On Frustrated Sleeper Agents
Last week I read a New Yorker article by Margaret Talbot investigating why Supreme Court Justice Samuel Alito gets angrier and more outspoken the more he achieves his legal aspirations.
Contrary to what you would expect from his recent public disdain for progressive legal opponents, Alito spent his earlier jobs cultivating a reputation for quiet, measured, incrementalism–a paragon of bureaucratic boredom. Longtime friends and colleagues report shock at his recent partisanship.
Samuel Alito was a sleeper agent. The opportunity structure of the American legal system catastrophically failed to filter out an extremist before he reached the top of the hierarchy. This is the kind of outcome that should terrify a bureaucratic organization. Elites expect long hierarchies with heavy credentialing to weed out weirdos and extinguish extremists. Only the smoothest stools/pearls (depending on your mood) should pass all the way through a bureaucracy’s digestive tract.
It makes sense that the Supreme Court might lose popular legitimacy for unintentionally empowering a partisan extremist but Alito’s declining satisfaction with his situation surprised me. Reading Talbot’s account inspired me with a hypothesis. Sleeper agents depend on the premise that once they climb high enough into the hierarchy they can access energy for change that is far more powerful than was available in their earlier positions.1 Suppose there exist two types of sleeper agents: destructive and constructive. Destructive sleeper agents wait for the moment they can maximally sabotage their organization and escape. Constructive sleeper agents wait for the moment they can maximally transform the organization to achieve its unrealized potential.
Destructive sleeper agents will naturally have an easier time since destruction is simpler and results in organizations past points of no return. Destruction involves sowing mistrust, dissolving friendships, polluting resources, and breaking capital. Constructive sleeper agents may do some of this but need to keep the bulk of the organization in good health.
Constructive sleeper agents must also hide a contempt for the organization’s current leadership. If the agent respected leadership, they would believe it quicker to achieve their goal by sharing their plan for reform up the chain of command than by climbing the chain personally. The sleeper agent believes revealing their plan would harm their prospects because their superiors would oppose the plan strongly enough close the agent’s opportunities for promotion and head off the plan in other ways.
I suspect that the combination of scorn for leadership and expectation of immense power upon promotion doom constructive sleeper agents like Alito to misery. The concentrations of power at the top of a bureaucratic hierarchy are more distributed over the body of the organization than a constructive sleeper agent expects.
Chester Barnard, the early 20th century telecoms executive turned organizational theorist, wrote from experience of all the difficulties leaders face in exercising their official authority. Barnard believed that leaders tend to have little scope for ordering anything beyond what their subordinates expect ordered. And even then, subordinates will reinterpret orders at their own discretion. To make matters worse, any time a leader makes an order that oversteps their legitimate authority, they lose authority for future orders: “there is no principle of executive conduct better established in good organizations than that orders will not be issued which cannot or will not be obeyed” (The Functions of the Executive, 1938). The ponderous hulk of a bureaucracy lurching whichever way a leader commands creates an illusion of executive control. Most of the time the momentum of the organization is the force charting the course and all the executive can do is make it look graceful.
Court analysts have noticed Justice John Roberts’ anxiety about departing too far from precedent and the consequences for the legitimacy of the Court’s authority. Alito seems less concerned as we should expect from constructive sleeper agents. Alito spent his whole career holding his tongue so he could strike down disliked precedents not preserve the legitimacy of the system.
The institution of the American legal system may attract constructive sleeper because the formal authority the Supreme Court justices wield is so great, far-reaching, and lightly checked. But even here, with such an extreme payoff for climbing the ladder, the constraints of bureaucratic leadership are revealing themselves to Alito’s chagrin. Alito succeeded in overturning Roe but instead of the American legal system snapping onto an anti-abortion path for the foreseeable future, the unprecedented opinion has ignited legal battles all over the country that will inevitably rise back up to the Supreme Court for further judgements. The dark irony is that even if the American legal system were full of constructive sleeper agents like Alito, their commitment to the long game would keep them quiet and reinforce Alito’s sense of isolation. The Dobbs decision along with Alito’s other victories have not birthed a brand new legal era, free of yesteryear’s precedents. These successes mark the next chapter for the continuation ongoing conflicts albeit along more conservative lines. This is not to dismiss the terrible power and ramifications of these decisions. Any incrementalist would take these events as unqualified victories. But to the constructive sleeper agent who has been holding their tongue their entire career on the idea that losing battle after battle will be worth winning the war, Alito seems bitter.
Donald Trump’s presidency provides a complementary case for these ideas. Although he was in not a sleeper agent, he advocated positions and methods that similar politicians believed they had to keep secret. And while constructive is the last word you might associate with Trump, he initially sought to build the capacities of the country in a way he considered an improvement. But like Alito, Trump underestimated the unruliness of bureaucratic hulks for radical executives. Another recent New Yorker article2 captures his surprise by documenting Trump’s conflicts with his generals in the waning days of his presidency.
It turned out that the generals had rules, standards, and expertise, not blind loyalty. The President’s loud complaint to John Kelly one day was typical: “You fucking generals, why can’t you be like the German generals?”
“Which generals?” Kelly asked.
“The German generals in World War II,” Trump responded.
“You do know that they tried to kill Hitler three times and almost pulled it off?” Kelly said.
But, of course, Trump did not know that. “No, no, no, they were totally loyal to him,” the President replied. In his version of history, the generals of the Third Reich had been completely subservient to Hitler; this was the model he wanted for his military. Kelly told Trump that there were no such American generals, but the President was determined to test the proposition.
The article describes Trump’s darndest efforts to find a yes-man (the President’s own words) to chair the Joint Chiefs of Staff. The pool of candidates was already so filtered by bureaucratic credentialing that the best general Trump could find for the job was Mark Milley whose undivided loyalties lasted at most two weeks.
If bureaucracies doom constructive sleeper agents to frustration (despite incremental success), what happens next? The boring possibility is nothing. The distinguished sourpuss fumes for their remaining tenure. They may also retire early though this seems unlikely given all the effort and time they expended on the climb. Perhaps most dangerous, a frustrated constructive sleeper agent may shift tactics into a destructive sleeper agent. They may interpret their failure, despite maximum formal authority, as evidence that the organization/institution itself is unsalvageable. Trump’s attempt to steal the election and weaponize Republicans against the democratic process exemplifies this kind of transformation. The mask drops to reveal that the agent’s devotion to the organization existed purely as devotion to a fantastical ideal. In Alito’s case, open partisanship may foreshadow further destructive acts spurred by disillusion with the actuality of the American legal system.3
Frustrated sleeper agents are not evidence that bureaucracies are bullet proof or that executives cannot do grievous harm. Both New Yorker articles are illustrations of bureaucratic fragility.
My minimal takeaway is that the patient, clever connivers who succeed in carrying radical ideologies to the top of a bureaucracy will have predictably adversarial relationships to their peers and the prevailing norms. Understanding this recurring relationship could help opponents foresee and resist sleeper agents’ agendas. The efforts of radical reformers might also become more transparent and inclusive if they adjusted their expectations to match the organizational realities social scientists have documented.
But the twist motivating me to write this post–the twist I had not realized until I was nearly finished writing–is that constructive sleeper agents might be all over.4 You find them in careerists who secretly fantasize detailed plans for how work could be better managed but never say a peep from 9 to 5. You find them among executives who surprise everyone with unexpected reforms and then get bitter or leave when they do not take. I see constructive sleeper agents all over academia. Consider the style of graduate student that can rhapsodize treatises against passé professors and draconian disciplinary rites yet once they hit the job market hide the rhetoric, genuflect to the tried-and-true citations, and unfurl ever-longer CVs. Consider the tenured professors that gripe about the uninspired state of current research but seem unable to publish papers to reinvigorate it. They hold their nose climbing the ladder and are as surprised as their peers to discover they don’t much enjoy the smell of the upper rungs.
Socjobrumors (I have less than 0 interest in providing the link) surveys the nastier thoughts sociologists have about one another but require anonymity to share. I have seen two tenured sociologists extol the virtues of collaborative work (science is social!) and then raise an eyebrow when a student plans to coauthor all their dissertation papers.5
Trying to outsmart the iron cage only surrounds the escape artist with more ornate and intricate bars.
That is, sleeper agents expect a concave relationship between their time at an organization and their power to change it. Their power to affect change in the future will be larger than the sum of all the change they could have realized earlier had they not been “sleeping.” The required intensity of the future power spike for “sleeping” to be worth it has to be even larger if we do any time discounting (wins now > wins later) or if time spent asleep works counter to the agent’s long term goal.↩︎
Every page of the article had at least one story that galled me.↩︎
This could explain other Supreme Court improprieties such as Justice Thomas’ wife’s involvement in January 6. This kind of scenario should be giving John Roberts ulcers.↩︎
They have lizard eyes, drink blood, and live in the giant hollow beneath Earth’s surfaces.↩︎
In both cases they couched their disdain with a sage scholarly concern that even though they of course love collaborative work, other less understanding, less progressive faculty at other universities would be less magnanimous.↩︎