Wednesday, March 27, 2024

Good Online Learning Design is Good Learning Design

Associate Professor Elaine Huber,
University of Sydney
It is good to have a study which confirms, with scholarly rigor, what educators already knew: engagement is most important, with a focus on the student experience, and a supportive environment (McEwen & Huber, 2024).

What makes good teaching applies equally in a classroom, & online. It is just easier to hide bad teaching in a classroom. As an educator I have found that students are just as happy with well designed online courses as classroom based. There is plenty of research over decades to say the learning outcomes are much the same. 

Educators need to stop treating learning online as something new and novel. This is the normal way students have been learning for at least the last decade. It is just taking a long time for educators to admit this.

I first tried to teach online in 1999, shortly after joining a university faculty. Being a computer professional, I had no problem with the technology. The problem was my fixed idea as to what university teaching was: I was trying to emulate the lecture online, & failing to engage students. What I had to do was give up the idea that I was central to the student learning, and instead the student was. I then had an Epiphany, when I found myself announcing, at the end of a lecture series, it would be my last. I stopped giving lectures, & accepted a commission to prepare an online course, after being trained in vocational education techniques. After teaching vocational students, I discovered the same course content, & techniques, worked fine for university students.

Later as an online student myself, I experienced what it was like at two Australian universities, a vocational college, & a North American university. What was surprising was how achingly lonely & frustrating the experience was, how it was much the same on both sides of the Pacific, & how despite the problems, online 14,000 km from home was a better experience than being on campus at an Australian university.


McEwen, C., & Huber, E. (2024). Developing an Analytical Framework to Compare Students’ Experiences of Online Learning with Indicators of Good Online Learning Site Design. Advancing Scholarship and Research in Higher Education, 5(1).

Preparing for Solar Storms

Tom Worthington with the Telstra Tower in the distance.
Picture by Gary Ramage, Canberra Times,
published 25 March 2024. Reproduced by permission
In an interview with
The Canberra Times last week, I pointed out that space based telecommunications are vulnerable to solar storms, so terrestrial facilities such as Telstra Tower remain useful (Why Telstra Tower could save us in an apocalypse, Lucy Arundell, March 25 2024). As it happens, the Australian Space Weather Forecasting Centre (part of the Bureau of Meteorology), issued a severe space weather WATCH the day before the article was published: "The effects are expected to be significant. Increased awareness of critical infrastructure is advised." The alert was cancelled the next day. The following Tuesday I was interviewed on radio about the same topic.

My comment on solar storms was a throwaway remark, but the journalist identified it as the most interesting aspect of the interview. I often find such insights when being interviewed by journalists.

Thursday, March 21, 2024

Machine Learning, Games, Economic Systems and The End of the World

Greetings from the Australian National University where  Dr. Yun Kun Cheung is speaking on "Machine Learning in Games and Economic Systems" at the weekly AI ML & Friends seminar. One question raised was if algorithmic trading can cause stock markets to collapse, as well as deliberate attacks which incorporate algorithmic learning.

This is my second AI seminar of the day discussing the adverse effects of AI. The first was Arvind Narayanan & Sayash Kapoor (Princeton University) on "AI and Existential Risk". At question time I asked if the use of AI might be an acceptable risk, where it reduces the risk of nuclear war. As an example, the Australian Strategic Policy Institute released an article discussing the use of Australian nuclear powered submarines to defend Taiwan, and attack the Chinese mainland ("Punishing the Dragon—it’s not about Tomahawk missiles from SSNs", Malcolm Davis, 20 Mar 2024). Such a strategy risks escalating into nuclear war. As an alternative, I suggested small AI enabled drones, with limited offensive capability, could be used in place of nuclear submarines. As well as being more effective for defending, they have less capability for strategic offensive use.

Tuesday, March 19, 2024

Supporting students during placements

Dr. Romany Martin, University of Tasmania, talked just now on "Supporting allied health students during rural placements" in the regular ACEN Research Conversations webinar. It struck me how much there was in common with computer students on placements at small organisations. 

One issue not discussed was the problem of scale. Dr Martin mentioned a supervisor who personally delivered groceries to a student isolated at home with COVID-19, but you can't do that if you have many hundreds of students. One way to overcome that is with software. If provided some advice for development of the Student Practice Evaluation Form- Revised Package, produced by University of Queensland. But that is for keeping track of, and assessing, occupational therapy students on placements. Is there anything more general?

Tuesday, March 12, 2024

Catastrophic Risks in Artificial Intelligence

Greetings from the Australian National University Colloquium on Artificial Intelligence and Catastrophic Risk. Normally I attend weekly AI, ML and Friends Seminars in the ANU School of Computing, but today I am in the social sciences building, with philosophers. The colloquium is by the ANU Machine Intelligence and Normative Theory Lab. In the first presentation by Professor Seth Lazar points out that "transformer based" generative AI is less brittle: much harder to get it to produce weird results. He also claimed Google was barely able to match Chat GPT's performance. Professor Lazar argued catastrophic and current risks of AI could be addressed together, including through regulation. 

On a positive note Professor Lazar argued AI could be used to efficiently improve human welfare, more than inefficient manual systems. However, I suggest this presents a rosy view of human nature. Resources are not inequitably distributed today due to inefficiency, but because those who have the resources have made a conscious decision to deprive others of them. With an efficient AI system they could implement this deliberate inequity much more effectively. 

Some feasible catastrophic risks Professor Lazar mentioned were discovering new chemical and biological weapons, cyber attacks, and safety critical attacks. A current worry he mentioned is targeting conventional weapons using complex computer systems, as is being used in Gaza now

At question time I asked Professor Lazar what advice would give the federal government, which has announced a trial of Microsoft Copilot in 50 government agencies. He suggested a Chief AI Officer in an AI Agency to oversee this. Also he suggested funding an AI Safety Institute. He hoped that Copilot would just be used for wording letters.

Professor Lazar  used computer generated images to illustrate his talk. These were based on the poem 'The Second Coming' by William Butler Yeats. This theosophical work has echoes where I am sitting today. The location of the ANU was decided by two theosophists Walter and Marion Mahony Griffin.

Professor Cameron Domenico,
Rutgers University–Newark
Professor Lazar, will be followed by Professor Cameron Domenico, Rutgers University–Newark, and Professor David Thorstad, Vanderbilt University.

ps: If all this catastrophic risks of AI sounds excessively alarmist, consider that Australia is going to build six optionally crewed ships. Each armed with 32 missiles, these ships will be able to sail thousands of kilometers with no one on board. Given the possibility of an enemy jamming the link to the ship, it will be tempting to build in an autonomous mode. 

Saturday, March 9, 2024

SoundPEATS RunFree Lite Open Ear Headphones for Webinars

The SoundPEATS RunFree Lite Open Ear Headphones work well for webinars. I have tried a lot of headphones, earbuds, and more exotic gadgets, but these seem the most practical. The sound quality is good, they are loud enough,  easy to put on & stay in place. They don't interfere with my glasses. The battery lasts much longer than Bose Smart Glasses, for a fraction of the price. 

One great advantage over earbuds is that the controls are not, touch sensitive, and can be located with touch. Unlike ear buds I can yank the SoundPEATS off with one hand, and stuff them in a pocket. A bonus is the SoundPEATS work very well for Zoom calls, being relatively inconspicuous from the front.

Wednesday, March 6, 2024

March First Wednesday Connect

Greetings from March CBRIN First Wednesday Connect at Canberra Airport. At the moment we are hearing about how the Airport uses robot mowers. I am not sure where the robot dog fits in.

Australian Government Trial of Generative AI for Law, Education, Health, and Aged Care

The Digital Transformation Agency has announced 50 Australian Public Service (APS) agencies are conducting a 6-month trial of Copilot (Microsoft's implementation of Chat GPT), ending June 2024. Staff first take learning module. Agencies have also been given some general guidance, on Accountability, Transparency, Explainability, Privacy, Fairness, and Wellbeing. Agencies where AI could be controversial include Attorney-General's, Education, Health and Aged Care, Home Affairs, and the National Disability Insurance Agency.

A previous Australian Government got into difficulties with relatively simple technology in what was known as the "Robodebt Scheme", which resulted in several deaths. Careless application of AI has the potential to cause human misery and casualties, on a much larger scale. It is to be hoped the APS applies the technology with thought, so there is no need for a Robo 2.0 Royal Commission.

ps: As it happens I will be running ANU computer project students though some Generative AI exercises using Copilot, over the next few weeks. Some of the students are studying programming AI in depth, but this is more general on how to use it.

Open Education Week, 4-8 March 2024

Greetings from Athabasca University (AU), Canada, where I am attending an Open Education Week event on "Exploring Openness in Education 2024". The audience is mostly M.Ed. and Ed. Doc students and faculty. Am one of the alumni, having completed my MEd in 2017. The panel includes Dr. Rory McGreal, who was one of my Professors when I studied at AU. I am not actually in Canada (I have never physically been to AU), but using a video conference.

Dr. McGreal is enthusiastic on using AI to create educational content, and help teach students. Other panelists are more skeptical, and working on guidelines for this. 

ps: I hope to will have the opportunity to discuss these issues in person at OEGlobal 2024 in Brisbane, 13-15 November 2024.

pps: The audio cut out on my laptop after a few minutes, so I dialed in for the sound. I had just purchased low cost SoundPEATS RunFree Lite Open Ear Headphones. These look a bit odd, but worked remarkably well. I was inspired by Johnnie Moore, who uses a similar headset for making short philosophical videos..

Tuesday, March 5, 2024

Education and the Ripple Effect With China's Presence in SE Asia

Greetings from the Australian National University School of Regulation and Global Governance, where Associate Professor Enze Han is talking about his new book "The Ripple Effect: China's Complex Presence in Southeast Asia" (Oxford University Press, 2024). Dr. Han talked about the economic, as well as political support which China provides to countries of the region. At question time he was asked about the effects of education. He pointed out that Chinese language learning was popular in the region, but also that Chinese parents send their children to universities in the region. 

One element missing from the analysis was how this differs from that of previous growing economic powers. One of the audience asked Dr. Han about this. He pointed to South Korean influence in Vietnam.

Friday, March 1, 2024

Automated Misspelling

While I was pontificating about AI for learning this morning, my bemused colleagues were looking at the spelling mistakes in my blog. A check of the browser's list of spelling exceptions showed that somehow I had told it these were acceptable: adfvice, aemail, aletr, amagating, arile, benifit, faciliting, preditions, quailty, realise, and (worst of all) studnts. I have now deleted these and will also check the exception lists on my email. 

Australian Universities Accord Final Report: According to Generative AI

For the fun of it I asked Microsoft Copilot to summarize and critique the Australian Universities Accord Final Report. Here is what it came up with. ;-)


The Australian Universities Accord Final Report, released by the Hon Jason Clare MP, Minister for Education, contains 47 recommendations aimed at reforming higher education to meet Australia’s future skills needs. Here are the key points:

  1. Reform Goals: The report sets a vision for the next decade and beyond. It aims to enhance the higher education sector’s effectiveness and responsiveness.

  2. Workforce Qualifications: The report recommends that at least 80% of the workforce should have either a vocational education and training (VET) or university qualification by 2050Currently, this figure stands at 60%1.

  3. Long-Term Plan: The Accord Final Report provides a long-term reform plan to address the evolving demands of Australia’s workforce and economy.

For more detailed insights, you can refer to the Summary Report prepared by the Department of Education2. It outlines the themes and issues identified in the full report.

Remember, this is just a concise overview, and I recommend exploring the full report for comprehensive information.


Let’s delve into a concise critique of the Australian Universities Accord Final Report. Here are some key points to consider:

  1. Ambitious Goals: The report sets ambitious targets, such as aiming for 80% of the workforce to have either a vocational education and training (VET) or university qualification by 2050. While this goal is commendable, achieving it will require substantial effort and investment.

  2. Implementation Challenges: The report outlines several recommendations, but translating them into effective policies and practices may face challenges. Implementation across diverse universities and regions could be complex.

  3. Equity and Access: While the report emphasizes workforce qualifications, it’s essential to ensure equitable access to higher education. Addressing barriers faced by disadvantaged groups, including Indigenous students and those from low socioeconomic backgrounds, is crucial.

  4. Funding and Resources: The report doesn’t delve deeply into funding mechanisms. Sustainable funding models are essential to support quality education, research, and infrastructure.

  5. Industry Collaboration: The report highlights the need for stronger collaboration between universities and industries. However, striking the right balance without compromising academic autonomy is critical.

  6. Digital Transformation: The report acknowledges the importance of digital skills. Universities must adapt swiftly to technological advancements and prepare graduates for a rapidly changing job market.

  7. Research and Innovation: While workforce qualifications are vital, universities’ role in research, innovation, and knowledge creation should not be overshadowed. Balancing practical skills with intellectual growth is essential.

In summary, the Accord Final Report provides a roadmap, but its success hinges on effective execution, stakeholder engagement, and ongoing evaluation. Policymakers, educators, and industry leaders must collaborate to turn these recommendations into meaningful outcomes for Australia’s higher education sector.