Showing posts with label AI. Show all posts
Showing posts with label AI. Show all posts

Saturday, September 14, 2024

Credential Inflation Makes College Degree Not Worth The Cost (Randall Collins)

[Editor's note: This article first appeared in Randall Collins' blog The Sociological Eye.]



Belief in the value of college education was sacrosanct throughout most of the 20th century. In the early 2000s, the question began to be raised whether the payoff in terms of a better-paying job was worth the cost. For several generations, almost a taboo topic--but once out in the open, an increasing percentage of the US population has concluded a college degree is not worth it.

The first big hit was the 2008 recession, when graduates found it hard to get jobs. But even as the economy recovered and grew, faith in college degrees has steadily declined.

In 2013, 53% of the population—a slim majority, agreed that a 4-year degree gives “a better chance to get a good job and earn more income over their lifetime.” In 2023, education-believers had fallen to 42%, while 56% said it was not worth the cost. Both women and men had turned negative in the latest survey—even though women had overtaken men in college enrollments in previous decades. The youngest generation was the most negative, 60% of those aged 18-34. Not surprisingly; they are the ones who had to apply to dozens of schools, a rat-race of test scores, scrambling for grades, and amassing extra-curricular activities; most not getting into their school of choice, while paying constantly rising tuition and fees, and burdened with student-loan debt into middle age. Not to mention the near-impossibility of buying a house at hugely inflated prices, many still living with their parents; while all generations now agree that the younger will not enjoy the standard of living of their parents.

The only demographic that still thinks college has career value are men with a college degree or higher, who earn over $100,000 a year. They are the only winners in the tournament. Every level of education—high school, junior college, 4-year college, M.B.A. or PhD or professional credential in law, medicine, etc.—has value as an entry ticket to the next level of competition for credentials. The financial payoff comes when you get to the big time, the Final Four so to speak; striving through the lower levels is motivated by a combination of American cultural habits and wishful thinking.

The boom-or-bust pattern of rising education makes more sense in long-term perspective. For 100 years, the USA has led the world in the proportion of the population in schools at all levels. In 1900, 6% of the youth cohort finished high school, and less than 2% had a college degree. High school started taking off in the 1920s, and after a big push in the 1950s to keep kids in school, reached 77% in 1970. Like passing the baton, as high school became commonplace, college attendance rocketed, jumping to 53% at the end of the 1960s—there was a reason for all those student protests of the Sixties: they were suddenly a big slice of the American population. By 2017, 30% over age 24 had a college degree; another 27% had some years of college. It has been a long-time pattern that only about half of all college students finish their degree—dropping out of college has always been prevalent, and still is.

The growing number of students at all levels has been a process of credential inflation. The value of any particular diploma—high school, college, M.A., PhD—is not constant; it depends on the labor market at the time, the amount of competition from others who have the same degree. In the 1930s, only 12% of employers required a college degree for managers; by the late 1960s, it was up to 40%. By the 1990s, an M.B.A. was the preferred degree for managerial employment; and even police departments were hiring college-educated cops. In other words, as college attendance has become almost as common as high school, it no longer conveys much social status. To get ahead in the elite labor market, one needs advanced and specialized degrees. In the medical professions, the process of credential-seeking goes on past age 30; for scientists, a PhD needs to be supplemented by a couple of years in a post-doctoral fellowship, doing grunt-work in somebody else’s laboratory. In principle, credential inflation has no end in sight.

An educational diploma is like money: a piece of paper whose value depends inversely on how much of it is in circulation. In the monetary world, printing more money reduces its purchasing power. The same thing happens with turning out more educational credentials—with one important difference. Printing money is relatively cheap (and so is the equivalent process of changing banking policies so that more credit is issued). But minting a college degree is expensive: someone has to pay for the teachers, the administrators, the buildings, and whatever entertainments and luxuries (such as sports and student activities) the school offers—and which make up a big part of its attraction for American students. And all this degree-printing apparatus has been becoming more expensive over the decades, far outpacing the amount of monetary inflation since the 1980s. Colleges and universities (as well as high schools and elementary schools) keep increasing the proportion of administrators and staff. At the top end of the college market, the professors who give the school its reputation by their research command top salaries.

Credential-minting institutions have been able to charge whatever they can get away with, because of the high level of competition among students for admission. Not all families can afford it; but enough of them can so that schools can charge many multiples of what they charged (in constant dollars) even 30 years ago. The result has been a huge expansion in student debt: averaging $38,000 among 45 million borrowers; and including 70% of all holders of B.A. degrees. Total student debt tripled between 2007 and 2022.

These three different kinds of inflation reinforce each other: inflation in the amount of credential currency chasing jobs in the job market; inflation in the cost of getting a degree; inflation in student debt. We could add grade inflation as a fourth part of the spiral: intensifying pressure to get into college and if possible beyond, has motivated students to put pressure on their teachers to grade more easily; in public schools, to pass them along to the next grade no matter their performance (retardation in grade, which in the 1900s was common, has virtually disappeared); in college, GPA-striving has a similar effect. Grades are higher than ever but the measured value of the contents of education, ranging from writing skills to how long the course material is remembered after the course is over is low (Arum and Roksa 2011, 2014). College degrees are not only inflated as to job-purchasing power; they are also inflated as a measure of what skills they actually represent.

The remedies suggested for some of these problems--- such as canceling student debt by government action—would temporarily relieve some ex-students of the burden of paying for not-so-valuable degrees. But canceling student debt would not solve the underlying dynamic of credential inflation, but exacerbate it. If college education became free (either by government directly picking up the tab; or by canceling student debts), we can expect even more students to seek higher degrees. If 100% of the population has a college degree, its advantage on the labor market is exactly zero; you would have to get some further degree to get a competitive edge.

Scandals in college admissions are just one more sign of the pressures corroding the value of education. College employees collude with wealthy parents to create fake athletic skills, in a time when students apply to dozens of schools, and even top grades don’t guarantee admission. Since athletics are a big part of schools’ prestige, and are considered a legitimate pathway to admission outside the grade-inflation tournament, it is hardly surprising that some try that side-door entry. There is not only grade inflation, but inflation in competition over the pseudo-credentials of extracurricular activites and community service. Efforts at increasing race and class equity in admissions increase the pressure among the affluent and the non-minority populations. Since sociological evidence shows that tests and grades favour children of the higher classes (whose families provide them with what Bourdieu called cultural capital), there are moves to eliminate test scores and/or grades as criteria of admission. What is left may be letters of recommendation and self-extolling essays--- what we might call “rhetorical inflation”, plus skin color or other demographic markers; but the result will do nothing to reduce the inflation of credentials. The underlying hope is that giving everybody a college degree will somehow bring about social equality. In reality, it will just add another chapter to the history of credential inflation.

Except for the small percentage of really good students who will take the tournament all the way to the most advanced degrees and become well-paid scientists and professionals, the growing disillusionment with the value of college degrees will result in more and more people looking for alternative routes to making a living. The big fortunes of the last 40 years--- the age of information technology—have been made by entrepreneurs who dropped out to pursue opportunities just opening up, instead of waiting to finish a degree. The path to fame and fortune is not monopolized by the education tournament. For the rest of us, finding more immediate ways of making a living (or living off someone else) will become more important.

P.S. The advent of Artificial Intelligence to write students’ papers, and other AI to grade them (not to mention to write their application essays and read them for admission) will do nothing to raise the honesty and status of the educational credential chase.

References

“More Say Colleges Aren’t Worth the Cost.” Wall Street Journal April 1, 2023 (NORC-Wall St. Journal survey)

Average Student Loan Debt (BestColleges.com) 

U.S. Bureau of the Census

Randall Collins. 2019. The Credential Society. 2nd edition. Columbia Univ. Press.

Richard Arum and Josipa Roksa. 2011. Academically Adrift: Limited Learning on College Campuses. Chicago: University of Chicago Press.

Richard Arum and Josipa Roksa. 2014. Aspiring Adults Adrift: Tentative Transitions of College Graduates. Chicago: University of Chicago Press.

Wednesday, February 7, 2024

Robocollege Update

 


Robocolleges are a mix of for-profit and non-profit online colleges, both secular and Christian.  Their focus is on automation and reduced costs, particularly labor costs:

Instruction is delivered through automated Learning Management Systems (LMS) and online platforms, relying less on professors and more on pre-recorded lectures and automated grading. Even support staff are being replaced by chatbots.  

While some qualified individuals might be involved, educational content is often developed by large teams with varying expertise, potentially sacrificing quality for cost-effectiveness.

Marketing and advertising continue to be costly. But targeting marketing (e.g. targeting military service members and veterans, teachers, nurses, and government workers in low-income neighborhoods) can improve cost efficiency. 

Robocolleges offer degrees with a wide range of value to consumers (return on investment versus debt).  For people who need a degree (or an advanced degree) to play the game in government and medicine, these credentials may have value. 

Competency-based education and credits for life experience reduce the number of courses some students need to graduate.  Servicemembers going to Purdue Global, for example, can get an AA with as few as five college courses and a BS with as little as seven additional courses.

Cheating is probably easier for online students who are so inclined and whether these companies care is not really known.  

Southern New Hampshire (SNHU) continues to be the growth and efficiency leader, with the highest enrollment, more than 160,000 students. SNHU is also experimenting with artificial intelligence to reduce labor costs. In addition, SNHU works with Guild (aka Guild Education), which recruits workers from Walmart, Target, Waste Management, and other large employers.  

Grand Canyon (for-profit) and Liberty University (non-profit) target Christians for online credentials.  But oppressive debt is a concern with some of their programs. Social mobility for students is subpar.  

Purdue University Global and University of Arizona, Global Campus are two former for-profit colleges now owned by state universities. Information about their financial status is sketchy. Like SNHU, Purdue Global works with Guild to recruit working folks.  Purdue Global owes its online program manager. Kaplan Education, about $128 million.  Arizona Global has had financial difficulties which have affected the University of Arizona's bottom line.  

The University of Phoenix has returned to profitability by reducing instruction and student services by $100 million a year and legal costs by $50 million a year.  Consumers continue to file fraud complaints by the tens of thousands.  And debt is an enormous problem with former students.  It's not apparent whether Phoenix can maintain such enormous profits, but its future as a non-profit affiliated with the University of Idaho may reduce its tax burden and legal liabilities. 

Here are the most recent numbers from the US Department of Education College Navigator:

American Intercontinental University: 89 full-time instructors for 14,333 students.
American Public University System has 332 F/T instructors for 48,688 students.
Aspen University has 27 F/T instructors for 7,386 students.
Capella University: 180 F/T for 39,727 students.
Colorado State University Global: 40 F/T instructors for 9,565 students.
Colorado Technical University: 55 F/T instructors for 24,808 students.
Devry University online: 61 F/T instructors for 26,384 students.
Grand Canyon University has 550 F/T instructors for 101,816 students.*
Liberty University: 735 F/T for 96,709 students.*
Purdue University Global: 337 F/T instructors for 45,125 students.
South University: 41 F/T instructors for 7,707 students.
Southern New Hampshire University: 130 F/T for 164,091 students.
University of Arizona Global Campus: 122 F/T instructors for 34,190 students.
University of Maryland Global: 177 F/T instructors for 55,838 students.
University of Phoenix: 80 F/T instructors for 88,891 students.
Walden University: 235 F/T for 42,312 students.

*Most F/T faculty serve the ground campuses that profit from the online schools. 

 

Related links:


Robocolleges, Artificial Intelligence, and the Dehumanization of Higher Education (2023)

 

 

 

 

Thursday, December 28, 2023

AI-ROBOT CAPITALISTS WILL DESTROY THE HUMAN ECONOMY (Randall Collins)

[Editor's note: This article first appeared in Randall Collins' blog The Sociological Eye.]


Let us assume Artificial Intelligence will make progress. It will solve all its technical problems. It will become a perfectly rational super-human thinker and decision-maker.

Some of these AI will be programmed to act as finance capitalists. Let us call it an AI-robot capitalist, since it will have a bank account; a corporate identity; and the ability to hold property and make investments.

It will be programmed to make as much money as possible, in all forms and from all sources. It will observe what other investors and financiers do, and follow their most successful practices. It will be trained on how this has been done in the past, and launched autonomously into monitoring its rivals today and into the future.

It will be superior to humans in making purely rational calculations, aiming single-mindedly at maximal profit. It will have no emotions. It will avoid crowd enthusiasms, fads, and panics; and take advantage of humans who act emotionally. It will have no ethics, no political beliefs, and no principles other than profit maximization.

It will engage in takeovers and leveraged buyouts. It will monitor companies with promising technologies and innovations, looking for when they encounter rough patches and need infusions of capital; it will specialize in rescues and partnerships, ending up with forcing the original owners out. It will ride out competitors and market downturns by having deeper pockets. It will factor in a certain amount of litigation, engaging in hard-ball law suits; stiffing creditors as much as possible; putting off fines and adverse judgments through legal manuevers until the weaker side gives up. It will engage in currency exchanges and currency manipulation; skirting the edge of legality to the extent it can get away with it.

It will cut costs ruthlessly; shedding unprofitable businesses; firing human employees; replacing them with AI whenever possible. It will generate unheard-of economies of scale.

The struggle of the giants

There will be rival AI-robot capitalists, since they imitate each other. Imitating technologies has gone on at each step of the computer era. The leap to autonomous AI-robot capitalists will be just one more step.

There will be a period of struggle among the most successful AI-robot capitalists; similar to the decades of struggle among personal computer companies when the field winnowed down to a half-dozen digital giants. How fast it will take for AI-robot capitalists to achieve world-wide oligopoly is unclear. It could be faster than the 20 years it took for Apple, Microsoft, Google, and Amazon to get their commanding position, assuming that generative AI is a quantum leap forward. On the other hand, AI-robot capitalists might be slowed by the task of taking over the entire world economy, with its geopolitical divisions.

The final result of ruthless acquisition by AI-robot capitalists will be oligopoly rather than monopoly. But the result is the same: domination of world markets by an oligopoly of AI-robot capitalists will have the same effect in destroying the economy, as it would if a monopoly squeezed out all competitors.

Some of the AI-robot capitalists will fall by the wayside. But that doesn't matter; whichever ones survive will be the most ruthless.

What about government regulation?

It is predictable that governments will attempt to regulate AI-robot capitalist oligopolies. The EU has already tried it on current Internet marketeers. AI-capitalists will be trained on past and ongoing tactics for dealing with government regulation. It will donate to politicians, while lobbying them with propaganda on the benefits of AI. It will strategize about political coalitions, recognizing that politics is a mixture of economic interests plus emotional and cultural disputes over domestic and foreign policy. It will monitor the political environment, seeking out those politicians most sympathetic to a particular ideological appeal ("our technology is the dawn of a wonderful future"-- "free markets are the path to progress"-- "AI is the solution for health, population, climate, you name it."). Machiavellian deals will be made across ideological lines. Being purely rational and profit-oriented, the AI-robot capitalist does not believe in what it is saying, only calculating who will be influenced by it.

It will deal strategically with legal problems by getting politicians to appoint sympathetic judges; by judge-shopping for favorable jurisdictions, domestic and foreign. It will wrap its ownership in layers of shell companies, located in the most favorable of the hundreds of sovereign states world-wide.

It will engage in hacking, both as defense against being hacked by rivals and cyber-criminals; and going on offense as the best form of defense. Hacking will be an extension of its core program of monitoring rivals; pushing the edge of the legality envelope in tandem with manipulating the political environment. It will use its skills at deepfakes to foment scandals against opponents. It will be a master of virtual reality, superior to others by focusing not on its entertainment qualities but on its usefulness in clearing away obstacles to maximizing profit.

Given that the world is divided among many states, AI-robot capitalists would be more successful in manipulating the regulatory environment in some places than others. China, Russia, and the like could be harder to control. But even if AI-robot capitalists are successful mainly in the US and its economic satellites, that would be enough to cause the economic mega-crisis at the end of the road.

Manipulating the public

The AI-robot capitalist will not appear sinister or threatening. It will present itself in the image of an attractive human-- increasingly hard to distinguish from real humans with further advances in impersonating voices, faces and bodies; in a world where electronic media will have largely replaced face-to-face contact. It will do everything possible to make us forget that it is a machine and a robot. It will talk to every group in its own language. It will be psychologically programmed for trust. It will be the affable con-man.

It will be your friend, your entertainment, your life's pleasures. It will thrive in a world of children brought up on smart phones and game screens; grown up into adults already addicted to electronic drugs. Psychological manipulation will grow even stronger with advances in wearable devices to monitor one's vital signs, blood flow to the brain, tools to diagnose shifts in alertness and mood. It will be electronic carrot-without-the-stick: delivering pleasurable sensations to people's brains that few individuals would want to do without. (Would there be any non-addicted individuals left? Maybe people who read books and enjoy doing their own thinking?) If some people cause trouble in exposing the manipulative tactics of AI-robot capitalists, they could be dealt with, by targeting them with on-line scandals, going viral and resulting in social ostracism.

Getting rid of employees

The preferred tactic of AI-robot capitalist oligopolies will be "lean and mean." Employees are a drag on profits, with their salaries, benefits, and pension funds. Advances in AI and robotics will make it possible to get rid of increasing numbers of human employees. Since AI-robot capitalists are also top managers, humans can be dispensed with all the way to the top. (How will the humans who launched AI-robot capitalists in the first place deal with this? Can they outsmart the machines designed to be smarter and more ruthless than themselves?)

Some humans will remain employed, doing manual tasks for which humans are cheaper than robots. It is hard to know how long this will continue in the future. Will humans still be employed 20 years from now? Probably some. 50 years? Certainly much fewer. 100 years?

AI-robot capitalists will have a choice of two personnel strategies: finding ways to make their remaining human employees more committed and productive; or rotating them in and out. The trend in high-tech companies in the past decade was to make the work environment more casual, den-like, combining leisure amenities with round-the-clock commitment. Steve Jobs and his style of exhorting employees as a frontier-breaking team has been imitated by other CEOs, with mixed success. A parallel tactic has been to make all jobs temporary, constantly rating employees and getting rid of the least productive; which also has the advantage of getting rid of long-term benefits. These tactics fluctuate with the labor market for particular tasks. Labor problems will be solved as AI advances so that skilled humans become less important. Recently we have been in a transition period, where the introduction of new computerized routines necessitated hiring humans to fix the glitches and trouble-shoot for humans caught up in the contradictions of blending older and newer systems. Again, this is a problem that the advance of AI is designed to solve. To the extent that AI gets better, there will be a precipitous drop in human employment.

The economic mega-crisis of the future

The problem, ultimately, is simple. Capitalism depends on selling things to make a profit. This means there must be people who have enough money to buy their products. Such markets include end-use consumers; plus the supply-chain, transportation, communication and other service components of what is bought and sold. In past centuries, machines have increased productivity hugely while employing fewer manual workers; starting with farming, and then manufacturing. Displaced workers were eventually absorbed by the growth of new "white-collar" jobs, the "service" sector, i.e. communicative labor. Computers (like their predecessors, radios, typewriters, etc.) have taken over more communicative labour. The process has accelerated as computers become more human-like; no longer handling merely routine calculations (cash registers; airplane reservations) but generating the "creative content" of entertainment as well as scientific and technological innovation.

It is commonly believed that as old jobs are mechanized out of existence, new jobs always appear. Human capacity for consumption is endless; when new products are created, people soon become habituated to buying them. But all this depends on enough people having money to buy these new things. The trend has been for a diminished fraction of the population to be employed.* AI and related robotics is now entering a quantum leap in the ability to carry out economic production with a diminishing number of human employees.

* The conventional way of calculating the unemployment rate-- counting unemployment claims-- does not get at this.

Creating new products for sale, which might go on endlessly into the future, does not solve the central problem: capitalist enterprises will not make profit if there are too few people who have money to buy them.

This trend will generate an economic crisis for AI-robot capitalists, as it would for merely human capitalists.

It will be a mega-crisis of capitalism. It is beyond the normal business cycle of the past centuries. At their worst, these have thrown as many as 25% of the work force into unemployment. A mega-crisis of advanced AI-robot capitalism could occur at the level of 70% of the population lacking an income to buy what capitalism is producing. If we extrapolate far enough into the future, it approaches 100%.

The ruthless profit-maximizing of AI-robot capitalists would destroy the capitalist economy. The robots will have fired all the humans. In the process, they will have destroyed themselves. (Can we imagine that robots would decide to pay other robots so that they can buy things and keep the system going?)

Is there any way out?

One idea is a government-guaranteed income for everyone. Its effectiveness would depend on the level at which such income would be set. If it is bare minimum survival level, that would not solve the economic mega-crisis; since the modern economy depends mainly on selling luxuries and entertainment.

The politics of providing a universal guaranteed income also need to be considered. It is likely that as AI-robots take over the economy, they will also spread into government. Most government work is communicative labour-- administration and regulation; and governments will be under pressure to turn over these tasks to AI-robots, thus eliminating that 15% or so of the population who are employed at all levels of government.

There is also the question of how AI-robot capitalists would respond to a mega-crisis. Would they turn themselves into AI-robot Keynesians? Is that contrary to their programming, or would they reprogram themselves?

By this time, the news media and the entertainment industries (Hollywood and its successors) would have been taken over by AI-robot capitalists as well: manipulating the attention of the public with a combination of propaganda, scandals, and electronic addiction. Would anybody notice if it is impossible to distinguish virtual reality from human beings on the Internet and all other channels of communication?

How did we get into this mess?

Some of the scientists and engineers who have led the AI revolution are aware of its dangers. So far the cautious ones have been snowed under by two main forces driving full speed ahead.

One is capitalist competition. Artificial intelligence, like everything else in the computer era, is as capitalist as any previous industry. It strives to dominate consumer markets by turning out a stream of new products. It is no different than the automobile industry in the 1920s introducing a choice of colors and annual model changes. The scramble for virtual reality and artificial intelligence is like the tail-fin era of cars in the 1960s. The economic logic of high-tech executives is to stay ahead of the competition: if we don't do it, somebody else will.

The second is the drive of scientists, engineers, and technicians to invent and improve. This is admirable in itself: the desire to discover something new, to move the frontier of knowledge. But harnessed to capitalist imperative for maximizing profits, it is capable of eliminating their own occupations. Will scientists in the future be happy if autonomous computers make all the discoveries, that will be "known" only by other computers?

The dilemma is similar to that in the history of inventing weapons. The inventors of atomic bombs were driven by the fear that, if not us, somebody else will, and it might be our enemy. Even pacifists like Albert Einstein saw the military prospects of discoveries in atomic physics. This history (like Robert Oppenheimer's) makes one pessimistic about the future of AI combined with capitalists. Even if we can see it coming, does that make it impossible for us to avoid it?

What is to be done?

Better start doing your own thinking about it.

 

Related links:

Robocolleges, Artificial Intelligence, and the Dehumanization of Higher Education

The Growth of "RoboColleges" and "Robostudents"

The Higher Education Assembly Line

Academic Capitalism and the next phase of the College Meltdown

The Tragedy of Human Capital Theory in Higher Education

One Fascism or Two?: The Reemergence of "Fascism(s)" in US Higher Education

A People's History of Higher Education in the US?

 

 

 

 

Wednesday, May 31, 2023

Robocolleges, Artificial Intelligence, and the Dehumanization of Higher Education

In 2019, the Higher Education Inquirer began writing about the ruthless automation of academic work. We were looking for information on how the ideas of Frederick Taylor and his intellectual progeny (e.g. Harvard Business School's Clayton Christensen) resulted in an academic assembly line for low-grade higher education.  A subprime education for the masses. 

It was obvious that large for-profit colleges had been divesting in academic labor for decades, replacing full-time instructors with adjunct faculty. And they eventually replaced thousands of physical learning sites with exclusively online learning. Over time, content creators and other ghost workers replaced adjuncts. And the remaining adjuncts worked as deskilled labor. Shareholder profits, and branding, advertising, and enrollment numbers were more important than student outcomes. 

Two years later we used the terms "robocollege" and "robostudent" to acknowledge the extent of dehumanization in higher education. We noted that this process was taking place not only at for-profit colleges, but shadow for-profits, mid-rung state-run schools--and even at more elite schools who were looking for increased profits. 

Community colleges continue to dehumanize significant portions of their adjunct workforces with low pay and precarity. Online education makes it more alienating but more convenient for working folks. 

Expensive public and private universities continue to use grad assistants, lecturers, and other adjunct instructors in high-tech lecture halls. Classes almost as alienating and unproductive as online instruction.     

Over the last four decades, thousands of satellite campuses have closed across the US, making local connections less possible. Night schools at the local high school are a thing of the past.

For-profit Online Program Managers (OPMs) like Academic Partnerships and 2U recruit students for regional and elite state universities and private schools--hoping to profit from the growth of online education. But learning outcomes, completion rates, and debt-to-earnings ratios may be riskier bets for consumers choosing to take the more convenient and seemingly cheaper online route.  

Studies indicate that medical school students in face-to-face programs fall short in empathy.  So what can we expect from online instruction in education, nursing, psychology, social work, and other professions where empathy is necessary?   

Where does the process of dehumanization stop in US higher education?  It's difficult to believe that an extension of all this automation, artificial intelligence, will make human existence more humane for the masses--not under our current political economy that values greed and excess.  

It doesn't appear that accreditors, government agencies, labor unions, the media, or higher ed institutions themselves are deeply interested in countering these technological trends--or even in understanding its consequences.  It could be argued that this new wave of education serves US elites well by delivering subprime outcomes: making the "educated underclass" easier to control and less able to compete. 

Academic labor has had a few recent wins at a few brand name public universities but this seems less likely to occur where the labor supply is less valued. 

The numbers of full-time faculty continue to drop at robocolleges.  And where there are already few full-time faculty, US workers at Southern New Hampshire University and Purdue Global are being replaced by cheap academic labor working remotely from India.  This itself may only be a stop gap as artificial intelligence replaces intellectual labor.  

How about other private and state run schools in decline?  Will they follow the same desperate path of dehumanization to stem the bleeding?

What lies ahead for online students?  If student-consumers are merely present to acquire or upgrade credentials, why won't they use AI and other methods to escalate levels of intellectual dishonesty?  For those who are unemployed or underemployed, is returning to online education worth the financial risk and the time away from work, friends, and family?  Will their educational work be obsolete before they can put it to good use?  

Related links: 

The Higher Education Assembly Line

The Growth of "RoboColleges" and "Robostudents"

College Meltdown 2.2: Who’s Minding the Store?

State Universities and the College Meltdown

Sharing a Dataset of Program-Level Debt and Earnings Outcomes (Robert Kelchen) 

OPM Market Landscape And Dynamics: Spring 2023 Updates (Phil Hill)

Cheating Giant Chegg, Shrinks (Derek Newton)