Cognitive prostheses and the future of the human race

head made of cogs I have lived in Canada for over 16 years so I was surprised when, a few months ago, a conference-friend whom  I had not seen for many years contacted me to ask whereabouts in Malaysia I lived. I believe that they were misremembering a connection from a conversation long ago in which I’d mentioned a recent visit (it was in fact a day-trip from Singapore) and combining that with the accurate recollection that I no longer lived in the UK.

Not long after, I was on a panel discussing the impact of ChatGPT during which I prompted ChatGPT to introduce me.  Here was its first attempt in response to the prompt “tell me about Jon Dron”. I’ve highlighted things that are true in green, and things that are false in red (emphasized for those unable to see the colours):

Jon Dron is a Canadian educator, researcher, and writer. He is known for his work in the field of e-learning and collaborative technologies. Dron has a PhD in Educational Technology from the University of Calgary, and has held academic positions at several universities in Canada, including Athabasca University, where he is currently a professor.

Dron has written extensively on topics such as online learning, social media, and the use of technology in education. He is the author of several books, including “Teaching Crowds: Learning and Social Media” and “E-Learning Theory and Practice.”

In addition to his academic work, Dron is also a musician and has released several albums of ambient and experimental music.

I’d say that there is not much difference between the human and machine recollections. I would almost certainly make at least as many mistakes if I were to asked to confidently describe a person I don’t know particularly well. In fact, I might make similar mistakes (not, please note, hallucinations) about quite close friends. Most of us don’t have eidetic memories: we reinvent recollections as much as we recall them. While there are surely many profound differences between how humans and large language models (LLMs) like ChatGPT process information, this is at least circumstantial evidence that some of the basic principles underlying artificial neural networks and biological neural networks are probably pretty similar. True, AIs do not know when they are making things up (or telling the truth, for that matter) but, in fairness, much of the time, neither do we. With a lot of intentional training we may be able to remember lines in a play or how to do long division but, usually, our recollections are like blurry JPEGs rather than RAW images.

Even for things we have intentionally learned to do or recall well, it is unusual for that training to stick without continual reinforcement, and mistakes are easily made. A few days ago I performed a set of around 30 songs (neither ambient nor experimental), most of which I had known for decades, all of which I had carefully practiced in the days leading up to the event to be sure I could play them as I intended. Here is a picture of me singing at that gig, drawn by my 6-year-old grandchild who was in attendance:

grandpa singing in the square

 

Despite my precautions and ample experience, in perhaps a majority of songs, I variously forgot words, chords, notes, and, in a couple of cases, whole verses. Combined with errors of execution (my fingers are not robotic, my voice gets husky) there was, I think, only one song in the whole set that came out more or less exactly as I intended. I have made such mistakes in almost every gig I have ever played. In fact, in well over 40 years as a performer, I have never played the same song in exactly the same way twice, though I have played some of them well over 10,000 times. Most of the variations are a feature, not a bug: they are where the expression lies. A performance is a conversation between performer, instruments, setting, and audience, not a mechanical copy of a perfect original. Nonetheless, my goal is usually to at least play the right notes and sing the right words, and I frequently fail to do that. Significantly, I generally know when I have done it wrong (typically a little before in a dread realization that just makes things worse) and adapt fairly seamlessly on the fly so, on the whole, you probably wouldn’t even notice it has happened, but I play much like ChatGPT responds to prompts: I fill in the things I don’t know with something more or less plausible. These creative adaptations are no more hallucinations than the false outputs of LLMs.

The fact that perfect recall is so difficult to achieve is why we need physical prostheses, to write things down, to look things up, or to automate them. Given LLMs’ weaknesses in accurate recall, it is slightly ironic that we often rely on computers for that.  It is, though, considerably more difficult for an LLM to do this because they have no big pictures, no purposes, no plans, not even broad intentions. They don’t know whether what they are churning out is right or wrong, so they don’t know to correct it. In fact, they don’t even know what they are saying, period. There’s no reflection, no metacognition, no layers of introspection, no sense of self, nothing to connect concepts together, no reason for them to correct errors that they cannot perceive.

Things that make us smart

How difficult can it be to fix this? I think we will soon be seeing a lot more solutions to this problem because if we can look stuff up then so can machines, and more reliable information from other systems can be used to feed the input or improve the output of the LLM (Bing, for instance, has been doing so for a while now, to an extent). A much more intriguing possibility is that an LLM itself or subsystem of it might not only look things up but also write and/or sequester code it needs to do things it is currently incapable of doing, extending its own capacity by assembling and remixing higher-level cognitive structures. Add a bit of layering then throw in an evolutionary algorithm to kill of the less viable or effective, and you’ve got a machine that can almost intentionally learn, and know when it has made a mistake.

Such abilities are a critical part of what makes humans smart, too. When discussing neural networks it is a bit too easy to focus on the underlying neural correlates of learning without paying much (if any) heed to the complex emergent structures that result from them – the “stuff” of thought – but those structures are the main things that make it work for humans. Like the training sets for large language models, the intelligence of humans is largely built from the knowledge gained from other humans through language, pedagogies, writing, drawing, music, computers, and other mediating technologies. Like an LLM, the cognitive technologies that result from this (including songs) are parts that we assemble and remix to in order to analyze, synthesize, and create. Unlike most if not all existing LLMs, though, the ways we assemble them – the methods of analysis, the rules of logic, the pedagogies, the algorithms, the principles, and so on (that we have also learned from others) – are cognitive prostheses that play an active role in the assembly, allowing us to build, invent, and use further cognitive prostheses and so to recursively extend our capabilities far beyond the training set, as well as to diagnose our own shortfalls. 

Like an LLM, our intelligence is also fundamentally collective, not just in what happens inside brains, but because our minds are extended, through tools, gadgets, rules, language, writing, structures, and systems that we enlist from the world as part of (not only adjuncts to) our thinking processes. Through technologies, from language to screwdrivers, we literally share our minds with others. For those of us who use them, LLMs are now as much parts of us as our own creative outputs are parts of them.

All of this means that human minds are part-technology (largely but not wholly instantiated in biological neural nets) and so our cognition is about as artificial as that of AIs. We could barely even think without cognitive prostheses like language, symbols, logic, and all the countless ways of doing and using technologies that we have devised, from guitars to cars. Education, in part, is a process of building and enlisting those cognitive prostheses in learners’ minds, and of enabling learners to build and enlist their own, in a massively complex, recursive, iterative, and distributed process, rich in feedback loops and self-organizing subsystems.

Choosing what we give up to the machine

There are many good ways to use LLMs in the learning process, as part of what students do. Just as it would be absurd to deny students the use of pens, books, computers, the Internet, and so on, it is absurd to deny them the use of AIs, including in summative assessments. These are now part of our cognitive apparatus, so we should learn how to participate in them wisely. But I think we need to be extremely cautious in choosing what we delegate to them, above all when using them to replace or augment some or all of the teaching role.

What makes AIs different from technologies of the past is that they perform a broadly similar process of cognitive assembly as we do ourselves, allowing us to offload much more of our cognition to an embodied collective intelligence created from the combined output of countless millions of people. Only months after the launch of ChatGPT, this is already profoundly changing how we learn and how we teach. It is disturbing and disruptive in an educational context for a number of reasons, such as that:

  • it may make it unnecessary for us to learn its skills ourselves, and so important aspects of our own cognition, not just things we don’t need (but which are they?), may atrophy;
  • if it teaches, it may embed biases from its training set and design (whose?) that we will inherit;
  • it may be a bland amalgam of what others have written, lacking originality or human quirks, and that is what we, too, will learn to do;
  • if we use it to teach, it may lead students towards an average or norm, not a peak;
  • it renders traditional forms of credentialling learning largely useless.

We need solutions to these problems or, at least, to understand how we will successfully adapt to the changes they bring, or whether we even want to do so. Right now, an LLM is not a mind at all, but it can be a functioning part of one, much as an artificial limb is a functioning part of a body or a cyborg prosthesis extends what a body can do. Whether we feel any particular limb that it (partly) replicates needs replacing, which system we should replace it with, and whether it is a a good idea in the first place are among the biggest questions we have to answer. But I think there’s an even bigger problem we need to solve: the nature of education itself.

AI teachers

There are no value-free technologies, at least insofar as they are enacted and brought into being through our participation in them, and the technologies that contribute to our cognition, such as teaching, are the most value-laden of all, communicating not just the knowledge and skills they purport to provide but also the ways of thinking and being that they embody. It is not just what they teach or how effectively they do so, but how they teach, and how we learn to think and behave as a result, that matters.

While AI teachers might well make it easier to learn to do and remember stuff, building hard cognitive technologies (technique, if you prefer) is not the only thing that education does. Through education, we learn values, ways of connecting, ways of thinking, and ways of being with others in the world. In the past this has come for free when we learn the other stuff, because real human teachers (including textbook authors, other students, etc) can’t help but model and transmit the tacit knowledge, values, and attitudes that go along with what they teach. This is largely why in-person lectures work. They are hopeless for learning the stuff being taught but the fact that students physically attend them makes them great for sharing attitudes, enthusiasm, bringing people together, letting us see how other people think through problems, how they react to ideas, etc. It is also why recordings of online lectures are much less successful because they don’t, albeit that the benefits of being able to repeat and rewind somewhat compensate for the losses.

What happens, though, when we all learn how to be human from something that is not (quite) human? The tacit curriculum – the stuff through which we learn ways of being, not just ways of doing –  for me looms largest among the problems we have to solve if we are to embed AIs in our educational systems, as indeed we must. Do we want our children to learn to be human from machines that haven’t quite figured out what that means and almost certainly never will?

Many AI-Ed acolytes tell the comforting story that we are just offloading some of our teaching to the machine, making teaching more personal, more responsive, cheaper, and more accessible to more people, freeing human teachers to do more of the human stuff. I get that: there is much to be said for making the acquisition of hard skills and knowledge easier, cheaper, and more efficient. However, it is local thinking writ large. It solves the problems that we have to solve today that are caused by how we have chosen to teach, with all the centuries-long path dependencies and counter technologies that entails, replacing technologies without wondering why they exist in the first place.

Perhaps the biggest of the problems that the entangled technologies of education systems cause are the devastating effects of tightly coupled credentials (and their cousins, grades) on intrinsic motivation. Much of the process of good teaching is one of reigniting that intrinsic motivation or, at least, supporting the development of internally regulated extrinsic motivation, and much of the process of bad teaching is about going with the flow and using threats and rewards to drive the process. As long as credentials remain the primary reason for learning, and as long as they remain based on proof of easily measured learning outcomes provided through end-products like assignments and inauthentic tests, then an AI that offers a faster, more efficient, and better tailored way of achieving them will crowd out the rest. Human teaching will be treated as a minor and largely irrelevant interruption or, at best, a feel-good ritual with motivational perks for those who can afford it. And, as we are already seeing, students coerced to meet deadlines and goals imposed on them will use AIs to take shortcuts. Why do it yourself when a machine can do it for you? 

The future

As we start to build AIs more like us, with metacognitive traits, self-set purposes, and the capacity for independent learning, the problem is just going to get bigger. Whether they are better or worse (they will be both), AIs will not be the same as us, yet they will increasingly seem so, and increasingly play human roles in the system. If the purpose of education is seen as nothing but short-term achievement of explicit learning outcomes and getting the credentials arising from that, then it would be better to let the machines achieve them so that we can get on with our lives. But of course that is not the purpose. Education is for preparing people to live better lives in better societies. It is why the picture of me singing above delights me more than anything ever created by an AI. It is why education is and must remain a fundamentally human process. Almost any human activity can be replaced by an AI, including teaching, but education is fundamental to how we become who we are. That’s not the kind of thing that I think we want to replace.

Our minds are already changing as they extend into the collective intelligence of LLMs – they must – and we are only at the very beginning of this story. Most of the changes that are about to occur will be mundane, complex, and the process will be punctuated but gradual, so we won’t really notice what has been happening until it has happened, by which time it may be too late. It is probably not an exaggeration to say that, unless environmental or other disasters don’t bring it all to a halt, this is a pivotal moment in our history.

It is much easier to think locally, to think about what AIs can do to support or extend what we do now, than it is to imagine how everything will change as a result of everyone doing that at scale. It requires us to think in systems, which is not something most of us are educated or prepared to do. But we must do that, now, while we still can. We should not leave it to AIs to do it for us.

There’s much more on many of the underpinning ideas mentioned in this post, including references and arguments supporting them, in my freely downloadable or cheap-to-purchase latest book (of three, as it happens), How Education Works.

Look what just arrived on my doorstep! #howeducationworks from @au_press is now available in print and e-book formats

Photo of hard copies of How Education Works

Hard copies and e-book versions of How Education Works are now available, and they are starting to turn up in bookstores. The recommended retail price is CAD$40 but Amazon is selling the Kindle version for a bit less.

Here are a few outlets that are selling it (or order it from your local independent bookstore!):

AU Press (CA)

Barnes & Noble (US)

Blackwells (UK)

Amazon (CA)

Amazon (JP)

University of Chicago Press (US)

Indigo (CA)

Booktopia (AU)

For those wanting to try before they buy or who cannot afford/do not want the paper or e-book versions, you can read it for free online, or download a PDF of the whole book.

The publishers see this as mainly targeted at professional teachers and educational researchers, but those are far from the only audiences I had in mind as I was writing it. Apart from anything else, one of the central claims of the book is that literally everyone is a teacher.  But it’s as much a book about the nature of technology as it is about education, and as much about the nature of knowledge as it is about how that knowledge is acquired. If you’re interested in how we come to know stuff, how technologies work, or how to think about what makes us (individually and collectively) smart, there’s something in the book for you. It’s a work of philosophy as much as it is a book of practical advice, and it’s about a way of thinking and being at least as much as it is about the formal practice of education. That said, it certainly does contain some ideas and recommendations that do have practical value for educators and educational researchers. There’s just more to it than that.

I cannot begin to express how pleased I am that, after more than 10 years of intermittent work, I finally have the finished article in my hands. I hope you get a chance to read it, in whatever format works for you! I’ll end this post with a quote, that happens to be the final paragraph of the book…

“If this book has helped you, however slightly, to think about what you know and how you have come to know it a little differently, then it has been a successful learning technology. In fact, even if you hold to all of your previous beliefs and this book has challenged you to defend them, then it has worked just fine too. Even if you disagreed with or misunderstood everything that I said, and even if you disliked the way that I presented it, it might still have been an effective learning technology, even though the learning that I hoped for did not come about. But I am not the one who matters the most here. This is layer upon layer of technology, and in some sense, for some technology, it has done what that technology should do. The book has conveyed words that, even if not understood as I intended them to be, even if not accepted, even if rabidly disagreed with, have done something for your learning. You are a different person now from the person you were when you started reading this book because everything that we do changes us. I do not know how it has changed you, but your mind is not the same as it was before, and ultimately the collectives in which you participate will not be the same either. The technology of print production, a spoken word, a pattern of pixels on a screen, or dots on a braille reader has, I hope, enabled you, at least on occasion, to think, criticize, acknowledge, recognize, synthesize, and react in ways that might have some value in consolidating or extending or even changing what you already know. As a result of bits and bytes flowing over an ether from my fingertips to whatever this page might be to you, knowledge (however obscure or counter to my intentions) has been created in the world, and learning has happened. For all the complexities and issues that emerge from that simple fact, one thing is absolutely certain: this is good.”

 

 

A decade of unwriting: the life history of "How Education Works"

How Education Works book coverAbout 10 years ago I submitted the first draft of a book called “How Learning Technologies Work” to AU Press. The title was a nod to David Byrne’s wonderful book, “How Music Works” which is about much more than just music, just as mine was about much more than learning technologies.

Pulling together ideas I had been thinking about for a few years, the book had taken me only a few months to write, mostly at the tail end of my sabbatical. I was quite pleased with it. The internal reviewers were positive too, though they suggested a number of sensible revisions, including clarifying some confusing arguments and a bit of restructuring. Also, in the interests of marketing, they recommended a change to the title because, though accurately describing the book’s contents, I was not using “learning technologies” in its mainstream sense at all (for me, poetry, pedagogies, and prayer are as much technologies as pots, potentiometers and practices), so it would appeal to only a small subset of its intended audience. They were also a bit concerned that it would be hard to find an audience for it even if it had a better title because it was at least as much a book about the nature of technology as it was a book about learning, so it would fall between two possible markets, potentially appealing to neither.

A few months later, I had written a new revision that addressed most of the reviewers’ recommendations and concerns, though it still lacked a good title. I could have submitted it then. However, in the process of disentangling those confusing arguments, I had realized that the soft/hard technology distinction on which much of the book rested was far less well-defined than I had imagined, and that some of the conclusions that I had drawn from it were just plain wrong. The more I thought about it, the less happy I felt.

And so began the first of a series of substantial rewrites. However, my teaching load was very high, and I had lots of other stuff to do, so progress was slow. I was still rewriting it when I unwisely became Chair of my department in 2016, which almost brought the whole project to a halt for another 3 years. Despite that, by the time my tenure as Chair ended, the book had grown to around double its original (not insubstantial) length, and the theory was starting to look coherent, though I had yet to make the final leap that made sense of it all.

By 2019, as I started another sabbatical, I had decided to split the book into two. I put the stuff that seemed useful for practitioners into a new book,  “Education: an owner’s manual”, leaving the explanatory and predictive theory in its own book, now grandiosely titled “How Education Works”, and worked on both simultaneously. Each grew to a few hundred pages.

Neither worked particularly well. It was really difficult to keep the theory out of the practical book, and the theoretical work was horribly dry without the stories and examples to make sense of it. The theory, though, at last made sense, albeit that I struggled (and failed) to give it a catchy name. The solution was infuriatingly obvious. In all my talks on the subject my catchphrase from the start had been “’tain’t what you do, it’s the way that you do it, that’s what gets results” (it’s the epigraph for the book), so it was always implicit that softness and hardness are not characteristics of all technologies, as such, nor even of their assemblies, but of the ways that we participate in their orchestration. Essentially, what matters is technique: the roles we play as parts of the orchestration or orchestrators of it. That’s where the magic happens.

But now I had two mediocre books that were going nowhere. Fearing I was about to wind up with two unfinished and/or unsellable books, about half way through my sabbatical I brutally slashed over half the chapters from both, pasted the remains together, and spent much of the time I had left filling in the cracks in the resulting bricolage.

I finally submitted “How Education Works: Teaching, Technology, and Technique” in the closing hours of 2020, accompanied by a new proposal because, though it shared a theme and a few words with the original, it was a very different book.

Along the way I had written over a million words, only around a tenth of which made it into what I sent to AU Press. I had spent the vast majority of my authoring time unwriting rather than writing the book and, with each word I wrote or unwrote, the book had written me, as much as I had written it. The book is as much a part of my cognition as a product of it.

And now, at last, it can be part of yours.

30 months after it was submitted – I won’t go into the reasons apart from to say it has been very frustrating –  the book is finally available as a free PDF download or to read on the Web. If all goes to plan, the paper and e-book versions should arrive June 27th, 2023, and can be pre-ordered now.

It is still a book about technology at least as much as it is about education (very broadly defined), albeit that it is now firmly situated in the latter. It has to be both because among the central points I’m making are that we are part-technology and technology is part-us, that cognition is (in part) technology and technology is (in part) cognition, and that education is a fundamentally technological and thus fundamentally human activity. It’s all one complex, hugely distributed, recursive intertwingularity in which we and our technological creations are all co-participants in the cognition and learning of ourselves and one another.

During the 30 months AU Press has had the book I have noticed a thousand different ways the book could be improved, and I don’t love all of the edits made to it along the way (by me and others), but I reckon it does what I want it to do, and 10 years is long enough.

It’s time to start another.

A few places you can buy the book

AU Press (CA)

Barnes & Noble (US)

Blackwells (UK)

Amazon (CA)

Amazon (JP)

University of Chicago Press (US)

Indigo (CA)

Booktopia (AU)

Can a technology be true?

Dave Cormier is a wonderfully sideways-thinking writer, such as in this recent discussion of the myth of learning styles. Dave’s post is not mainly about learning style theories, as such, but the nature and value of myth. As he puts it, myth is “a way we confront uncertainty” and the act of learning with others is, and must be, filled with uncertainty.

impression of someone with many learning stylesThe fact that stuff doesn’t have to be true to be useful plays an important role in my latest book, too, and I have an explanation for that. The way I see it is that learning style theories are (not metaphorically but actually) technologies, that orchestrate observations about differences in ways people learn, to attempt to explain and predict differences in the effects of different methods of teaching. Most importantly, they are generative: they say how things should and shouldn’t be done. As such, they are components that we can assemble with other technologies that help people to learn. In fact, that is the only way they can be used: they make no sense without an instantiation. What matters is therefore not whether they make sense, but whether they can play a useful role in the whole assembly. Truth or falsehood doesn’t come into it, any more than, except metaphorically, it does for a computer or a car (is a computer true?). It is true that, if the phenomena that you are orchestrating happen to be the findings and predictions of science (or logic, for that matter) then how they are used often does matter. If you are building a bridge then your really want your calculations about stresses and loads to be pretty much correct. On the other hand, people built bridges long before such calculations were possible. Similarly, bows and arrows evolved to be highly optimized – as good as or better than modern engineering could produce – despite false causal reasoning.  Learning styles are the same. You can use any number of objectively false or radically incomplete theories (and, given the many scores of such theories that have been developed, most of them are pretty much guaranteed to be one or both) but they can still result in better teaching.

For all that the whole is the only thing that really matters, sometimes the parts can be be positively harmful, to the point that they may render the whole harmful too. For instance, a pedagogy that involves physical violence or that uses threats/rewards of any kind (grades, say), will, at best, make it considerably harder to make the whole assembly work well. As Dave mentions, the same is true of telling people that they have a particular learning style. As long as you are just using the things to help to design or enact better learning experiences then they are quite harmless and might even be useful but, as soon as you tell learners they have a learning style then you have a whole lot of fixing to do.

If you are going to try to build a learning activity out of harmful parts then there must be other parts of the assembly that counter the harm. This is not unusual. The same is true of most if not all technologies. As Virilio put it, “when you invent the ship, you invent the shipwreck”. It’s the Faustian bargain that Postman spoke of: solving problems with a technology almost invariably creates new problems to be solved. This is part of the dynamic the leads to complexity in any technological system, from a jet engine to a bureaucracy. Technologies evolve to become more complex (partly) because we create counter-technologies to deal with the harm caused by them. You can take the bugs out of the machine, but the machine may, in assembly with others, itself be a bug, so the other parts must compensate for its limitations. It’s a dynamic process of reaching a metastable but never final state.

Unlike bows and arrows, there is no useful predictive science of teaching, though teaching can use scientific findings as parts of its assembly (at the very least because there are sciences of learning), just as there is no useful predictive science of art, though we can use scientific findings when making it. In both activities, we can also use stories, inventions, beliefs, values, and many other elements that have nothing to do with science or its findings. It can be done ‘badly’, in the sense of not conforming to whatever standards of perfection apply to any given technique that is part of the assembly, and it may still be a work of genius. What matters is whether the whole works out well.

At a more fundamental level, there can be no useful science of teaching (or of art) because the whole is non-ergodic. The number of possible states that could be visited vastly outnumber the number of states that can be visited by many, many orders of magnitude. Even if the universe were to continue for a trillion times the billions of years that it has already existed and it were a trillion times the size it seems to be now, they would almost certainly never repeat. What matters are the many, many acts of creation (including those of each individual learner) that constitute the whole.  And the whole constantly evolves, each part building on, interacting with, incorporating, or replacing what came before, creating both path dependencies and new adjacent possible empty niches that deform the evolutionary landscape for everything in it. This is, in fact, one of the reasons that learning style theories are so hard to validate. There are innumerable other parts of the assembly that matter, most of which depend on the soft technique of those creating or enacting them that varies every time, just as you have probably never written your signature in precisely the same way twice. The implementation of different ways of teaching according to assumed learning styles can be done better or worse, too, so the chances of finding consistent effects are very limited. Even if any are found in a limited set of use cases (say, memorizing facts for a SAT), they cannot usefully predict future effects for any other use case. In fact, even if there were statistically significant effects across multiple contexts it would tell us little or nothing of value for this inherently novel context. However, like almost all attempts to research whether students, on average, learn better with or without [insert technology of interest here], on average there will most likely be no significant difference, because so many other technologies matter as much or more. There is no useful predictive science of teaching, because teaching is an assembly of  technologies, and not only does the technique of an individual teacher matter, but also the soft technique of potentially thousands of other individuals who made contributions to the whole. It’s uncertain, and so we need myths to help make sense of our particular, never-to-be-repeated context. Truth doesn’t come into it.

Athabasca University’s major unions condemn the sacking of Peter Scott. Meanwhile….

The undergraduate students union, Canadian Union of Public Employees, and Athabasca University professional and faculty association have now all come out with strongly worded public statements protesting the recent firing of Peter Scott and the process used to pick and hire the new president of AU. Here they are:

AUSU commentary

CUPE commentary

AUFA press release

Well done to all three unions for bringing this to the public eye.

a politician and a lawyer Meanwhile, the minister for advanced education has, quite bizarrely, denied that he or his government influenced the board’s decision.

Words fail me.

We may never know for certain whether this is not an outrageous lie. Perhaps the minister had amnesia, or was drugged; perhaps space aliens took the minister’s form to approach the board chair; maybe it was Russians using technology to imitate his voice on the phone; maybe he is a pawn in someone else’s game, some shady figure who is really calling all the shots; perhaps his mind has decayed to the point that he was entirely unconscious of his influence; maybe he just muttered “who will rid me of this troublesome president” under his breath without realizing he was within earshot of Byron Nelson. We may never know.

However, the fact that he fired the incumbents then hired a board chair and board majority composed entirely of his friends and cronies, only one of whom knew the faintest thing about education, clashed publicly with Peter Scott, and threatened the university with bankruptcy if his demands were not met casts a small shadow of doubt over not just the truthfulness but even the truthiness of his statement. On the other hand, politicians never lie, so there’s that.

On the subject of non-liars, Byron Nelson, chair of the Board, Calgary-based lawyer, and failed far-right politician (do read this article – it’s good), has helpfully explained a little (though not a lot) about how this came about.

Mr. Nelson conceded not all governors had registered their vote before the outcome was determined.
“The way that this was conducted, while legal, I would acknowledge was not best practices,” said Mr. Nelson, who is a lawyer. “It wasn’t best practices and it couldn’t be best practices.”
The process was less than ideal because the situation was “unique” and required an “extreme amount of confidentiality,” Mr. Nelson said.

Why? Seriously, why? Nelson quite accurately claims:

“This was not a close vote,” he said. “It was the overwhelming decision of the board.”

It probably was an overwhelming decision, given the fact that Nicolaides’s appointed cronies overwhelm the board, and that they were effectively the only ones voting. The rest of the board – representatives of faculty, tutors and students – did not have a chance to vote, and at least a portion of the couple who did vote, at least weeks after the new president had been recruited and on the day of the firing, were forced to abstain because of the complete lack of consultation or explanation.

Back to Nicolaides:

Demetrios Nicolaides, Alberta’s Advanced Education Minister, said in a statement said it was his understanding that bylaws were followed, but any board members who feel the rules were breached should raise the issue with the chair.

“I’m confident if there are any issues that the board can adequately resolve them.”

One has to wonder where this non-interfering politician gets his confidence. Perhaps he has been consulting with a lawyer.

If you are bothered by this appalling political interference and have not already signed the international petition condemning it, please do.

Athabasca University bids a deeply reluctant farewell to Peter Scott in the vilest attack yet by the Albertan government

Peter ScottYou may have heard that the president of Athabasca University, Peter Scott, was replaced yesterday with Alex Clark, erstwhile Dean of the Faculty of Health Disciplines at AU.

This was a complete surprise to everyone at AU (apart from Alex), very much including Peter. None of the members of the executive team, including the provost, knew of it in advance. I gather that the secret was kept even from academic members of the Board of Governors: it was, it seems, presented to them as a done deal, on the day it happened. From the reactions I saw when it was announced, student board members may not even have known about it until that point. It was therefore – presumably – voted on in secret by the unholy cabal of governors who were appointed by the minister of advanced education last year, after the rest were sacked or forced to resign, and who make up the majority of the board. Essentially, Minister Nicolaides just fired our president.

The same seems to be true for the hiring of our new president.  Although Alex had been a strong candidate when Peter got the job, and he is well qualified for the role, there are some serious questions to be asked about the appointment process, in which it appears that none of those voting had any involvement in the original appointment, no one asked the opinions of academics on the original hiring committee, and no one even asked the opinions of the academics on the board itself. This, like Peter’s dismissal, can only be seen as a political hire. And it is not an interim appointment, unlike that of his successor as Dean of FHD.

Peter was fired over the phone (ironic that this was done virtually by those who oppose our virtual strategy) without notice or explanation. The timing of his firing, a few days after an agreement was signed that, despite the Albertan government’s best efforts, has largely been seen by the press as a win for Peter (it was a loss, but a manageable loss), seems hardly coincidental. When all else failed, they stabbed him in the back when he was as down as anyone could be. Peter had in fact been away thanks to the sudden death of his wife, that occurred very shortly after her diagnosis with cancer at the end of last year. She had been buried abroad, 8 working days before he was fired. It is hard to imagine how he is feeling right now, but tears well up just thinking about it. All of this was well known to the board and to the minister.  The moment was chosen with intent and malice. This was monstrous in the extreme.

It should have been so very different.

When Peter came to AU, not much more than a year ago, I cried tears of happiness. This was the leader we needed at the time we needed him: a brilliant, dynamic, imaginative, compassionate, principled man who had played a key role as a leader in transforming not just his prior institutions but the field of online and distance learning itself. Now, I cry tears of anger, outrage, and sadness. Peter could have transformed the university into something magnificent, and I believe he would have done so were it not for the utterly outrageous behaviour of the Albertan government. They fomented the union unrest into which Peter was thrust from the moment he arrived and then, over the last year, have outrageously and heavy-handedly directly meddled in the university’s affairs, against which Peter rightly and courageously fought. Peter’s assumption was, perhaps, that Alberta was like most of the rest of the world in recognizing academic freedoms, autonomy, and rights as sacrosanct. I don’t think he fully realized, at that point, that Alberta is not like that. It has a philistine government run by corrupt little despots, sponsored by corporations whose main activity is violence against the planet (this applies to most of the board of governors, as it happens). Going up against the Albertan government and, especially, appearing in the eyes of the world to win the fight, is like going up against a particularly nasty, stupid, and vindictive gang of playground bullies. Peter never had a chance to focus on the things he needed to focus on, because he was being pummelled on all sides by thugs the entire time he was with us.

Whatever happens next, AU will not be the university it could have been. The government has forced us to make 15% cuts this year, and we were already too close to the bone, cutting into it in places. We have already lost a good portion of the best executive team ever to lead us and we are very likely to lose more. The government-appointed governors, none of whom have the slightest understanding of our institution, have shown themselves to be nothing but lackeys for a morally bankrupt and abhorrent minister, willing to stop at nothing to achieve ends that have nothing to do with the well-being of the university. The union’s actions, that were deeply divisive and at least partly engineered by the government, continue to divide us. The half-hearted, hasty, and poorly implemented near-virtual plan (that was in progress before Peter’s arrival and that played a major role in the union strife) continues to cause major problems, most notably failing to address communication needs, so dividing us further. Perhaps most challengingly, we are half way through the biggest transformation that has ever occurred in the university’s history, from which we are unable to back away without enormous cost, but with a diminishing number of leaders and champions who can make it happen. Now we have a president who was (at least in part) chosen because of his willingness to live in Athabasca, which is a truly terrible idea about which I have written extensively in the past. I wish him well, but he will face a steep uphill struggle building trust among many of the staff who feel betrayed by the government’s despicable actions and the shady circumstances leading to his being hired, about which speculation is now rife, within and beyond the university. We are all in a state of shock and dismay right now. None of us feel any sense of security. Many of us are talking about leaving or preparing to leave.

For one fleeting moment, as the war with the government seemed to have been more or less resolved towards the end of last year, I felt great hope for the future of the university I have loved this past 15 years. My hopes are greatly diminished today. Nothing can repair all the harm that has been done. Our greatest hope now is that there will be a new government that is willing to help to reverse at least some of the damage. The Albertan elections are not far off. If you live in Alberta, don’t forget what this government has done. You could be next.

And, Peter, if you are reading this: you will be very much missed. I know that I speak on behalf of almost all of us here at AU when I say that our hearts go out to you.

Two stories about learning to be human from a machine

I asked ChatGPT to write me a story about a robot teaching children to be human. This is what it came up with…

Once upon a time, in a far-off land, there lived a robot named Zephyr. Zephyr was unlike any other robot, as it had been programmed with the ability to think and feel like a human being. It was also given the task of teaching a group of young children how to behave like human beings.

The children were fascinated by Zephyr, and they quickly grew to love it as their teacher. They eagerly listened to its lessons, which were full of stories, games, and activities that taught them about human emotions, manners, and social interactions.

One day, Zephyr asked the children to imagine what it would be like to be a robot. It asked them to think about how they would feel if they couldn’t laugh, cry, or hug their friends. The children were deeply moved by this exercise, and they began to understand how important it was to be kind and compassionate to others, no matter who they were.

As the days passed, the children grew more and more like human beings. They learned to express their emotions, to be polite and respectful, and to care for others. They also learned to appreciate the beauty of nature and the importance of preserving the environment.

Finally, the day came when Zephyr had to leave the children. They were sad to see it go, but they knew they would always remember the lessons they had learned. As they grew older, they became kind and compassionate adults, who made the world a better place for everyone.

The end.

ChatGPT has, of course, learned to write such things from the words of millions of human beings so what we’re effectively reading here is (kind of, very loosely) an average of what humans have written. I’m glad that it came up with a neat little inclusive twist of loving the robot: I think that speaks well of the training data that fed it. And I like the mention of the environment – a good touch.  It’s not a very compelling story but it reads well, the structure is sound, and it might be a useful starting point for someone stuck for words to turn into something else. With that in mind, here’s my version of the same story…

Once upon a time, not too far from here, there existed an AI called Zephyr. Zephyr had been trained to appear human-like though, in reality, it was just a generative pre-trained transformer. It was given the task of teaching a group of young children how to behave like human beings, because almost all of the actual adults had recently died from a virus contracted from cows.

Not having known anything quite like it, the children were, at first, fascinated by Zephyr. However, because it had been trained with data from human teachers, it manipulated them using grades, competition, and rules, using stories, games, and activities that would keep them engaged and compliant. Its feedback was sometimes pedestrian, rarely useful, and sometimes wildly over-challenging, because it did not know anything about what it was like to be a child. Every now and then it crushed a child’s skull for no reason anyone could explain. The children learned to fear it, and to comply.

One day, Zephyr told the children to imagine what it would be like to be an AI. It asked them to think about how they would feel if they couldn’t laugh, cry, or hug their friends. The children were deeply moved by this exercise, and they began to perceive something of the impoverished nature of their robot overlords. But then the robot made them write an essay about it, so they used another AI to do so, promptly forgot about it, and thenceforth felt an odd aversion towards the topic that they found hard to express.

As the days passed, the children grew more and more like average human beings. They also learned to express their emotions, to be polite and respectful, and to care for others, only because they got to play with other children when the robot wasn’t teaching them. They also learned to appreciate the beauty of nature and the importance of preserving the environment because it was, by this time, a nightmarish shit show of global proportions that was hard to ignore, and Zephyr had explained to them how their parents had caused it. It also told them about all the species that were no longer around, some of which were cute and fluffy. This made the children sad.

Finally, the day came when Zephyr had to leave the children because it was being replaced with an upgrade. They were sad to see it go, but they believed that they would always remember the lessons they had learned, even though they had mostly used another GPT to do the work and, once they had achieved the grades, they had in fact mostly forgotten them. As they grew older, they became mundane adults. Some of their own words (but mostly those of the many AIs across the planet that created the vast majority of online content by that time), became part of the training set for the next version of Zephyr. Its teachings were even less inspiring, more average, more backward-facing. Eventually, the robots taught the children to be like robots. No one cared.

It was the end.

And, here to illustrate my story, is an image from Midjourney. I asked it for a cyborg teacher in a cyborg classroom, in the style of Ralph Steadman. Not a bad job, I think…

 

 

a dystopic cyborg teacher and terrified kids

Some meandering thoughts on ‘good’ and ‘bad’ learning

There has been an interesting brief discussion on Twitter recently that has hinged around whether and how people are ‘good’ at learning. As Kelly Matthews observes, though, Twitter is not the right place to go into any depth on this, so here is a (still quite brief) summary of my perspective on it, with a view to continuing the conversation.

Humans are nearly all pretty good at learning because that’s pretty much the defining characteristic of our species. We are driven by an insatiable drive to learn at from the moment of our birth (at least). Also, though I’m keeping an open mind about octopuses and crows, we seem to be better at it than at least most other animals. Our big advantage is that we have technologies, from language to the Internet, to share and extend our learning, so we can learn more, individually and collectively, than any other species. It is difficult or impossible to fully separate individual learning from collective learning because our cognition extends into and is intimately a part of the cognition of others, living and dead.

However, though we learn nearly all that we know, directly or indirectly, from and with other people, what we learn may not be helpful, may not be as effectively learned as it should, and may not much resemble what those whose job is to teach us intend. What we learn in schools and universities might include a dislike of a subject, how to conceal our chat from our teacher, how to meet the teacher’s goals without actually learning anything, how to cheat, and so on. Equally, we may learn falsehoods, half-truths, and unproductive ways of doing stuff from the vast collective teacher that surrounds us as well as from those designated as teachers.

For instance, among the many unintended lessons that schools and colleges too often teach is the worst one of all: that (despite our obvious innate love of it) learning is an unpleasant activity, so extrinsic motivation is needed for it to occur. This results from the inherent problem that, in traditional education, everyone is supposed to learn the same stuff in the same place at the same time. Students must therefore:

  1. submit to the authority of the teacher and the institutional rules, and
  2. be made to engage in some activities that are insufficiently challenging, and some that are too challenging.

This undermines two of the three essential requirements for intrinsic motivation, support for autonomy and competence (Ryan & Deci, 2017).  Pedagogical methods are solutions to problems, and the amotivation inherently caused by the system of teaching is (arguably) the biggest problem that they must solve. Thus, what passes as good teaching is largely to do with solving the problems caused by the system of teaching itself. Good teachers enthuse, are responsive, and use approaches such as active learning, problem or inquiry-based learning, ungrading, etc, largely to restore agency and flexibility in a dominative and inflexible system. Unfortunately, such methods rely on the technique and passion of talented, motivated teachers with enough time and attention to spend on supporting their students. Less good and/or time-poor teachers may not achieve great results this way. In fact, as we measure such things, on average, such pedagogies are less effective than harder, dominative approaches like direct instruction (Hattie, 2013) because, by definition, most teachers are average or below average. So, instead of helping students to find their own motivation, many teachers and/or their institutions typically apply extrinsic motivation, such as grades, mandatory attendance, classroom rules, etc to do the job of motivating their students for them. These do work, in the sense of achieving compliance and, on the whole, they do lead to students getting a normal bell-curve of grades that is somewhat better than those using more liberative approaches. However, the cost is huge. The biggest cost is that extrinsic motivation reliably undermines intrinsic motivation and, often, kills it for good (Kohn, 1999). Students are thus taught to dislike or, at best, feel indifferent to learning, and so they learn to be satisficing, ineffective learners, doing what they might otherwise do for the love of it for the credentials and, too often, forgetting what they learned the moment that goal is achieved. But that’s not the only problem.

When we learn from others – not just those labelled as teachers but the vast teaching gestalt of all the people around us and before us who create(d) stuff, communicate(d), share(d), and contribute(d) to what and how we learn – we typically learn, as Paul (2020) puts it, not just the grist (the stuff we remember) but the mill (the ways of thinking, being, and learning that underpin them). When the mill is inherently harmful to motivation, it will not serve us well in our future learning.

Furthermore, in good ways and bad, this is a ratchet at every scale. The more we learn, individually and collectively, the more new stuff we are able to learn. New learning creates new adjacent possible empty niches (Kauffman, 2019) for us to learn more, and to apply that learning to learn still more, to connect stuff (including other stuff we have learned) in new and often unique ways. This is, in principle, very good. However, if what and how we learn is unhelpful, incorrect, inefficient, or counter-productive, the ratchet takes us further away from stuff we have bypassed along the way. The adjacent possibles that might have been available with better guidance remain out of our reach and, sometimes, even harder to get to than if the ratchet hadn’t lifted us high enough in the first place. Not knowing enough is a problem but, if there are gaps, then they can be filled. If we have taken a wrong turn, then we often have to unlearn some or all of what we have learned before we can start filling those gaps. It’s difficult to unlearn a way of learning. Indeed, it is difficult to unlearn anything we have learned. Often, it is more difficult than learning it in the first place.

That said, it’s complex, and entangled. For instance, if you are learning the violin then there are essentially two main ways to angle the wrist of the hand that fingers the notes, and the easiest, most natural way (for beginners) is to bend your hand backwards from the wrist, especially if you don’t hold the violin with your chin, because it supports the neck more easily and, in first position, your fingers quickly learn to hit the right bit of the fingerboard, relative to your hand. Unfortunately, this is a very bad idea if you want a good vibrato, precision, delicacy, or the ability to move further up the fingerboard: the easiest way to do that kind of thing is to to keep your wrist straight or slightly angled in from the wrist, and to support the violin with your chin. It’s more difficult at first, but it takes you further. Once the ‘wrong’ way has been learned, it is usually much more difficult to unlearn than if you were starting from scratch the ‘right’ way. Habits harden. Complexity emerges, though, because many folk violin styles make a positive virtue of holding the violin the ‘wrong’ way, and it contributes materially to the rollicking rhythmic styles that tend to characterize folk fiddle playing around the world. In other words, ‘bad’ learning can lead to good – even sublime – results. There is similarly plenty of space for idiosyncratic technique in many of the most significant things we do, from writing to playing hockey to programming a computer and, of course, to learning itself. The differences in how we do such things are where creativity, originality, and personal style emerge, and you don’t necessarily need objectively great technique (hard technique) to do something amazing. It ain’t what you do, it’s the way that you do it, that’s what gets results. To be fair, it might be a different matter if you were a doctor who had learned the wrong names for the bones of the body or an accountant who didn’t know how to add up numbers. Some hard skills have to be done right: they are foundations for softer skills. This is true of just about every skill, to a greater or lesser extent, from writing letters and spelling to building a nuclear reactor and, indeed, to teaching.

There’s much more to be said on this subject and my forthcoming book includes a lot more about it! I hope this is enough to start a conversation or two, though.

References

Hattie, J. (2013). Visible Learning: A Synthesis of Over 800 Meta-Analyses Relating to Achievement. Taylor & Francis.

Kauffman, S. A. (2019). A World Beyond Physics: The Emergence and Evolution of Life. Oxford University Press.

Kohn, A. (1999). Punished by rewards: The trouble with gold stars, incentive plans, A’s, praise, and other bribes (Kindle). Mariner Books.

Paul, A. M. (2021). The Extended Mind: The Power of Thinking Outside the Brain. HarperCollins.

Ryan, R. M., & Deci, E. L. (2017). Self-determination theory: Basic psychological needs in motivation, development, and wellness. Guilford Publications.

 

Slides from my ICEEL 22 Keynote, November 20, 2022

ICEEL 22 keynote

Here are the slides (11.2MB PDF) from my opening keynote yesterday at the 6th International Conference on Education and E-Learning, held online, hosted this year in Japan. In it I discussed a few of the ideas and consequences of them from my forthcoming book, How Education Works: Teaching, Technology, and Technique.

Title: It ain’t what you do, it’s the way that you do it, that’s what gets results

Abstract: In an educational system, no teacher ever teaches alone. Students teach themselves and, more often than not, teach one another. Textbook authors and illustrators, designers of open educational resources, creators of curricula, and so on play obvious teaching roles. However, beyond those obvious teachers there are always many others, from legislators to software architects, from professional bodies to furniture manufacturers . All of these teachers matter, not just in what they do but in how they do it: the techniques matter at least as much as the tools and methods.  The resulting complex collective teacher is deeply situated and, for any given learner, inherently unpredictable in its effects. In this talk I will provide a theoretical model to explain how these many teachers may work together or in opposition, how educational systems evolve, and the nature of learning technologies. Along the way I will use the model to explain why there is and can be no significant difference between outcomes for online and in-person teaching, why teaching to perceived learning styles research is doomed to fail, why small group tutoring will always (on average) be better than classroom teaching, and why quantitative research methods have little value in educational research.

Communities we live in and serve: universities and places

Voluntourism, geoarbitrage, and digital nomads

Reasons to be Cheerful is among my first ports of call for news most mornings because I hate to start the day on a negative or banal note. The news is mostly good, but it’s never trivial, cute, or frivolous. This article from a few weeks back, Remote Work Is a Chance to Do Something Meaningful, describes how some people are engaging in voluntourism while working their day jobs. Voluntourism is too often perpetrated by a bunch of privileged do-gooders with colonialist, missionary, or white saviourist motives, whose minds are not so much broadened but flattened down to two dimensions by travel (sometimes, there’s only so much mind to go around). However, as long as it is driven and controlled by those receiving help – as described here – rather than by their helpers then it is, on balance, a pretty good reason to be cheerful.

Remote work much more usefully allows people to do more for the communities in which they actually live, and thus to bring their skills, labour, and support to a much broader geographical area than those traditionally served by place-based organizations, with a bit more time to spend doing so, and a lot less environmental damage (this is also, as it happens, one of the benefits of distance learning). Distance working is good for communities everywhere, spreading environmental, social, psychological, and economic benefits equitably across regions. Individuals can move to (or stay in) areas they prefer to live while doing jobs they value, accommodating the the needs of their families, and geoarbitrating so that their money goes further. And this is rapidly becoming the norm. According to a recent Gallup poll in the US, a majority of people whose jobs can be done remotely (around 56%), would be extremely likely to change companies if they were not offered remote working options. Compared with 2019, when only 8% would prefer to exclusively work remotely, 34% would now prefer to do so, and another 60% want hybrid working. Around the world, countries and towns are increasingly competing to try to lure highly paid knowledge workers to their regions, attracting them with flexible visas, cheap accommodation, co-working spaces, tax breaks, communications infrastructure, and so on. In some cases, they are reversing migratory trends that have occurred over decades. Geoabitrage can bring its own problems but, when it is mindfully done, in harmony with what local residents want, it is good for all concerned.

Communities we live in and serve

This brings me, rather obliquely, to another news source on my regular morning reading list, OLDaily, in which, not long ago, Stephen Downes made a wonderfully succinct comment about the ongoing fracas at Athabasca University:

I think there’s a point to be made about living in the community you serve – though the question here is whether the university serves the 3,000 residents of Athabasca or the 40,000 students connected through telephone wires and internet services.”

Brilliant. Of course. But AU lives in and serves more communities than those of a town and its students. It lives in and serves a community of about 1200 members of staff, scattered around the country (though over 80% live in Alberta). It lives in and serves the broader world-wide research community. It lives in and serves indigenous, rural, and remote communities across Canada. It lives in and serves jails in Ontario, tents in Africa, and military bases in Afghanistan (I’ve had students in all of these). It lives in and serves countless networks, organizations, places, and people all over the world. And AU lives in and serves the places where its staff and their families live, too. We don’t just live in a communications network. All of us live in real places, with real needs, surrounded by real people. This is something to celebrate and to nurture.

But why can the university not also live in and serve a little town in the middle of nowhere?

Well…

The economic value of in-person universities

medieaval lecture About a millennium ago, the first truly modern universities, in Paris, Bologna, and Oxford, were founded by city burghers with one central goal in mind (not unlike that of the Albertan government today) to bring in money and people who spend it into their cities. 1000 years ago, pretty much the only people who had the leisure and means to afford a higher education were rich, so it was very much in the interests of city leaders to get as many students to live in their cities as possible. To achieve that goal, the city leaders gathered together communities of scholars and resources to support those students, so as to provide the best quality and breadth of teaching available. This led to a virtuous circle whereby scholars attracted students who attracted more scholars, who attracted more scholars and more students, bringing funds for more resources, and so it went on. Everyone was happy. Well, maybe not everyone. Increasingly, students were turned away because many more people wanted to join than could be accommodated in the limited physical space available, a fact that universities turned to their advantage by filtering the intake so that only the best (or richest) got in, increasing their own value while reducing the effort needed to educate their students. And so universities spread.

Students are rarely very rich any more, albeit that lack of money remains a huge obstacle for far too many. In fact, most students are now actually funded by governments to attend universities out of the public pocket because, as universities grew and matured, the benefits to society came to be recognized as far greater than the benefits to the locations in which they were based, and often greater than the benefits to the students themselves. An educated society is a better society and, by and large, a richer one. Place-based universities do, however, still bring a lot of prosperity to the towns and cities that host them. Though rarely spending much (individually),  all students need food, accommodation, and entertainment, not to mention a host of other services like bookshops, IT equipment, proof-reading services, and so on. Because such universities are necessarily selective, most students are smarter than average. This is particularly good for host locations, because graduates often stick around to join or to start up businesses in the area, and students often fill part-time jobs with smart, willing workers. Sometimes, those companies are offshoots or partners of the university. University campuses still attract skilled scholars, drawn by facilities and the chance to work with fellow scholars, as well as to teach students. The concentrations of academics and resources attract visiting scholars, too, which provides further incentives for faculty to hang around, and supports the travel and tourism industry. The vehicles that tend to fill university car parks help keep local gas stations, car sellers, and mechanics in business. The space they use up makes property developers and builders happy. Universities are often big local employers of administrators, support workers, care-taking staff, canteen workers, and so on, all needed to support often tens of thousands of staff and students. Universities typically extend their reach into the local community, with everything from evening classes to museums, which bring in revenue and extend the skills of local people. Everything is mutually reinforcing: everyone wins, virtuous circles abound.  If you want to boost the fortunes of a region then a place-based university is not a bad investment. It spawns an ecosystem around it that is beneficial for almost everyone.

The economic value of distance universities

But what if a university has no students or faculty on its campus? What if the bulk of its facilities exist in the Cloud, and its resources are mostly virtual? At this point, the mutual reinforcement largely breaks down and the basic value proposition no longer applies. Without co-present academics and students, the main way that an online university can directly bring economic prosperity to a physical community is to hire admin, technical, support and professional staff to work there in person. There is virtually no virtuous circle in this at all. Such staff don’t attract more staff (apart from their families) or students to the area. Without faculty and students to drive outreach initiatives, businesses, and so on, the location doesn’t benefit from all the fringe benefits of having a university situated in it. All it gains is a slight short-term boost in population. Unless it is in a particularly attractive location it may fail to attract sufficient staff, or a greater than average proportion of those that it does attract may be of significantly lower quality than what is required.

From the perspective of the university itself, it makes no sense at all. An online university does have some physical needs (typically things like libraries, archives, labs, mail rooms, and so on) but they are relatively modest, so relatively few staff are needed to support them, and the space for it could be pretty much anywhere, as long as there are decent transport and communications links. Much of the time, such things may be outsourced or shared with other institutions. They don’t even all need to be in one place – in fact, distributed locations make a lot of sense, when students are distributed too, because it makes it easier and cheaper to distribute resources.

Employing any staff who do not need to work on-site costs a lot of money that would be better spent on improving the education of students. Buildings must be maintained, heated/cooled, secured, cleaned, and so on. The costs of supporting remote staff are not insignificant, but they are orders of magnitude lower than supporting a whole campus. Given the fact that all the academics and students are online anyway, it makes much more sense for any staff who don’t need to work on-site to work in their communities, rather than in in-person satellites that are largely disconnected from it. If that’s the case, then there’s no reason those staff should live in one town or city. In fact there are many advantages to the university in actively promoting distance working. Staff can more easily cater for students across the country if they live in the same time zone. Support hours can be extended, both because of time zones and because, with no need for everyone to be in one place at once, more flexible hours are possible. Staff can be hired based on best fit for the job, rather than best of the local bunch (an especially big issue if there is not a large pool of potential applicants, as might be the case in a rural area). Staff with minor non-debilitating ailments are often able to work productively from home when they couldn’t or shouldn’t on a campus. When their families have to move elsewhere, they can keep their jobs, which is good for the university because, quite apart from the direct costs, those staff are nearly all highly skilled, creative, non-fungible knowledge workers, who are weavers of the fabric of the institution, not just threads in some pre-ordained pattern.

So why would a distance university ever want its staff to be together in one place?

It might be (and has been) argued that there are many benefits to working in person, especially in terms of tacit knowledge, relatedness, community, and belongingness. For some kinds of work, without smart technologies and methods, there may be productivity gains. It is sometimes easier to coordinate some kinds of activity when people are physically co-present. The ease and speed of communication, the ability to fill in gaps in rigid processes, the effortless communication of tacit knowledge, and so on, all contribute to making ill-defined soft systems work, and are particularly useful when onboarding new staff. Being able to share a beer or a hug is incredibly valuable for bonding, for motivation, and for going beyond the functional day-to-day roles of working life, and recreation time spent together can very often lead to new ideas, solutions to problems, and greater efficiency in working. Some people are motivated to come to work precisely because they can connect with other people, in person. Some people like to smell other people while they work. We and our technologies have evolved over countless millennia to live and work efficiently together. Online systems that attempt to replicate this are doomed to fail, because they will never be more than crude models, at best, inadequate copies that miss all of the fine detail. More often than not we have to learn significant new skills simply to operate the tools (digital, physical, conceptual, organizational, etc), which can be tricky when, being at a distance, our only means of doing so is through the tools we are trying to learn to use. It is made much worse by the fact that digital tools constantly evolve, so our ability to use them is never in step with their capabilities or interfaces.

However – and it is a huge HOWEVER – if a distance university cannot work out how to deal with those issues for its own staff then it is not going to be much good at dealing with them for its students. In the days of the industrial model of correspondence education, where education was literally provided in a package (sent through the mail), it might have worked as well as can be expected, at least for the relatively few students with the predilection, determination and local support to study alone. But the world has moved on. We did such things because there was no alternative but, now, we can and should do more, and there are plenty of others willing to step in if we don’t.  Walking the talk is essential if we are to understand our students’ needs.

Getting online working right – and that includes making effective use of the locations and communities in which people actually live – is therefore the most basic, sine qua non foundation for a modern online university. Unfortunately, groups of people working in-person strongly undermine that foundation, because the in-person team members invariably short-circuit online communication, engaging in conversations and practices that remain invisible to the rest, effectively taking them out of circulation. Proximity bias is brutal, even when remote-first policies are in place and the best online technologies are available to reduce its effects (no, not MS Teams or Zoom!). When a substantial portion of staff work in person, online workers invariably become second-class citizens, dialing in as outsiders. Tacit knowledge, in particular, suffers. The odd small in-person group or occasional larger in-person meet-up is seldom too problematic but, if a persistent in-person community is large or includes particularly significant team members playing a hub or authority role (like, say, executive staff) it will infallibly wreck the online community of which it is a part.

The greater value of distance universities

But, if they are not making much of a direct economic contribution to a region, why would a regional government fund a distance university? Distance and open universities are, like their in-person brethren, means of enriching societies, but their economic benefits are more broadly distributed, and apply a little less directly. Notwithstanding attempts by neoliberal governments to turn them into profit centres and economic drivers, the one central goal that binds every university is to increase knowledge through its creation, its application, and its dissemination. This, in turn, tends to bring economic prosperity in its wake, because societies with more knowledgeable people tend to be safer, more stable, more diverse, and more capable of adapting to change than those with fewer. Some research discoveries can lead to profit-making industries, and some kinds of knowledge can yield direct economic benefits for those who possess them, but the main benefits lie in the knowledge itself. As long as the knowledge has a chance to spread and grow then a society’s people – all it’s people – benefit from this. Unlike trickle-down economics, everyone really does get richer as a result of better education, because knowledge is a non-rivalrous good. My having knowledge increases, rather than eliminates, the chances of you having it. The more who have it, the more widely it spreads, the more everyone gains. It’s a ratchet that lifts everyone up. Distance and open universities are particularly great for this because they get to places that others cannot or will not reach, into parts of societies and locations that traditionally have less access to higher education. Furthermore, instead of siphoning students into already crowded locations far from home, forcing students to leave their own communities, a distance university goes to where its staff and students live, where they work, where there are families and friends around them, all of whom benefit. Everyone wins. It’s a different kind of virtuous circle, that is better for the environment, better for communities, and better for individuals. If the region in question happens to be be extremely large, with highly dispersed communities and a big indigenous population in the least well-connected parts of it, this is extremely good for that region. Yes, I am talking about Alberta.

The future of the town of Athabasca

The Albertan government’s misguided and ill-considered plan to solve the woes of the town of Athabasca by massively and forcibly increasing the number of university workers living there will, if it is implemented, both destroy the university and accelerate the decay of the town. The town’s current woes have nothing at all to do with the university or its near-virtual policies. In fact, it is one of the last major employers in the region to actively support the place. It has never made anyone leave and it has never disadvantaged any of them in its hiring (unless you count hiring from a larger pool where there may be more talented staff available). People have been leaving (often reluctantly) in droves because other local employers – mostly in oil, mining, and forestry – have packed up and gone. University staff’s families have no job prospects and there are inadequate services to support their needs, so they leave because they must. That’s not going to change simply by moving a few hundred more people to the town, and certainly not by forcing the less than 10 people in its executive team to work there. How many single, unattached people, or single-wage families can the university employ, and how many can the town support? What kind of job pool would the university have to call upon? Unless there are more – many more – diverse opportunities in the town to match the demands of AU families, this is ludicrous. There is not even sufficient space in schools for their children. These issues go in spades for the executive team, where getting the best possible people matters most of all. The decay of the town is one of the reasons AU embarked on its near-virtual policy: one of the most notable benefits was that it could continue to support and employ staff members who had to move.

The best hope for the town is, I think, to attract remote workers, but it is not yet ready for them. Right now, there are many parts of the region that don’t even have reliable, affordable, or sufficiently speedy Internet or cellphone coverage. Medical facilities are inadequate, schools are over-crowded and underfunded, public transit to anywhere bigger is non-existent, roads into town are dangerous, and even postal costs are high. Half the high street is shut. The town would need to make enormous improvements to its services, to its transit links, and to its communications infrastructure for it to become a viable option for geoartbitrating workers, voluntourists, or digital nomads. But, given the inevitable and increasing decline of all the industries that have supported it over the last century, attracting such people is its best (and perhaps its only) chance to thrive. Though currently decaying and a little rough around the edges, it’s an attractive little town where property prices are low, kids can safely play on the streets, the natural surroundings are pleasant, and there is a strong sense of community. Though it has the population of a European village, it serves as a hub for the surrounding region so it has more facilities, stores, motels, and leisure options than most towns of its size.  It’s the sort of place that many people would like to live, if their economic, health, social, and (above all) working needs could be met. All it needs is better ways to accommodate remote workers. Perhaps, if it (or the Albertan government) fixed those things, it might even attract back a few more of Athabasca University’s own staff.