I’ve since read the book (which is weird but fascinating). The protagonist is a girl named Nell who is a pauper and victim of abuse in a dystopian world. By a stroke of luck, Nell comes to own a device that combines artificial intelligence and real human interaction to teach her all she needs to know to survive and develop a high level of intellectual capacity. The device adjusts the lessons to Nell’s moods and unique needs. Over time, she develops an exceptional vocabulary, critical physical skills (including self-defense) and a knowledge base on par with that of societal elites – which enables her to transcend the misery of her life.

Crow told the conference crowd last year: In 2030, we will have tools like this. In fact, he said, ASU and engineers elsewhere are developing them now. But if we reconvene in 2030 without figuring out how we get those kinds of tools to kids like Nell, we will have failed.

The recent and rapid advances in artificial intelligence have been on my radar for some time, but I came home from last week’s 2023 ASU-GSV conference even more certain that advances in AI via models such as GPT-4 (the latest iteration of ChatGPT) and Bing will soon be used as radically personalized learning tools like Nell’s primer. That future seemed far off in 2022 — but these tools are developing so fast, they’re not just here now; in a matter of weeks or months, they’re going to be your kid’s tutor, your teacher’s assistant and your family’s homework helper.

I attended several conference panels on AI, and one specifically on Khan Academy’s new tutoring program, Khanmigo, which is powered by GPT-4, blew me away. As Sal Khan said, he realized the power of this generation of AI: “This changes everything.” Of course, attendees discussed the safety and security risks and threats of using AI in the classroom. But what struck me was the potential for these sophisticated tools that harness the intelligence of the internet to radically personalize educational content and its delivery to each child. Educators can radically equalize education opportunities if they figure out how to ride this technological revolution effectively.

Khanmigo can do extraordinary tasks. For example, it writes with students, not for them. It gives sophisticated prompts to encourage students to think more deeply about what they’re reading or encountering, and to explain their thinking. It will soon be able to remember students’ individual histories and customize lessons and assessments to their needs and preferences. And that’s just the start. Khan described how one student reading The Great Gatsby conversed in real time with an AI version of Jay Gatsby himself to discuss the book’s imagery and symbolism. Khan said his own daughter invented a character for a story and then asked to speak to her own character — through Khanmigo — to further develop the plot.

Khanmigo — and likely other competing tools to come — also have the potential to revolutionize teaching. Right now, a teacher can use AI to develop a lesson plan, create an assessment customized to each student’s background or interests, and facilitate breakout sessions. This portends a massive shift in the teaching landscape for both K-12 and higher education — and likely even workforce training. By one account, the use of AI in colleges and universities is “beyond the point of no return.” A professor from Wharton School of Business at the conference said he actually requires his students to use AI to write their papers, but they must turn them in with a “use guide” that demonstrates how they utilized the tool and cited it appropriately. He warns students that AI will lie and that they are responsible for ensuring accuracy. The professor said he no longer accepts papers that are “less than good” because, with the aid of AI, standards are now higher for everyone.

All this feels like science fiction becoming reality, but it is just the start. You have probably heard about how GPT-4 has made shocking advances compared to the previous generation of AI. Watch how it performs on the AP Bio or the bar exam. Watch how it performs nearly all duties of an executive assistant. Watch how it writes original and pretty good poetry or essays. Kids are indeed using this tool to write their final papers this year. But the pace of development is so rapid that one panelist predicted that in a year, AI will be making its own scientific discoveries — without direction from a human scientist. The implications for the types of jobs that will disappear and emerge because of these developments are difficult to predict, but rapid change and disruption will almost certainly be the new normal. This is just the beginning. Buckle your seat belts.

To be sure, the risks are real. Questions about student privacy, safety and security are serious. Preventing plagiarism, which is virtually undetectable with GPT-4, is on every teacher’s mind. Khan is currently working with school districts to set up guardrails and help students, teachers and parents navigate these very real concerns. But a common response — to shut down or forbid the use of AI in schools — is as shortsighted and fruitless as trying to stop an avalanche by building a snowbank. This technology is unstoppable. Educators and district, state and federal leaders need to start planning now for how to maximize the opportunities for students and families and educators while minimizing the risks.

A host of policy and research questions need to be explored: What kind of guardrails are available and which are most effective? Which tools and pedagogical approaches best accelerate learning? In what ways can AI support innovations that truly move the needle for teaching and learning? Education policy leaders, ed tech developers and researchers must begin to address these issues. Quickly.

I believe AI can make the teaching profession much more effective and sustainable. It can also put an end to the ridiculous notion that one teacher must be wholly responsible for addressing every student’s learning level and individual needs. AI — combined with novel staffing models like team teaching and specialized roles being piloted in districts like Mesa, Arizona, by my colleagues at ASU — could finally allow teachers to start working in subjects they’re most suited to. Instead of fretting about the lack of high-dosage, daily tutoring, which is the best way to address learning gaps, districts and families could see an army of AI tutors available for all students across the U.S. Parents who have been frustrated with the lack of attention to their children’s needs could set up an AI tutor at home.

But to go back to Michael Crow’s message: If technology and education leaders develop these tools but do not ensure they reach the students most in need, they will have failed. The field must begin to 1) track what is happening in schools and living rooms across the country around AI and learning; 2) build a policy infrastructure and research agenda to develop and enforce safeguards and move knowledge in real time; and 3) dream big about realizing a future of learning with the aid of AI.

As CRPE’s 25^th anniversary essay series predicted in 2018, there are many things those planning for the future of education cannot know with the rise of AI: the effect of rapid climate change, natural disasters and migrations; shifting geopolitical forces; fast-rising inequalities; and racial injustices. It is clear, however, that education must change to adapt to these new realities. This must happen quickly and well if educators are to adeptly combine the positive forces of AI with powers that only the human mind possesses. To make this shift, schools will need help to transition to a more nimble and resilient system of learning pathways for students. CRPE has been writing about this transition for five years, and we are now launching a series of research studies, grant investments and convenings that bring together educators with technology developers to help navigate the path forward.

I hope that when people reconvene at ASU-GSV in 2030, AI will have been utilized so effectively to reimagine education that attendees can say they have radically customized learning for all kids like Nell. Despite the risks, using AI in classrooms could help eliminate poverty, reinvigorate the global economy, stem climate change and, potentially, help us humans co-exist more peacefully. The time is now to envision the future and begin taking steps to get there.

Robin Lake is director of the Center on Reinventing Public Education. You can find her on Twitter @RbnLake.

As the director of the Center on Reinventing Public Education, I’ve been closely following the impacts of the COVID-19 pandemic on our education system. One of the most significant impacts has been the widespread school closures, which have disrupted the education of millions of students around the world.

As we start to emerge from the pandemic and schools begin to reopen, it’s important that we focus on helping students recover from the impacts of these closures. Here are a few key ways that we can do that:

1. Prioritize mental health: The pandemic has been a stressful and unsettling time for everyone, and students are no exception. It’s important that we prioritize their mental health and well-being as they return to school. This could include providing additional support for students who are struggling, as well as incorporating mindfulness and stress-reduction techniques into the curriculum.

2. Address learning loss: Many students have experienced learning loss as a result of the pandemic, with disadvantaged students disproportionately affected. It’s important that we provide additional support to help these students catch up, whether through summer programs, tutoring or other interventions.

3. Rebuild relationships: The pandemic has disrupted the social and emotional bonds that are so important for students’ learning and development. As schools reopen, it will be important to focus on rebuilding these relationships and creating a sense of community within the classroom.

4. Flexibility: Finally, it’s important to be flexible and responsive to the needs of students as they return to school. This may mean providing additional support for those who are struggling, or offering alternative learning options for students who may not be ready to return to in-person learning.

Not bad, right? ChatGPT ended that essay with a typical high school writing crutch: “In conclusion …” and then a repeat of the same points. You’ll also notice the AI didn’t recognize that schools are, in fact, open again.

I also asked ChatGPT to write me an op-ed for The 74 on the topic of extraterrestrial education. The essay was coherent and relevant, citing the need for students to develop strong foundations in the science of supporting human life on other planets, environmental sustainability, and “intercultural communication and diplomacy.”

It’s fun to play with these bots, which can write sophisticated comparative essays and even draft legislation. My communications manager quipped when she saw these essays that she is already out of a job. My colleagues at Arizona State University are wondering how they will assess student essays for plagiarism, even next term.

If these bots, which are in their earliest and most crude state, can spit out writing like this already, what will they do in two years? How many jobs will disappear in that period alone — or shift to require radically different skill sets, higher-order thinking and the ability to collaborate with humans and robots? This is a sobering reminder that the future we wrote about five years ago for CRPE’s 25th anniversary is already here.

We said the rise of artificial intelligence and other technologies, combined with the realities of climate change and geopolitical dynamics, could lead to rising inequality, civic unrest and other chaos. On the other hand, we argued, the future is still largely within our control. If we embrace change and innovation, we can prepare the next generations of thinkers, problem solvers and leaders to not only confront the complex realities ahead, but to also discover new ways to thrive. We could try to prevent bot-written essays by confining students to pen and paper in a room with no technology. But what if, instead, we asked them to analyze the AI essays to understand why it’s important to break the rules in writing to communicate more sophisticated thoughts and ideas?

As we kick off 2023, we face the urgency of addressing the pandemic’s immediate impacts, such as learning loss. But the bot serves as a potent reminder that we will have failed this generation if we do not also use this moment to shift public education toward the future. Here’s what the bot had to say on that:

The future of work is rapidly changing, and it’s important that our education system keeps up. The jobs of tomorrow will require a combination of technical skills, critical thinking and collaboration, and our education system must adapt to meet these evolving needs.

• Read more: The future of the high school essay: We talk to 4 teachers, 2 experts and 1 AI chatbot

This is a daunting challenge, but we and others have been writing and thinking about this for several years. In my 2019 New Year’s message, a year before we at CRPE became consumed with pandemic response, I wrote that we needed to more aggressively design schools for kids who are complex learners; radically reshape the high school experience; shift more student supports to out-of-school time and community organizations; make public funds more flexible and longer-term to allow for lifetime education and career retooling; and shift oversight and accountability toward learning pathways and trained customized opportunities, such as tutoring and career training.

Today, these recommendations seem even more relevant than ever.

A version of this essay originally appeared on the CRPE blog.

As we noted in our inaugural State of the American Student report, students with disabilities lost out on critical therapies and foundational learning and socialization opportunities during the early days of the pandemic. Nearly half (44%) of parents of students with cognitive disabilities reported that schools abandoned their child’s legal right to access an equitable education when they moved to remote learning, according to Understood, a national nonprofit that supports those who think and learn differently.

To establish a baseline understanding of the impact on those students, and to begin to track progress toward helping them recover the knowledge, skills and supports they missed during the pandemic, CRPE commissioned the nonprofit Center for Learner Equity to convene a panel of experts to review the latest research. The goal was to summarize what we know, don’t know and need to know going forward to help students with disabilities.

The top line finding of our new report is — disturbingly — that we still know little about how such students are faring. Less than a third of most rigorous academic studies in the past year disaggregate outcomes for students with disabilities. Most of those few studies are limited to a specific state or locale, which means findings are hard to generalize. Nearly all the studies focus on grades 3 to 8, where state test scores are most readily available.

Scores on standardized math and English assessments declined for all students and the same is true for students with disabilities. Results from the National Assessment of Educational Progress showed somewhat sharper drops for students with disabilities than for other children. Different studies show similar or even fewer declines. But any drop in achievement for this group of students should be concerning, as they typically score below their traditionally developing peers to begin with.

We know next to nothing about post-high school outcomes like college enrollment or persistence or employment. High school graduation rates rose for students with disabilities during the pandemic, but it’s unclear if that was a good thing. Requirements were loosened for almost all students, and basic support services for the transition out of high school were fundamentally disrupted.

Another major barrier to parsing the research: Results for students with disabilities are usually reported as a monolithic block, rather than in categories that would note the variation and complexities of real children who have very different abilities and diagnoses, from emotional and behavioral disorders to physical disabilities. The research rarely divides the data to note students with disabilities who may also be facing other challenges, such as economic disadvantage, racial discrimination, or being an English learner or recent immigrant. Our State of the Student report stresses that the averages seen in these reports obscure critical variations in student needs.

The review found little, if any, research on mental health and behavioral outcomes disaggregated for students with disabilities. One exception: a study from a large urban district that shows suspension rates for children with disabilities, particularly Black boys, temporarily increased after a return to in-person learning.

Ameliorating these impacts for students with disabilities may be more difficult than for other students, our new report shows. The research indicates a spike in the number of underqualified special education teachers working in classrooms. In Pennsylvania, the number of emergency-certified special education teachers nearly doubled from 2018 to fall 2020. Nationally, 45% of schools reported at least one vacancy in special education teaching staff positions, according to new data from the National Center for Educational Statistics.

Federal special education law requires school districts to compensate students with disabilities for lost instructional or therapeutic time. But staffing challenges means many schools are likely stretched just trying to deliver regular instruction, much less compensatory services. Across the country, some districts have wrongly asserted that they are not required to compensate for pandemic-related lost instructional time. Only about one in four parents of children with disabilities have received information about compensatory services, and fewer than one in five parents said their child had received those services, according to a national survey conducted by a legal group that protects the rights of students with disabilities. Nearly nine out of 10 parents, however, reported their child experienced learning loss or regression during the pandemic.

Our panel of scholars recommended three steps policymakers can take to better help these students:

• Invest in data and research to track short- and long-term outcomes for students with disabilities and to disaggregate results to specify disability status as well as other factors like race.
• Provide technical assistance to districts struggling to meet such students’ needs.
• Identify and disseminate examples of innovative and effective strategies for educating students with disabilities.

For me, that last point is critical. New online learning tools, innovative staffing models and creative community partnerships can help schools address the immediate needs of students with disabilities. They might also help meet the needs of millions of other children who face unique learning obstacles or emotional challenges. American schools are facing wicked problems. But if educators and communities can explore and implement new approaches to help students with learning differences, the most effective changes might help build toward something better for all students, as well.

Getty Images

Anyone who cares about kids must rejoice over their being back in school with their peers. But that should not blind us to the harsh truths we have learned about our public education system, how badly it responded to the pandemic and how, as always, it served those with loud voices and political power and left those who were already struggling in school even further behind. 

What happened during the past 20 months should have been entirely predictable for anyone who was advocating for students and families before the pandemic struck.

A rigid system designed for sameness cracked under the pressure of a crisis. Despite the exhaustive work of many well-meaning people, schools and school systems were largely unable to meet individual student needs. Children who had already been struggling were subjected to even more hardship. People were rightly outraged that some students did not have access to Wi-Fi and portable devices. To many, such inequities were enough to cause them to first call for schools to remain open, then for them to remain closed.

But where was the outrage over unequal access to technology before the pandemic struck? Why were people not furious over the decades of research that shows historically marginalized students — Black, Hispanic and low-income, in particular — are taught by less effective teachers? Or the large and persistent gaps in academic outcomes by race and income?

Many were horrified to witness, via CRPE’s ongoing data collection, how slowly and badly so many school districts pivoted to remote learning and how few adopted anything akin to innovation, or even well-known, evidence-based interventions. But those who have long fought for shifts in 21st century teaching and learning simply gave each other a sad and resigned shrug.

Millions of suburban families were shocked to see union politics and outdated management systems impede even a basic functioning of services and individualized support. But low-income families, complex learners and those with a child with a disability thought, “Welcome to the party.”

It’s become cliché to say that the pandemic exposed and exacerbated inequality, so let me be more specific. Let’s look reality in the eye and not kid ourselves into thinking those inequalities were accidental when they were squarely by design.

American public schools are hardwired for inequality. Union policies and the way we fund schools ensure that students who most need the best and most effective teaching do not receive it. Lack of incentives to respond to student and family needs, combined with weak accountability for improved outcomes, means schools and districts resist, rather than embrace, individualization, adaptation and innovation.

No, what happened should not surprise us. It should, in fact, deepen our resolve for the changes that so-called reformers have been seeking for decades: high-functioning, 21st century schools and districts driven by evidence instead of politics, and immediate high-quality choices and options for those who do not have access to such schools and districts.

As we look around at the still-unfolding aftermath of the pandemic, the evidence is clear: Our students need help now. They missed many months worth of instruction and suffered socially and emotionally. We must pay them back what they are owed, and we must find a way to build a more equitable, nimble and responsive American education system.

Now more than ever, we need deep and lasting reforms. Opponents of such changes must be called out for what they are doing: standing in the way of what students need.

And yet, the so-called education reform movement was hardly moving in unison pre-pandemic. Old coalitions were flailing due in part to their own missteps and in part to fierce backlash against controversial policies necessary for change. Differences between liberals and conservatives previously seen as tolerable for a bipartisan movement became litmus tests.

It is time for a new, broader reform coalition made up of all those who saw things in the American education system during the pandemic that they cannot unsee — doctors, mental health providers, church leaders, afterschool providers, community activists, suburban parents, parents of students with disabilities and business leaders. Advocates for children must lead the way by uniting despite our differences. 

We cannot afford infighting and boutique squabbles. Education supporters from all corners must come together to align, strategize and win legislative battles in the interest of children.

Time is wasting for this generation of students, and history will repeat itself for the next generation if we do not act.

Lafer’s methodology, which has not been peer-reviewed, measures the budget impact of closing local charter schools on three hypothetical school district budgets. It makes several flawed assumptions that result in unsupported conclusions.

The study assumes that without charter schools, all the charter students within district boundaries would attend that district’s schools. Then it assumes that the district’s new tax revenue connected to those new students would exceed the cost of educating them, resulting in an improved financial picture for the district.

The questionable assumptions don’t end there.

Lafer assumes the Oakland Unified School District wouldn’t hire any new staff in its central office to help educate the 15,000 new students the district would gain if charters were closed. He also assumes no new costs for school buildings and transportation.

His low-cost estimate to educate a lot more students doesn’t even agree with Oakland Unified’s financial history.

Oakland’s enrollment in 2000-2001 was as high as it would be if all charter students returned to district schools today. Nineteen years ago, the district was beleaguered and schools were just as poorly resourced as they are today. Moreover, when enrollment grew previously in districts like Oakland, spending increased at a higher rate than revenues, not at a lower rate.

The author is trying to turn an institutional failure into an advantage — a creative approach, but not an accurate assessment.

History shows a district that is already spending more than it should on its central office and operating too many under-enrolled schools would not become more efficient if it grew significantly.

Actual district expenses rise and fall as enrollment numbers change, even though most districts find it painful to cut staff when enrollment numbers indicate they should.

The study focuses its analysis on charter school growth, ignoring other influences on district enrollment. While charter schools have drawn students away from district classrooms, so have other school districts, private schools and changes in family size. School districts must not look to one source of financial give-and-take.

The author highlights the fact that the loss of a few students sprinkled across the various grades cannot be solved by laying off any single teacher — a point that economists refer to as a “lumpiness” problem. This is a challenge for districts every fall, whether or not they have charter schools, and applies whether enrollment is growing or falling.

If this were a true cost-benefit analysis, why are the academic benefits to students not considered in the equation? A Stanford University analysis found urban charter schools in Southern California and the San Francisco Bay significantly boosted student achievement in both reading and math.

I’ve outlined specific methodological problems, but several other facts undermine Lafer’s implied claim that charter schools are to blame for district financial problems:

• Oakland, one of the three districts profiled in Lafer’s study, has had stable enrollment for the past five years — and rising revenues.
• Many California districts have financial problems and few, if any, charter schools. Clovis Unified, for example, has the 10^th largest deficit in the state and few charters.
• Many districts are financially stable, despite having a large number of charter schools, such as Albany City Unified and Capistrano Unified.
• Most California districts that encounter fiscal problems stabilize over a few short years. Long-term fiscal distress is unusual, confined to a few districts with a history of gross financial mismanagement.
• California’s own Legislative Analyst’s Office finds that the key predictors of fiscal distress in school districts are unsustainable collective bargaining agreements, failure to maintain healthy reserves, and flawed enrollment and income projections.

Financial stability is a challenge for all school systems. California has an opportunity to lead the way in developing new solutions. Transition funding, for example, could help districts make adjustments when they lose enrollment. State policies should help districts with particularly troublesome expenses, such as the long-term costs of school buildings, or retiree health care and pension costs.

Studies that suddenly blame long-standing problems in public education on charter schools make it harder to identify the real problems and potential solutions.

Robin Lake is director of the Center on Reinventing Public Education at the University of Washington Bothell.

For the fifth time in the past 10 years, LAUSD is searching for a new superintendent. The school board’s list of required qualifications likely include:

• Able to drive and execute on an academic improvement vision for more than 640,000 students.

• Able to turn around or close hundreds of low-performing schools.

• Able to head off looming bankruptcy caused by unsustainable pension, labor contracts, and central office costs.

• Able to skillfully manage the politics of an oft-divided school board and community.

The list may as well include, “Able to leap tall buildings in a single bound.”

Should LAUSD’s school board be looking for the superhero who can do all of these things? The pool of people who possess this unique mix of political, financial, and academic vision and skill is small. And most of those people know that the politically elected school board system is designed to eat them up and spit them out, not provide them the cover they need to succeed. In other words, there are few people who can do this job—and even fewer who would want it.

No wonder the average tenure for urban superintendents is about three years. Interviews with some who have taken on this “impossible job” in the past make it clear that superintendents are whipsawed by political demands and unable to mount and sustain the strategies that would create effective solutions for students. Even with a supportive school board, the boldest and most savvy superintendents can at most hope for a two-year window before a new board is voted in by those who oppose the changes. Except for superintendents who are protected by mayors or others whose hold on power is very secure, most superintendents choose between relatively short tenures marked by bold action and longer tenures sustained by caution and accommodation. As one veteran district superintendent said: “We are constantly choosing between initiatives that might work, but would get you fired, and initiatives that are too weak to do much but might survive long enough to make a little bit of difference.”

So what should LA do? The answer is not to search for a new superhero. Instead, the school board should make an impossible job possible by moving decision-making authority (and the associated politics) to the school level. School leaders should be given as much authority as possible to make the right decisions for their school—getting to choose teachers and staff, deciding how to use money and what services they pay for. A few years ago, John Deasy resigned from LAUSD after an extremely controversial district-wide purchase of iPads. Imagine instead if each school had decided which technology would best suit their needs. Deasy might still be there.

Other district leaders have gone to battle with the teachers union over things like district-wide teacher evaluation requirements. Why not let every school set their own approaches to teacher evaluation as long as they are getting results? Even cost savings issues can best be resolved at the school level. When schools control their own funds, they are much less likely to want to pay for central services.

There are challenges to moving authority to the school level. Not every principal has the skills needed today to handle their own budget and curriculum decisions. Recruiting and developing capable school-level leadership takes time, but is a much more easily solvable problem than hiring a superhero superintendent. Most importantly, giving principals the power to lead is the most effective approach to improving schools for urban students.

Managing politics and community preferences are, for good reason, a necessary part of public education. LA’s next superintendent will need the political skills to garner community support and the management skills to oversee the district. They will need to be committed to transparency, educator empowerment, and accountability. But placing the burden of managing all of the political decisions for a community like LAUSD in one person’s hands is a fool’s errand.

LA should take a lesson from Chicago, as pointed out by my colleague, Paul Hill: “The parts came together, not because a person on horseback had imposed a brilliant plan, but because over time educators gained information and the freedom to do sensible things.” The board and the new superintendent should seize this opportunity to develop a cohesive vision for citywide improvement, one that can survive leadership transitions because it is rooted in the community and in the schools themselves.

There is no escaping the fact that the woman or man who next leads LAUSD will have to make tough decisions, but their ability to do that will be stronger if they have a clear mandate for a small number of critical decisions, not a litany of politically laden ones. Superintendents come and go. School board majorities change. And top-down improvement initiatives lack the support to sustain them over time. Let’s stop the endless search for a superhero and recognize that it’s time to let schools lead.

Robin Lake is director of the Center on Reinventing Public Education as well as affiliate faculty at the School of Interdisciplinary Arts and Sciences at the University of Washington Bothell.