeply believed in the power of socialist collectivization. He thought that by reorganizing society and unleashing the “creative power of the masses,” things previously thought impossible were now achievable. The exaggerated claims confirmed his worldview.
3. “Scientific” Justification: The claims were given a veneer of scientific credibility. This came from two main sources:
Lysenkoism: A discredited Soviet pseudo-agricultural theory promoted by Trofim Lysenko. It rejected genetics and promoted techniques like “close planting” and “deep plowing,” arguing that planting seeds extremely close together would make them cooperate rather than compete. Chinese officials claimed their high yields were due to these methods.
Qian Xuesen’s Endorsement: This was perhaps the most crucial element. Qian Xuesen was a brilliant, US-educated scientist and the father of China’s missile program. In 1958, he wrote an article published in China Youth Daily where he did a rough calculation based on the amount of solar energy that falls on a mu of land. He concluded that, theoretically, it was possible to convert that energy into a crop yield of over 40,000 jin.
When Mao was told about the fantastic yields, he was initially skeptical. But when he was told that Qian Xuesen, China’s most respected scientist, had confirmed it was theoretically possible, his doubts were erased. He reasoned that if it was scientifically possible, then the revolutionary spirit of the Chinese peasants could make it a reality.
The Catastrophic Consequences
This mass delusion had a direct and horrifying outcome: The Great Famine (1959-1962).
The central government, believing these fantastical reports, set impossibly high grain procurement quotas. Local officials, to prove their “success” and meet the quotas, seized virtually all the grain from the peasants, including their food, animal feed, and even the seeds for the next planting season.
The peasants had produced a normal amount of food, but because the state believed they had produced 10 or 20 times that amount, their entire harvest was taken away.
The result was the worst famine in human history. With no food left in the countryside, tens of millions of people starved to death. The episode of the “10,000 jin per mu” was not a harmless propaganda folly; it was a direct cause of this unprecedented tragedy, a testament to the dangers of when political ideology completely detaches from reality.
Some quotes from this:
Qian Xuesen’s Endorsement: This was perhaps the most crucial element. Qian Xuesen was a brilliant, US-educated scientist and the father of China’s missile program. In 1958, he wrote an article published in China Youth Daily where he did a rough calculation based on the amount of solar energy that falls on a mu of land. He concluded that, theoretically, it was possible to convert that energy into a crop yield of over 40,000 jin.
When Mao was told about the fantastic yields, he was initially skeptical. But when he was told that Qian Xuesen, China’s most respected scientist, had confirmed it was theoretically possible, his doubts were erased. He reasoned that if it was scientifically possible, then the revolutionary spirit of the Chinese peasants could make it a reality.
The central government, believing these fantastical reports, set impossibly high grain procurement quotas. Local officials, to prove their “success” and meet the quotas, seized virtually all the grain from the peasants, including their food, animal feed, and even the seeds for the next planting season.
We should heavily discount negative feelings related to criticism, instead of taking them at face value (as showing that something is wrong and should be fixed, e.g. by getting rid of the source of the criticism). I think this can often manifest not as “I hate this criticism” but more like “This person is so annoying and lack basic social skills.”
There’s probably an effect where the less criticism we hear, the more sensitive we become to the remaining criticism, suggesting a slippery slope towards being surrounded by yes-men.
Remember that most CEOs had to work their way up to that position, and have seen sycophancy from the bottom and understand that it’s bad, but still fall prey to this problem.
The status “jab” is itself a valuable signal. Here’s a pastiche of the model I’m developing integrating the insights I’ve gained from researching LLM-Induced Psychosis (and rereading Keith Johnstone).
Status is the coordination signal, in the same way that pain is the survival signal. If you don’t care about coordinating with others then it’s fine to ignore it.
For everyone else, we correctly need to maintain a baseline level of status. Despite everything, this still represents the amount of coordination you can actually muster pretty well.
Almost every social interaction has a status valence associated with it. Actually, it’s not quite a spectrum like “valence” suggests: it’s a square… raise mine, lower mine, raise yours, lower yours. The extra dimension arises from the fact that this is relative to our coordination context. If I give you a compliment, it signals that I think you are an asset in the current context relative to what we had both understood to be the case. If I self-deprecate, it signals that I think I am not as helpful relative to our mutual understanding. This still feels good, because your model of the coordination context correctly (if I’m not lying) gives you status, as you are now more of an asset to the coordination group than was previously understood. But only to a point… eventually I may successfully self-deprecate to the point where it is common knowledge that I am a drag on the context-group’s ability to coordinate, and it will no longer feel good to hear me drive that point home even more. (“Haha, sorry I’m late guys… you know me lolol!”)
But actually, it’s more nuanced than this! Within a single coordination context (e.g. among friends) it works like this, but there are lots of different coordination contexts! This makes coordination-potential (not status) a resource, in that there’s a finite amount to be shared (in the moment, it’s not zero-sum more broadly… trade still works!). So the ‘raise yours’ signal additionally allocates coordination-potential to you, while the ‘lower mine’ deallocates coordination-potential belonging to me. This is why you still like me when I self-deprecate (as long as I’m not too obnoxious about it). And why someone who’s too helpful isn’t “high status”. Technically, this should be a separate signal, but I think evolution has only hardwired two-dimensions of the signal.
Now what about the “jabs”, those sure don’t feel good do they? And of course not, it sucks to update towards reduced ability to coordinate! That’s straightforwardly just a bad thing …mostly. Because not every coordination context is a good context for you even if it is yours. If you have an idea, and I think it’s a bad idea, then the honest thing for me to do is to signal that I will not coordinate with you in the context of that idea. And that feels bad, a dig at your status as it inherently is—as long as I signal that clearly. If I couch my words carefully, then I can tell you honestly that I think your idea is bad while still leaving you with the impression that I am still cooperative w.r.t. it to some extent. A typical “friendly” way to do this is for me to “agree to disagree”, which means that I won’t get in the way of your collecting coordination-potential towards it. That’s a fine outcome to the extent we have different goals and values, but becomes more of a disservice the more that we have an explicitly shared purpose.
With this lens, we can see that many of the pathologies of status are really just people wanting stupid things and/or Goodharting the signals of course. For example, our CEO wants to coordinate against people who don’t want to cooperate with his ideas (i.e. coordination contexts). This means that he’s no longer receiving feedback about which of his ideas are worth cooperating with… which could be fine if he only has good ideas (as if). He’s still susceptible to this despite having seen it, because he foolishly believes that his ideas are actually always good (why else would he have them?). Made worse by the fact that his earlier good ideas are more likely the ones that got coordinated with, meaning that his ideas have always worked out “if you would just give them a chance”. And he probably has this idea of suppressing dissent in the first place as a way of avoiding the pain of the status jabs, i.e. Goodharting.
In sum, the epistemic role of status is thus: it is the signal by which your friends tell you which of your ideas, values, projects, goals, are worth coordinating with.
One of the worst examples of this “psychosis”, in terms of consequences, is the 1959-61 Great Chinese Famine which killed between 15 and 55 million people.
We should heavily discount negative feelings related to criticism, instead of taking them at face value (as showing that something is wrong and should be fixed, e.g. by getting rid of the source of the criticism). I think this can often manifest not as “I hate this criticism” but more like “This person is so annoying and lack basic social skills.”
There’s probably an effect where the less criticism we hear, the more sensitive we become to the remaining criticism, suggesting a slippery slope towards being surrounded by yes-men.
Remember that most CEOs had to work their way up to that position, and have seen sycophancy from the bottom and understand that it’s bad, but still fall prey to this problem.
Most organizational leaders have people they have to answer to and could be replaced if they perform badly. Why doesn’t this fix the problem? Trying to answer this myself, I found this paper which says:
I guess this is an instance of a more general phenomenon known as “board capture”, which helps explain why having a board doesn’t solve the whole problem. The paper also says:
So I guess the CEO being fireable does solve the problem to some extent.
AI written account of how Mao came to make the disastrous decision that killed tens of millions, for anyone curious. This matches my own understanding.
Of course. The episode you’re referring to is one of the most famous and tragic chapters of China’s Great Leap Forward (1958-1962). It wasn’t just a single moment but a nationwide frenzy of exaggeration, and Mao Zedong’s belief in these claims was a critical factor that fueled the disaster.
This phenomenon was centered around the creation of so-called “Sputnik Fields” (卫星田, Wèixīng Tián).
Here is a breakdown of the episode: the context, why it happened, Mao’s involvement, and the devastating consequences.
The Context: The Great Leap Forward
In 1958, Mao launched the Great Leap Forward, a campaign to rapidly transform China from an agrarian society into a socialist industrial power. The atmosphere was one of intense revolutionary fervor and political pressure. The core belief was that sheer willpower and the collectivized power of the masses could overcome any material or scientific obstacle.
The slogan of the day was “more, faster, better, cheaper.” Officials at every level were under immense pressure to report fantastic successes to prove their revolutionary credentials and avoid being labeled a “right-wing conservative.”
The “Sputnik Fields” and the “10,000 Jin” Claim
The term “Sputnik Field” was inspired by the Soviet Union’s recent launch of the Sputnik satellite in 1957. The name implied that China was achieving miraculous, space-age breakthroughs in agriculture.
The claims started in early 1958 and escalated rapidly:
First, a county reported a winter wheat yield of 2,105 jin per mu.
Soon after, another reported 3,500 jin per mu.
By the summer, the numbers had become astronomical. A commune in Henan province famously claimed a yield of 7,320 jin per mu.
This was quickly topped by claims of 10,000 jin per mu (万斤亩, wàn jīn mǔ), and eventually, the official People’s Daily newspaper reported a record-breaking rice yield of over 130,000 jin per mu in Macheng County, Hubei.
(For context: 1 mu is about 1/6th of an acre or 667 square meters. 1 jin is half a kilogram or 1.1 lbs. A good, realistic yield at the time was around 400-500 jin per mu. 10,000 jin per mu is equivalent to about 75,000 kg per hectare, a yield that is still physically impossible for rice or wheat today.)
How Were These “Miracles” Faked?
These incredible yields were elaborate hoaxes created for visiting officials and journalists. The most common method was to:
Select a small, visible plot of land—the “Sputnik Field.”
Just before the visit, cadres would secretly uproot mature crops (like rice or wheat) from many surrounding fields during the night.
They would then transplant and cram all these crops onto the single small plot, making it appear incredibly dense and fruitful.
The most iconic and notorious propaganda photo from this era shows several children standing on top of a field of wheat, seemingly held up by the dense stalks. In reality, the children were standing on a wooden bench hidden beneath the transplanted wheat.
Why Did Mao Believe It?
Mao’s conviction was not born out of simple gullibility but from a combination of factors:
1. Political Atmosphere and Information Bubble: Mao was surrounded by officials who told him what he wanted to hear. Reporting bad news was politically dangerous, so a tsunami of good news, however fake, flowed to the top. When he toured the countryside, he was only shown the carefully staged “Sputnik Fields.”
2. Ideological Zeal: Mao deeply believed in the power of socialist collectivization. He thought that by reorganizing society and unleashing the “creative power of the masses,” things previously thought impossible were now achievable. The exaggerated claims confirmed his worldview.
3. “Scientific” Justification: The claims were given a veneer of scientific credibility. This came from two main sources:
Lysenkoism: A discredited Soviet pseudo-agricultural theory promoted by Trofim Lysenko. It rejected genetics and promoted techniques like “close planting” and “deep plowing,” arguing that planting seeds extremely close together would make them cooperate rather than compete. Chinese officials claimed their high yields were due to these methods.
Qian Xuesen’s Endorsement: This was perhaps the most crucial element. Qian Xuesen was a brilliant, US-educated scientist and the father of China’s missile program. In 1958, he wrote an article published in China Youth Daily where he did a rough calculation based on the amount of solar energy that falls on a mu of land. He concluded that, theoretically, it was possible to convert that energy into a crop yield of over 40,000 jin.
When Mao was told about the fantastic yields, he was initially skeptical. But when he was told that Qian Xuesen, China’s most respected scientist, had confirmed it was theoretically possible, his doubts were erased. He reasoned that if it was scientifically possible, then the revolutionary spirit of the Chinese peasants could make it a reality.
The Catastrophic Consequences
This mass delusion had a direct and horrifying outcome: The Great Famine (1959-1962).
The central government, believing these fantastical reports, set impossibly high grain procurement quotas. Local officials, to prove their “success” and meet the quotas, seized virtually all the grain from the peasants, including their food, animal feed, and even the seeds for the next planting season.
The peasants had produced a normal amount of food, but because the state believed they had produced 10 or 20 times that amount, their entire harvest was taken away.
The result was the worst famine in human history. With no food left in the countryside, tens of millions of people starved to death. The episode of the “10,000 jin per mu” was not a harmless propaganda folly; it was a direct cause of this unprecedented tragedy, a testament to the dangers of when political ideology completely detaches from reality.
Some quotes from this:
Qian Xuesen’s Endorsement: This was perhaps the most crucial element. Qian Xuesen was a brilliant, US-educated scientist and the father of China’s missile program. In 1958, he wrote an article published in China Youth Daily where he did a rough calculation based on the amount of solar energy that falls on a mu of land. He concluded that, theoretically, it was possible to convert that energy into a crop yield of over 40,000 jin.
When Mao was told about the fantastic yields, he was initially skeptical. But when he was told that Qian Xuesen, China’s most respected scientist, had confirmed it was theoretically possible, his doubts were erased. He reasoned that if it was scientifically possible, then the revolutionary spirit of the Chinese peasants could make it a reality.
The central government, believing these fantastical reports, set impossibly high grain procurement quotas. Local officials, to prove their “success” and meet the quotas, seized virtually all the grain from the peasants, including their food, animal feed, and even the seeds for the next planting season.
The status “jab” is itself a valuable signal. Here’s a pastiche of the model I’m developing integrating the insights I’ve gained from researching LLM-Induced Psychosis (and rereading Keith Johnstone).
Status is the coordination signal, in the same way that pain is the survival signal. If you don’t care about coordinating with others then it’s fine to ignore it.
For everyone else, we correctly need to maintain a baseline level of status. Despite everything, this still represents the amount of coordination you can actually muster pretty well.
Almost every social interaction has a status valence associated with it. Actually, it’s not quite a spectrum like “valence” suggests: it’s a square… raise mine, lower mine, raise yours, lower yours. The extra dimension arises from the fact that this is relative to our coordination context. If I give you a compliment, it signals that I think you are an asset in the current context relative to what we had both understood to be the case. If I self-deprecate, it signals that I think I am not as helpful relative to our mutual understanding. This still feels good, because your model of the coordination context correctly (if I’m not lying) gives you status, as you are now more of an asset to the coordination group than was previously understood. But only to a point… eventually I may successfully self-deprecate to the point where it is common knowledge that I am a drag on the context-group’s ability to coordinate, and it will no longer feel good to hear me drive that point home even more. (“Haha, sorry I’m late guys… you know me lolol!”)
But actually, it’s more nuanced than this! Within a single coordination context (e.g. among friends) it works like this, but there are lots of different coordination contexts! This makes coordination-potential (not status) a resource, in that there’s a finite amount to be shared (in the moment, it’s not zero-sum more broadly… trade still works!). So the ‘raise yours’ signal additionally allocates coordination-potential to you, while the ‘lower mine’ deallocates coordination-potential belonging to me. This is why you still like me when I self-deprecate (as long as I’m not too obnoxious about it). And why someone who’s too helpful isn’t “high status”. Technically, this should be a separate signal, but I think evolution has only hardwired two-dimensions of the signal.
Now what about the “jabs”, those sure don’t feel good do they? And of course not, it sucks to update towards reduced ability to coordinate! That’s straightforwardly just a bad thing …mostly. Because not every coordination context is a good context for you even if it is yours. If you have an idea, and I think it’s a bad idea, then the honest thing for me to do is to signal that I will not coordinate with you in the context of that idea. And that feels bad, a dig at your status as it inherently is—as long as I signal that clearly. If I couch my words carefully, then I can tell you honestly that I think your idea is bad while still leaving you with the impression that I am still cooperative w.r.t. it to some extent. A typical “friendly” way to do this is for me to “agree to disagree”, which means that I won’t get in the way of your collecting coordination-potential towards it. That’s a fine outcome to the extent we have different goals and values, but becomes more of a disservice the more that we have an explicitly shared purpose.
With this lens, we can see that many of the pathologies of status are really just people wanting stupid things and/or Goodharting the signals of course. For example, our CEO wants to coordinate against people who don’t want to cooperate with his ideas (i.e. coordination contexts). This means that he’s no longer receiving feedback about which of his ideas are worth cooperating with… which could be fine if he only has good ideas (as if). He’s still susceptible to this despite having seen it, because he foolishly believes that his ideas are actually always good (why else would he have them?). Made worse by the fact that his earlier good ideas are more likely the ones that got coordinated with, meaning that his ideas have always worked out “if you would just give them a chance”. And he probably has this idea of suppressing dissent in the first place as a way of avoiding the pain of the status jabs, i.e. Goodharting.
In sum, the epistemic role of status is thus: it is the signal by which your friends tell you which of your ideas, values, projects, goals, are worth coordinating with.