Figure 2 compares ChatGPT’s abilities across the four criteria categories: organization, idea development, language, and conventions.

Figure 2

In a Historic House museum in Newton, Massachusetts, nine children seated at three tables configured in a U-shape are each working on their own online lesson. After their 25-minute “Pomodoro” cycle—a time-management technique designed to optimize one’s ability to focus on a specific task—they break for a variety of outdoor recreational activities, from badminton to Bananagrams.

The children are enrolled in KaiPod Learning, a program that offers small-group learning pods with access to virtual schools, in-person tutoring and support, and a variety of student-driven enrichment activities. The day I visited, many, but not all, of the students planned to join a yoga session in the afternoon.

KaiPod is among the startup pods that emerged from the height of the pandemic and that have so far survived.

In the summer of 2020, the frenzy around learning pods—also called microschools and pandemic pods—was high. As described in “The Rapid Rise of Pandemic Pods” (What Next, Winter 2021), families—including mine—were frenetically assembling or joining them out of a desire to preserve some in-person support, community, and normalcy in an otherwise abnormal year.

At the same time, equity concerns and parent shaming ran rampant. Educators, researchers, and the media worried about who would have access to these pods and whether low-income families would be left out of them.

A year later, the scene looks different. While the Delta variant has kept plans changing, people seem more interested in a return to in-person schooling. The conversation around pods hasn’t vanished, but it has quieted. Many families, including my own, pulled out of their pods last year because they found them unsustainable for any number of reasons.

And yet many pods that have an institutional structure behind them, rather than being fully parent-run, have survived. They are finding their niches and growing. Despite fears that pods would benefit only people in prosperous suburbs such as Newton, some of the most robust pod experiments have taken place in school districts disproportionately serving low-income and minority students. According to the Center for Reinventing Public Education, which collected information on 372 different learning pods during the pandemic, 36 percent of the largest urban school districts operated or sponsored learning pods during the pandemic, for example, with the majority of these focused on explicitly serving the most vulnerable students. According to CRPE, nearly 39 percent of these pods operated throughout the 2020–21 year. Only 12 percent definitively closed; it was unclear what happened to the remainder.

Some districts are seeking to continue to make use of pods to create alternative schooling arrangements that better support those children who need it the most. It’s worth monitoring to see if something more durable persists from this movement as the nation moves through a third year of interrupted schooling. Case studies from Cleveland and Boston, as well as DeKalb County in Georgia, Edgecombe County in North Carolina, and Guilford County in North Carolina, help give a deeper sense of how the pods performed and what they may facilitate in the years ahead.

Cleveland

When Cleveland declared in July of 2020 that the school year would begin remotely, community organizations—including the Cleveland Foundation, MyCom, Say Yes Cleveland, and the United Way of Cleveland—sprang into action alongside the Cleveland Municipal School District. As documented in a report, “Building Community-based Academic Learning Pods for Cleveland’s Children,” the organizations worked to open 24 pods that served 808 of Cleveland’s most vulnerable students, all but 32 of whom were enrolled in kindergarten through 8th grade. The funds were largely from philanthropic sources, although federal CARES Act funds also supported the effort.

The top reason for which parents and guardians reported enrolling students in the pods was educational support, followed by needing safe care while they worked. For some students, the pods served as an option of last resort, without which they would not have been able to attend classes online, despite the district’s distribution of computers and internet hotspots. This is because many students lived exclusively with their grandparents, who were unable to help them log on. Students in grades K–5 were particularly in need of such assistance. Other students were challenged by homelessness or utilities that were disconnected at home. Attendance at the pods was relatively high at 75 percent overall and 85 percent among the K–5 students.

Students and parents were overwhelmingly satisfied with the pod experience, with 98 percent of parents expressing appreciation. At the same time, 55 percent of parents said the pods didn’t meet students’ academic needs, but it’s hard to know how that compares to expectations or the counterfactual of what students’ academic experience would have been without the pods. Academic data from the pods hasn’t been released yet to shed light on this topic, but there are a few preliminary bright spots. The district’s data, for example, showed that the pod students logged into the district’s learning-management system more and completed more assignments than the non-pod students. Judy Willard, one of the staff members at one of the pods, reported that students were on track with their academic learning despite many having started the year 65 lessons behind.

The pods in Cleveland are not in operation for this 2021–22 school year, but the district is exploring using a pod-like structure to facilitate student-led peer-tutoring efforts.

Boston

In Boston, as in Cleveland, a group of community organizations—the YMCA of Greater Boston, Latinos for Education, Inquilinos Boricuas en Acción, and the BASE—came together through philanthropic funding to stand up 12 pods that enrolled over 165 students, 82 percent of whom identified as Black or Latinx. Eleven of the pods were in person for K–8 students, and one was virtual for high school students.

The organizations had been coordinating prior to Covid to reimagine schooling to close the opportunity gap for Boston students of color. When they launched their pods in September 2020, they had four principal goals: to offer a safe and supportive environment; create a daily structure to help students stay on track; demonstrate the benefits of students working with Black and Latinx staff; and set up a broader infrastructure to support students.

Bellwether Education, an education consultancy, studied and advised the intervention relative to those goals. There were positives and negatives. Attendance was lower than expected, and Bellwether’s forthcoming report doesn’t provide quantitative academic outcomes. On the other hand, with 95 percent of the staff identifying as Black or Latinx and 100 percent holding previous educational experience, 76 percent of parents said their child’s connection was stronger with the pod staff than with their regular school teacher. Ninety-two percent of parents further reported that they were informed by staff about their child’s day. This kind of family engagement could be a harbinger of greater academic connection and progress, although it’s hard to know given the limited data released so far.

Given the lack of a virtual schooling option in Boston for the 2021–22 school year, the pods are not continuing, but the leaders of the community organizations are seeking to find novel ways to partner with the local schools to continue providing the full set of child supports that, based on the survey data, parents appreciated.

The Future of Pods

Unlike Boston and Cleveland, some districts are actively continuing their pods.

Along with TNTP, a nonprofit education consultancy, CRPE created more in-depth partnerships with six school districts to try to create something more lasting and transformational out of the pods movement. DeKalb County School District in Georgia, for example, is using the pods to reinvent alternative schools. Alternative schools, which serve students who have dropped out or transferred from traditional schools, have historically struggled to show the value they add for students.

Edgecombe County Public Schools in North Carolina launched learning hubs last fall to help students connect to online classes and get in-person support. District leaders discovered that families valued increased flexibility around where and when learning happened, so they worked with students and teachers to design a “spoke-and-hub model.” Long-term, the district hopes this model will offer a new approach to school that builds stronger connections between school and community. In this more hybrid future of schooling, students would enroll in a brick-and-mortar or virtual school for the “hub” of their experience and then elementary and middle school students will join “spokes”—or interest-based groups—for the other time. High school students will receive tutor-like support and work at paid positions or internships.

Guildford County Public Schools, also in North Carolina, is looking to craft school days in which high school students learn for three hours in person and then have more flexible time out of school to engage in a variety of activities, including completing assignments, working, or receiving tutoring or other enrichment opportunities. The district envisions this as part of a greater overhaul of their high schools that weren’t serving many students effectively, even before Covid.

It seems unlikely that pods will be a dominant force in American schooling anytime soon. They will likely fade in influence relative to the 2020–21 school year. Yet many parents and district leaders remain intrigued by the possibilities pods create—enough so that this option will persist in some localities as one schooling choice in a broader set. Indeed, Tyton Partners, an education advisory firm, estimates that 1.5 million children are enrolled in microschools this fall. Based on the reported parent satisfaction, the pods seeded in some of these localities may continue to grow.

Michael Horn is an executive editor of Education Next, co-founder of and a distinguished fellow at the Clayton Christensen Institute for Disruptive Innovation, and senior strategist at Guild Education.

This article appeared in the Winter 2022 issue of Education Next. Suggested citation format:

Horn, M.B. (2022). Some Pods Will Outlast the Pandemic: Students, parents say they appreciate the support. Education Next, 22(1), 84-86.

Teaching Machines: The History of Personalized Learning
by Audrey Watters
2021, MIT Press, $34.95; 328 pages.

As reviewed by Michael B. Horn

For nearly a decade, Audrey Watters has cast herself as a snarky and skeptical writer about education technology. From theories of personalized learning to new education-technology companies, Watters attempts to cut down the hype and to dash hopes.

In her writings, she frequently covers the history of education, and argues that many of the ideas behind education technology and innovation are neither new nor good.

Her new book, Teaching Machines: The History of Personalized Learning, rests on these two pillars. The book presents two compelling microhistories of teaching machines sandwiched between a preface and a conclusion that attempt unsuccessfully to use those histories to contextualize—and cast doubt upon—personalized learning and today’s efforts to deploy new technology in that effort. Her big objection to personalized learning and education technology is that the two inevitably entail a crude behaviorist approach to instruction that deprives students and teachers of freedom.

Although the teaching machine is most associated with Harvard psychology professor B. F. Skinner, Watters takes the reader back to the era of President Calvin Coolidge and Ohio State Professor Sidney Pressey’s efforts to build and commercialize an “Automatic Teacher”—a machine that would allow students to answer questions, receive feedback, and, at the switch of a lever, progress only after they correctly answered the question.

Pressey’s background was in the field of standardized intelligence testing, which had become popular at the time. Although he knew much about standardized tests and textbooks, “the manufacturing of a piece of scientific equipment was something quite different,” Watters writes.

Watters presents a lengthy description of Pressey’s foibles and frustrations in commercializing his invention. It’s a history that foreshadows Skinner’s experience, and Watters makes sure the reader doesn’t miss the echoes by pointing out that would-be innovators such as Skinner ignored the past and seemed to believe that, in Watters’s words, “Surely this time, things would be different.”

Indeed, Skinner’s dramatic and futile efforts to commercialize a teaching machine weren’t much different from Pressey’s. Watters captures everything from Skinner’s behaviorist philosophy to his tone-deaf dealings with former Harvard President James Bryant Conant, as he tries to convince Conant that his teaching machine will fix American education in the wake of Sputnik. Readers also learn of Skinner’s emotional and highly erratic dealings with the Rheem Manufacturing Company, with which he had signed an agreement to produce his machine.

At times the narrative delves too deeply, in my estimation, into the minutiae and details of primary sources. Yet overall, Watters uses these sources well, and her sharp writing propels the story forward.

What Watters paints ultimately is less a story of Skinner’s device failing in the commercial marketplace for educational reasons and more a tale of flawed business models and missteps in production.

This distinction is at the root of the book’s problems, which start with its subtitle, “The History of Personalized Learning.” A book that fully covered this topic would focus not just on the history of the teaching machine—something more education innovators would do well to understand—but also on many other personalized techniques and approaches, from tutoring to Montessori education. Watters does helpfully explain why she doesn’t tackle computer-based and online education and keeps her primary focus on the era of teaching machines, but equating the movement to personalize learning with machine technology is reductionist.

The history that Watters presents is solid, but her commentary around it is at times flawed. For instance, she misunderstands why many people call traditional schools the “factory model” of education. Yes, many of the features of American education that critics often compare to factories were in fact imported from the Prussian education system. However, as David Tyack and Larry Cuban demonstrate in their timeless volume Tinkering Toward Utopia, the push to incorporate standardized testing into American schools and the use of Frederick Winslow Taylor’s principles of scientific management there were clearly inspired by America’s factories, which themselves were seen as the latest in technology. Watters acknowledges this movement but still castigates those who would call them factory-model schools.

What’s more, her extensive discussion of behaviorism could use more grounding, as her analogies break down in several places. One of her critiques of behaviorism is that it doesn’t work well. Yet she writes about how these techniques are used at Google to create personalization for individuals. It’s hard to argue that Google hasn’t been successful in this pursuit. So if personalization works in the realm of the consumer internet, as at Google, and if that success is based at least in part on behaviorism, then this would suggest that behaviorism works—which is at odds with part of the story Watters tries to tell.

She would still argue that this sort of personalization based on behaviorism is bad because it limits freedom, but research on creativity suggests that in order to be creative, one must first build knowledge and understand the rules of a domain before one can begin usefully breaking rules—particularly in adjacent or orthogonal fields. That would suggest, then, that behaviorism, while not a complete education theory, would serve certain learning purposes such as building knowledge. This, in turn, would allow for the use of skills like critical thinking and creativity.

With that said, there are significant reasons to doubt the direct transferability of behaviorism to education from the consumer internet world—which renders some of Watters’s analogies less useful. Nudges, for example, have a mixed track record in education (see “Nudging and Shoving Students Toward Success,” features, Spring 2021). Civitas Learning, a student-success company based on predictive analytics that Watters references, has largely failed, because its algorithm struggled to be useful as it scaled. At least one challenge with using artificial intelligence in education is that any mistakes an algorithm makes can derail a student’s learning and self-efficacy, whereas on the consumer internet a mistaken recommendation from Amazon or Netflix has little downside, at least for an individual customer. But these aren’t the challenges that Watters raises. Indeed, her dislike of behaviorism because of its limits on freedom leads her to recast Seymour Papert, known as a pioneer of constructionist learning, as a behaviorist.

This suggests that Watters is primarily just ranting against the use of any and all digital education technology. That sort of protest seems akin to sitting on top of a moving train and yelling stop.

Watters doesn’t get into the topic of how some of the competitors to Skinner’s teaching machine have fared. In fact, some of today’s technologies that she belittles have seen massive adoption. Khan Academy, a foil she writes about in the book, has over 100 million users—in dramatic contrast to Skinner’s experience. Age of Learning, the maker of the popular ABCmouse app and website, serves more than 50 million children. Indeed, the digitization of America’s schooling curriculum is well underway and has likely accelerated since the pandemic. Even longtime education publishers like McGraw-Hill, for example, are majority digital, not print, companies now. Whether they are successfully personalizing learning is a different question.

In her conclusion, Watters writes that the adoption of technology in education has ebbed and flowed over time; it’s “not a short-lived fad but rather a recurring trend.” This portion of the book is, in many ways, a statement of her professional career as a critic protesting technology as a detriment to individuals’ freedom. Watters cites the Freedom Schools that arose from the 1964 civil-rights project Freedom Summer as “a network of alternative education centers that offered the kind of teaching and learning that the public school system of Mississippi had refused to provide its Black population.” She goes on to say, “If we reject teaching machines and technologies of behavioral control in education, we certainly won’t be the first to do so. . . . From the history of refusal, we can see when students and teachers and communities protested attempts to engineer them, into either enlightenment or submission. From the alternatives they imagined and built—most notably, perhaps, the Freedom Schools, we can glean ways to construct and share knowledge that depend on humans rather than machines, liberating us from the efficient control of the ‘Skinner box.’ These practices privilege the much messier forms of teaching and learning, forms that are necessarily grounded in freedom and dignity.”

It is all fascinating history. But contrary to the author’s contention, the historical examples stop well short of demonstrating that today’s innovative practices will impede freedom rather than advancing it.

Michael B. Horn is executive editor of Education Next, co-founder of and distinguished fellow at the Clayton Christensen Institute for Disruptive Innovation, and senior strategist at Guild Education.