Spring in the ANU Fellows Garden

 

Greetings from the Fellows Garden at the Australian National University in Canberra. It is spring and the renovated ANU University House looks good.

Energy Beyond Bab al-Mandeb

Greetings from the ANU Energy Update 2026 subtitled "Beyond Hormuz - Australia and the new energy geopolitics". Things are moving fast in the energy sector, with the title already out of date, the geopolitics having shifted focus to the Bab al-Mandeb Strait. More locally, Anthropic has announced a $31bn data centre in western Queensland, which will require a considerable amount of energy. I am in the room at the Australian National University, but the event is also available live online. 

Taking the second point first, the Anthropic facility will likely to contract for its own renewable supply, use its own batteries, and supplement this with locally extracted gas.

Essentially, a data center is a large shed, built on a concrete pad. There will need to be a lot of plumbing for cooling, & power installed. After than racks of equipment are trucked in, bolted down & plugged in. After being built, a few people are needed to guard the premises, clean & carry out maintenance. The programmers & other software staff are elsewhere. So there will be very few long term jobs in Queensland, or Australia, from the facility. 

Some data centers dispense with the big shed & simply put the computers in shipping containers, looking much like a big battery. 

One area which might take off in Australia is plug-in solar panels. In Europe these are seen as being for balconies of apartments. However, in Australia they may become popular for detached houses. The practical limit for a plugin system is about 7 square meters of panels. This is about as much as you can hang off a balcony & as much as the household wiring can easily carry. However, adding a battery to the system could provide all the off peak energy a small home needs. One potential application would be a standalone solar carport to charge an electric car. 

ANU University House Reopening

The Australian National University is having an open Community Day on Saturday 15 August, commemorating 80 years. Registering for the event comes with the chance to win a two-night stay at the restored historic ANU University House, with dinner for two. 

The reopening of University House, marks a revival of the institution's fortunes, academic & financial. The lack of a venue where staff at all levels could freely discuss issues across the institution, contributed to governance problems. At times a leader can only be told something is a bad idea in an informal setting. Equally there is the chance to tell them what will work.

Marghanita da Cruz & Tom Worthington
at the ANU Celebration of Giving, in the
Great Hall of University House.
Photo by Adam da Cruz, 24 November 2014

University House was extensively damaged in a hailstorm in January 2020. It was not so much the loss of the great hall, or other formal areas which impeded consultation with staff, as the Fellows Bar & Fellows Garden outside. Here in the twlight, staff and graduate students would meet after work. While each table tended to be devoted to a discipline, there was interaction between them. 

AI Teaching People to Assemble Flatpack Furniture and Drones

Greetings from the School of Computing at the Australian National University, where Jiahao Zhan is explaining how videos can automatically be aligned with assembly diagrams. Anyone who has ever tried to put an Ikea flatpack together will under stand the value of this. You have a printed sheet and might even have a video demonstration, but how do they go together? Zhan's software turns the video into a set of step by step instructions. 

Zhan has spent time at Mitsubishi Electric Research Laboratories. As it happens Mitsubishi is building frigates for the Australian navy. Robot assembly could be used to speed construction. More locally, I had a technician in my home this week, trying to work out how to replace the motor in my Mitsubishi air-conditioner. ;-)

Apart from reducing the frustration with DIY, and teaching robots to assemble, this has applications in medical procedures and maintenance of safety critical infrastructure. As an example, in the past a large team of people would spend years producing maintenance training materials for a new aircraft. However, UAVs are now being designed, built and put into use within a few months, and being constantly updated. The operator needs to be able to assemble the UAV from a kit of parts in the field. Deployment can't be held up while instructional videos are produced, but correct assembly is a matter of life and death. 

ps: The seminar also demonstrated the hybrid mode. In addition to a room full of people, there were some on Zoom. At question time it was imply a matter of switching on the audio from the remote participant, so they could ask.

Improving Governance in Australian Universities

The Australian National Audit Office (ANAO) has issued a report on Australian National University Financial Management (4 June 2026). The findings (five) and recommendations (three) are remarkably short and readable. This contains useful advice for any Australian university. ANAO found the university's income is not keeping up with its costs, but there is no intimidate financial crisis. It suggests not relying on an increase in international student numbers. ANAO suggest proposals for change come with a business case. 

In my submission to the Higher Education Review, I suggested no radical change was needed to how universities and vocational institutes do educaion in Australia. However universities need to be reminded their primary mission is to provide educated professionals for the workplace, and applied research for industry, supported by fundamental research. Addressing areas of need require universities to fund some programs and defend others, adding and shedding staff. Australia can  double down on the use of online, blended, and mobile learning. This will not only provide a cost effective way to meet domestic needs, but also open up a new international market. AI needs to be incorporated in learning, but as an enabler, & a skill for graduates, but this required no fundamental change to the system.

ANU University House Reopening in August

Marghanita da Cruz & Tom Worthington
at the ANU Celebration of Giving, in the
Great Hall of University House.
Photo by Adam da Cruz, 24 November 2014

Professor Peter Kanowski, Master of University House, at the Australian National University (ANU), has announced it will reopen in August. The complex, which includes accommodation, meetings rooms, a Great Hall, restaurants, bar and gardens, has been closed since 2020. A hailstorm smashed the roof, along with those of several building on campus. Being a historic older building, restoration has taken a long time. 

I hadn't released how central University House was to the functioning of the institution, until it was closed. In my submission on the AU's draft straggly, I suggesting reopening the building be a top priority. The lack of a venue for senior executives to discuss the running of the university informally may have contributed to recent governance issues. It will also be good to have more of those magical times in the great hall.  

Online Accessibility Course Accessible Online

Tom Worthington's certificate of completion
for the Accessibility Fundamentals course
from Intopia, 18 May 2026

In support of Global Accessibility Awareness Day (GAAD), the ANU College of Systems and Society invited staff to compete a short Intopia Accessibility fundamentals online course. The course has a similar format to the "AI Literacy for All", from Digital Education Council, which I recently completed. But fortunately, the Intopia course is much, much shorter, and has closed captions, as well as transcripts for the short videos. This gives a brief introduction as to why accessibility is important and how to do it. 

The Sydney Olympics web accessibility case is mentioned in the course. As it happens I was one of the expert witnesses presenting evidence in the case. Not due to my expertise, but I was free, had a suit, & no conflict of interest. ;-)

The Beijing Olympic committee then invited me over to talk about it.  

AI for Higher Education Faculty: Course by the Digital Education Council

After congratulating myself for completing the short course "AI Literacy for All", by the Digital Education Council, I discovered there was another one "Certificate in AI for Higher Education - AI for Faculty", which perhaps I should have done instead. The "All" course was very short and simple, with content I already knew. The Faculty course is much longer (perhaps too long), with more depth (perhaps too much, with much I already knew). 

While providing a good introduction to AI for teaching staff, the course goes into too much detail on pedagogy, policy and projects. Much of this detail is material trained educators, administrators and project managers should already know. If they don't, they are only going to learn enough from a short course like this to get themselves, and their institution, into trouble. 

I suggest flipping the design: present the last section, from Singapore Management University (SMU), first. SMU provide practical techniques which educators could use to improve their teaching and reduce workload. The other material on policy and theory could be built on the back of that (or skipped for those of us already trained in it). As it is, the SMU material appears to be tacked on the end as an afterthought. Also I am still not sure exactly who, or what, the Digital Education Council is: how long has it been around, where is it based?

Synthetic Video Presentations

I had one "Wow!" moment in the course, with one video by Tamas Makany at SMU, about how to use an avatar for a training video. They explained how they used HeyGen software to create a video presentation featuring a synthetic version of themselves. It took a minute to realize that what I was looking at on the video was a an example of what was being discussed: it looked like a video of a real person. 

For several years I have been using text to speech software to create short video slide shows. These have a voice with an Australian male accent, which sounds remarkably like me. This use sa much simpler process than Dr Makany describes. I create a power-point presentation, with the narration for each slide in the notes. An online tool then turns that into a video. Being able to add a synthetic talking head would be useful. Dr. Chris Poskitt, also from SMU, described his use of a tool for adding questions to a presentation, unfortunately I couldn't work out what the tool was. The closed captions on the video were not available in English, which made it difficult. Also course system kept switching to high resolution video, which I kept switching back to low resolution, so my slow home wireless Internet modem could cope better. 

Course No Substitute for Teacher, Policy, or Project Training

The course gives a potted overview of teaching, but anyone teaching should know this stuff. There is an overview of how to do policy. There was a potted introduction on how to run an AI policy. However, as trained educator, I know about teaching and just need to know how to apply AI to this. As an experienced bureaucrat I know how to run policy processes, and don't need to be spoon fed this in an AI course. Similarly, as a certified computer professional I know how to run a project. The overviews of these areas in the course might be enough to give an untrained person the false impression they could do teaching, policy making or IT project management.

This course starts with a potted history of online learning and the application of AI to it. This history is somewhat short sighted, in that it claims online learning starts around the 1980s. I guess there isn't time for anything more detailed, but I am not sure why online learning need to be mentioned at all, as it is a separate topic from AI. You can do online learning without AI, and you can use AI for learning in a classroom. Is the Digital Education Council pushing a specific agenda? 

For me, the most significant insight from the course was the use of exiting learning tools enhanced with AI.  Tools such as drill and practice quizzes (Quizlet), lab simulations and chatbots can be created using AI. This can be done by the students themselves, with teacher guidance. This is an appealing approach, as it takes away some of the tedium creating the content for the tools, while retaining the teacher's oversight. It also involves students actively in their learning. 

More usefully Digital Education Council point to research they have done showing students across the world say they are already using AI. This is a useful wake-up call for educators who just wish AI would go away. But then some claims made I am not so sure about, for example that AI gives students instant feedback and that is a good thing. I am not so sure instant feedback is a good thing. We need to entourage students to think about the topic and the work they have done. If they get instant feedback from an apparently authoritative source, that cuts out reflection. However some of the pedagogy theory in the course is a bit dated, such as use of Bloom's Taxonomy.

The "AI Literacy for All" had videos with transcripts in multiple languages. However, this course appears to only have closed captions in English. This is a problem as I like to speed read through the transcript. Also some of the videos have no accompanying text. 

The course covers more than just Generative AI, including chatbots, which are applicable in education. In 2018 I took part in a workshop at University of Wollongong as part of the IEEE International Conference on Teaching, Assessment, and Learning for Engineering (TALE). Chi-Un Lei, Yuqian Chai, Xiangyu Hou, and Vincent Tam from University of Hong Kong, took us through using IBM Watson Assistant chatbot engine. My chatbot answered questions about an assignment deadline. It parsed the student's request for an extension and said "No". ;-) 

Some of the uses of AI proposed have ethical difficulties, such as an analysis of the student's performance across all courses and on phone calls. Other proposed uses are not new, such as analysis of the student's performance & personalization of lessons. Claims for these have been overstated. In a well design course it is possible to monitor student's performance & provide feedback via the regular assessment. 

Offering students ways to summarize their notes miss the point that the ability to summarize is one of the key ways students learn & is a skill valued by employers. 

No Dogfooding

Something which struck me a little way into my second Digital Education Council course on AI was the lack of dogfooding: that is doing what you advocate others do. That is, these are courses on how AI could be used in education, so where is the use of AI in these courses? 

Despite talking about how AI could be applied, these are very conventional online courses. There is a fixed linear structure: for each module you watch a video, read some readings, write some reflections, do a multiple choice quiz, then move to the next module. The only apparent use of AI is in some of the reflections, where the student is asked to make use of AI for an exercise ,then discuss the results. This is not necessarily a bad thing, this is a proven format for online educaion, which I am comfortable with. But where is the AI powered education DEC talks about, but doesn't do?

Something which adds to the difficulty of using AI, in association with the DEC AI courses, is that copying and pasting has been turned off in some modules. This also makes normal, non-AI study hard. Normally I would copy a question I am asked, then edit that to produce the answer, then paste it back. I would also write the answer in an editor which has spell checking. The AI courses, on my web browser, allow spell checking, but not correction. So I know I have words spelled wrong, but not what the right word is. I have a couple of goes at guessing what the correct spelling is, then give up and leave the misspelled word in. This is demoralizing and insulting for me. 

Western Blokes in Suits Bias

The early videos mostly feature a western males, in dark business suits or dark Silicon Valley expensive casual clothes. The dress standard gets more casual as the course progresses and the range of presenters increases, but there is, only one female presenter. The voices change between videos and I started to wonder if this was all AI generated, until the last more friendly and scruffy professor appeared, surprisingly from Singapore Management University. It would help if there was a more diverse range of presenters, although I must confess I am sitting here in my tweed coat, with tortoise shell glasses on. ;-)

Too Much Stuff

While talking about good education design, the course suffers from a problem common to such modules: too much stuff. The course took me weeks to do, even without the absurdly large number of optional readings. What is the point of offering a short course and then filling it with enough readings for a semester long program? 

While an experienced online student of education (seven years, three qualifications, in two countries), I struggled to keep on at this course, hour after hour, day after day, week after week. Around about the end of module 2, I started to loose the will to live. ;-)

Benefit from More Systematic Approach to Learning Design

Many of the steps recommended for use of AI in education also apply generally. To use the AI you need to know what you are teaching and how you want to assess it. Those steps also are important in education using pencil and paper.

Advertorial?

Some sections of the course described the benefits of particular products in such detail, that this started to sound like a paid advertisement for the product. 

Too Busy

While most of the course videos are slides with talking heads, a few are very busy animated product demonstrations. Text appears, a pointer moves around, windows pop up and disappear. This can be a bit overwhelming.

Weak on Privacy 

While the course repeatedly warns about privacy it demonstrates many tools which are hosted in the cloud in the USA. For institutions in Australia, Europe, and other parts of the world with privacy legislation, this makes them unusable.

Questions Require Knowledge Not in the Course

Several times the multiple choice questions ask about topics I don't remember being in the course. Perhaps I am just not a very attentive student, but perhaps the course was revised, material deleted and the questions not updated. As a student this was disconcerting, but generally I could guess the correct answer, by eliminating all the implausible options.

AI for Transfer Credit

One example which got my attention was AI course transfer credit.  I volunteered to help assess students applications for course credit. Eight long years later, I am still "temporarily" doing this thankless task. ;-)

If AI could be used to help assess course credit that would reduce the drudgery of the task, and as the course points out, improve equity.

Students not concerned about value for money

There are some interesting results from the Digital Education Council's survey of students internationally, although it was a relatively small number of students. What I found surprising was the concern about the value and value for money of their degree was the least of their worries, when it came to AI. Privacy was the top concern, which is not what I expected. A survey of staff had even fewer participants and while views of AI were more for than against, it is likely there is respondent bias in this survey (those keen on AI would be more likely to complete it).

Integrity?

The section of the course on integrity goes far beyond just AI and could be omitted. As an example, fake certificates used for enrollment predates AI by thousands of years. AI didn't cause this problem, even if it makes the problem worse. Solving the problem is not for educators to do.

No document presented by the student can be trusted. In every case you have to check with the institution it clams to be from if they really got those results. Some institutions have difficulty with this. When enrolling in Canada, I proudly presented my digital certificate from ANU. But I was asked for a certified paper copy. I had to pay to have this printed, signed, placed in an envelope, seals placed over the envelope seams, the seals each signed, placed in another envelope and couriered to Canada. This was accepted happily, but was all nonsense, as I could have easily faked it. 

One section of the course cited multiple universities who have decided Turnitin can't detect AI use. This is hardly a revelation, as anyone who has spent a few minutes trying it will see. ANU turned off Turnitin's AI detector on 1 January 2024.

Building AI

The section on building AI was unnecessary, and wrong, in parts. AI is a specialized form of IT and so IT professionals are needed for this. But the course suggests academics can build an AI system themselves, without mentioning of needing competent professionals. This is dangerous advice.

The second option for was for academics to do an AI startup, that is inventing the AI yourself, which is just silly. This is the equivalent of a catering company needing a computer, so soldering one together. While one company once did that 75 years ago, it is not an approach needed today. ;-)

The third option presented was to cooperate with corporations and startups, but without mentioning this is a high risk strategy (about 75% of computer projects fail). The most obvious, low risk, sensible option is not mentioned, which is to simply buy an AI service. There is no need to built it, invent it, collaborate, just buy an already built product. 

As an computer professional, I am often asked for recommendations on software and hardware. My advice is to buy what your friends and colleagues use. What you buy will be more likely to work and when you have problems you can ask people you know for help. The mistake many individuals and organisations make is to buy something new, on the assumption it must be better.

Decentralization

The course warns of the problems of decentralization, with different parts of the university having different approaches to AI, thus confusing the students. In a way this is understating the problem, with different instructors having different approaches: the decentralization goes all the way down to the individual. 

On the other hand decentralization doesn't matter so much to the student, as the university is just one organisation they have to deal with. At one point I was enrolled in two universities and a vocational education college at the same time, each with its own rules and timetables. Students will almost all be working so exposed to at least two sets of AI rules, one of their employer and the other where they are studying.

Guidelines

The section of the course on university guidelines was useful, as it included many examples, including an Australian one. 

Communication

The course got a little silly when it suggested communicating AI policy by email, intranet and web pages. What next, suggest what grade of paper is best for AI posters? ;-)

More seriously, communication of AI policy is important, but is no different than many other polices which need to be communicated. Just as no special strategy is needed for AI project management, none is needed for communications.

Fantasy Future

The last section of the course did not start well, presenting a future, where robotics & AI proves leisure time for the population & more time for students to explore their interests. This future has been predicted for other technological developments applied to learning, from correspondence courses to the Internet. However, they did not take into account the unchanged human nature. Traditional educational institutions have been able to accommodate each technological development, with the students & the community rejecting radical changes to educational delivery.

Despite this, I was most impressed with the last section of the course provided by SMU. Perhaps DEC should have left it to SMU to provide the entire course. But still, much of this was about the processes of education, which anyone teaching at a university should have learning in their basic teacher training (I did). One part I did not like was a 55 minute video. This was an interesting conversation between two experts, but 55 minutes is far, far too long. This should have been broken into smaller chunks.

One curious metaphor used was "hands on the wheel" of AI. My new car is controlled with voice and buttons. There is a steering wheel, but most of the time the car steers itself. That might be a better metaphor for AI in education: I select the destination, the car proposes a route, which I amend as needed then confirm. I then monitor the car's systems, while it dives itself. 

Singapore Education Leadership

Singapore's universities previously provided me with career, and life, changing inspiration. In 2013 I was giving a talk in Singapore on e-learning. One of the audience mentioned Singapore had an e-learning week, after a SARS outbreak, to prepare for future pandemics. As a result I was mentally and technically prepared for the COVID-19 outbreak a decade later. The SMU section of this course may well prove to be a similar pivotal moment in my teaching.

ACRONYMS

The educational acronyms used in the course were getting a bit silly, particularly the ABCDEF framework. What next an alphabet framework? Copilot wrote me one. ;-) 

A–Z Educational Acronym (All Letters in Order)

1. Active
2. Building
3. Curiosity
4. Drives
5. Engaged
6. Focused
7. Growth,
8. Helping
9. Innovative
10. Judgement
11. Kindle
12. Lifelong
13. Mastery.
14. Nurturing
15. Open
16. Problem‑solving
17. Questions
18. Reinforces
19. Skilled
20. Thinking,
21. Uplifting
22. Valuable
23. Wisdom
24. Xpanding
25. Youthful
26. Zeal.

Output

Here is one of the exercises I completed as part of the course. I am still not sure what I was supposed to do with it, as there was nowhere to submit it. This was done with the aid of MS Copiliot:

Learning Activity Brief: Exploring Project Reports with Microsoft Copilot

Learning Goal

Students will develop a clear understanding of the structure, purpose, and quality expectations of professional project reports in computing. By the end of the activity, students should be able to:

• Identify the essential components of a high‑quality computing project report

• Distinguish between technical detail, justification, and reflective analysis

• Evaluate the clarity, coherence, and professionalism of report writing

• Apply these insights to improve their own project reporting practices

Role of AI (Microsoft Copilot)

Students will use Microsoft Copilot as an exploratory and analytical tool. Copilot will support:

• Information gathering — e.g., asking Copilot to explain typical report structures, compare academic vs industry reports, or summarise best‑practice guidelines

• Critical evaluation — e.g., prompting Copilot to critique sample report excerpts or identify weaknesses in clarity, structure, or justification

• Reflection — e.g., asking Copilot how a reader might interpret a section, or what improvements would strengthen a report’s argument

Copilot is not used to generate a full project report. Instead, it acts as a catalyst for discussion, critique, and deeper understanding.

Activity Workflow (1 hour, small groups)

1. Initial Prompting (10 min) Groups ask Copilot to outline what makes an effective computing project report.

2. Deep Dive (20 min) Each group selects one component (e.g., requirements, design rationale, testing, evaluation) and uses Copilot to explore expectations, common pitfalls, and examples.

3. Critical Challenge (15 min) Groups provide Copilot with a short, deliberately flawed excerpt (provided by the instructor) and ask it to critique and suggest improvements.

4. Synthesis (15 min) Groups consolidate their findings into a concise artefact.

Student Product

Each group produces a one‑page “Project Report Quality Guide” that includes:

• A definition of the chosen report component

• Key quality criteria

• Common mistakes students make

• A short example of improved writing based on Copilot’s critique

• A brief reflection on how AI supported (and sometimes limited) their understanding

This product must be written in the students’ own words, with AI‑generated text clearly identified or paraphrased.

Assessment

This activity contributes to formative assessment and may be graded on participation or as a low‑stakes submission. Assessment focuses on:

• Accuracy and clarity of the group’s explanation of their report component

• Depth of analysis in identifying quality criteria and pitfalls

• Critical engagement with AI — evidence that students questioned, validated, or refined Copilot’s output

• Quality of the improved example — demonstrating understanding, not AI‑dependence

• Reflection on the role of AI in academic and professional writing

Rubric criteria can be aligned with:

• Understanding of report conventions

• Critical thinking

• Communication quality

• Responsible AI use 

The New World Order

Greetings from the Australian National University where Professor Amitav Acharya  is talking on his new book "The Once and Future World Order". He argues the world order did not come exclusively from the West. There was a two way interchange. The decline in Western dominance now taking place is not necessarily bad. In particular US dominance was not benign. What comes next doesn't have to be "West versus the rest". 

I suggest Australia would have difficulties comprehend, let alone navigate a word without US dominance. 

Professor Acharya looks far further back to the Hittites for lessons on world order. They signed a treaty with Egypt. Principles such as freedom of the seas are similarly old. He suggests we will have a "multiplex" replace the USA. I looked for a definition and ended up with a movie theater with many screens. Can Australia find a comfortable seat?

PS: I recommend a visit to the Istanbul Museum of The History of Science and Technology in Islam.

AI Literacy for All

Just completed the AI Literacy for All certificate* by the Digital Education Council for The Australian National University. When I was first invited to do the course I was skeptical, but despite having been to many training courses, workshops, symposiums & conference presentations on AI, I still learned some things. 

* Keep in mind this is not an AQF qualification. 

AI Boosterism in AI Training

I had some spare time so decided to get on with the AI training the Australian National University is encouraging staff to take. This is the usual online training module with some quizzes and exercises. It wasn't too bad, but as I know a bit about the topic, I was up to part 5 of 8 before it started telling me anything I didn't know. 

 At this point I was instructed to get AI to generate a LinkedIn post about AI & personal learning. While the previous modules did have some warnings about checking AI output for incorrect information and hallucinations, it was all a little too positive. At this point I used Copilot to generate the required LinkedIn post. This had only positive points on how AI could help with personal learning. As instructed I refined the result, but on my own initiative by asking for negative as well as positive points. That worked fine, but what struck me was that had I not asked, it would have all been positive.

Here are the negatives added:

"Negative impacts

• Over‑reliance on AI, which can weaken critical thinking and problem‑solving if learners default to AI-generated answers.

• Quality inconsistency, as AI can produce confident but incorrect explanations that mislead learners.

• Equity gaps, where those with better access to technology gain an advantage over those without it.

• Privacy concerns, especially when learning data is used to train models or inform performance decisions.

• Reduced originality, as learners may unintentionally mimic AI-generated patterns rather than developing their own voice or ideas.

These risks highlight the need for thoughtful integration rather than blind adoption."

Open Source Volunteers Are Like the Allen Key in a Flat-pack Bookcase: Vital But Unappreciated

Emma Davidson at EO26

Greetings from day three of Everything Open 2026 at University of Canberra. Emma is Program Director of IDEATE & started with a plea for industry to support their open source workers, describing them as like the allen keys in a flat-pack bookcase, pointing out that IKEA depends on open source software: She went onto propose 0.3% of the AUKUS funding be put into open source internships. Emma described AUKUS as a project for "imaginary nuclear submarines". She went on to praise the work of the Open Source Institute at University of Canberra, before outlining ANU Techlauncher program. Emma then moved on to the main theme of her talk about how to get a more diverse technology workforce and IDEATE's role in creating a more diverse university student body.

This being a Linux conference, apart from geopolitics,  Emma was asked which font she used for her slides. ;-)

My picks for the rest of the day:10:45AM  RepRapMicron - The Next Small Thing In 3D Printing, Vik Olliver

11:40AM So You've Decided to Build It Yourself, Leesa Ward

1:30PM Abstracting FPGAs in Python for fun and radio astronomy, Andrew Bolin

2:25PM Open Australia: Who we are, what we do, and what's in it for you., Donna Benjamin

3:45PM Everything Open Everywhere All At Once, Steven De Costa
4:45PM Lightning Talks

Reflecting on What a university is and can do

One of the ways I teach students is via reflection. The student is usually asked what they have achieved, what they aim to achieve in the future and what they will need to do to get to their goals. The university where I teach is now asking itself similar questions. What have been the achievements in the past, what do we aspire to in the near future and what makes us different from others. I have been teaching at the institution for more than a quarter of its life, so am in a reasonable position to suggest some answers.

Past Achievements

Australian universities were, from the start, created to train professionals and conduct useful research. In the act establishing the university, the functions included:

"(a) To encourage, and provide facilities for, post-graduate research and study, both generally and in relation to subjects of national importance to Australia;

(b) To provide facilities for university education for persons who elect to avail themselves of those facilities and, are eligible so to do; and

(c) Subject to the Statutes, to award and confer degrees and diplomas."

The University was originally envisaged having research schools for Medicine,  Physical Sciences, Social Sciences; and Pacific Studies. Another priority was specialist training for the Public Service. 

My university later added undergraduate students and more areas of research and training, but the emphasis remains on research and training for national priorities. Some of this is done formally, such as through the ASD-ANU Co-Lab, where staff from the Australian Signals Directorate work with academics and students to better protect the nation's digital infrastructure. Some is less formal, as when people from the Department of Defence, where I used to work, drop in for some advice. One achievement is that this mostly happens out of public view.

An achievement was that, along with other Australian universities, was the ability to switch over to online learning in a few weeks due to the COVID-19 pandemic. I was able to help with this having been trained for such a situation and then being able to train others. Perhaps an equally important achievement is that universities did not throw away this investment in e-learning skills and infrastructure. Universities have made efforts to incorporate the useful aspects of online learning with the campus experience. 

One earlier achievement was the role universities had in establishing the Internet in Australia, educating politicians and key public servants on its use, through what has been called the Internet Cabal.

The Near Future

The immediate challenge for the universities is to redesign leaning and assessment in response to AI. This is not just about stopping student cheating. It is about teaching staff learning how to teach using AI and teach students to use AI. 

A less intimidate challenge is to design programs to suit the needs of today's students. This requires short programs which can be assembled into the equivalent of traditional degrees. It also requires work integrated learning and recognition of prior learning. I learned how to teach and design programs for this in the vocational sector. 

Being Distinctive

The longer term challenge for Australian universities is to get away from comparing themselves with each other. Students seeking an education can increasingly choose more widely, ranging from local vocational institutions, which can now award degrees, to global online universities.

When I decided to affiliate with a university, early in the previous century, I wrote to every one in Canberra. The first to response came within five minutes, with a very simple offer: "Turn up Monday, we have an office for you". The other universities wanted to have meetings, and discuss pay and conditions. It is that flexibility which I suggest is a winning feature for a university. Students should have flexibility in how and what they study. Also, there should be an emphasis on the human element, even with most students studying mostly online. 

When I wanted to learn to teach online (for international students and in case  students could not get to campus), I started locally, then interstate, and finally worldwide. I wanted an education, the quality of which is unrelated to the research conducted at an institution. I started locally, the an Australian regional teaching university, then a similar one in Canada. 

Testing the Saftey of Smart Cars

Ivan Ang

Greetings from the Australian National University, where Ivan Ang is reporting his research on "User-centric Assessment of Robotic Systems via POMDP Planning of Adversaries". What got my attention was applying this to testing car autonomous driving. Recently I purchased a basic compact car. Despite the low cost, it came with a camera and radar for autonomous breaking, adaptive cruse control and lane keeping. I am trusting my life, and those of other road users, to these systems, so how well are they tested? Ivan pointed out that autonomous breaking was tested by pulling a dummy out in the path of the car on a string. The dummy's arms and legs are fixed, as its speed and direction. The developers of the system can optimize it for this test, but it then might do as well with real people. 

Advanced LinkedIn Workshop at ANU

Dr Fiona Scotney, ANU

Greetings from Dr Fiona Scotney’s Advanced LinkedIn Workshop at ATEM2025. A few hours ago I was in Sydney, and saw a LInkedIn post from Fiona, saying she was speaking on LinkedIn at ATEM2025. I had no idea what ATEM was and only knew her as a Director at The Australian National University. It turns out ATEM is the Association for Tertiary Education Management and they are having their conference at ANU this week.. 

Fiona provided useful tips, such as writing as you talk and keep in mind you are promoting your team and organisation, not just yourself. Tips included ending posts with a call to action. This is straight from the entrepreneurial pitch playbook (you get trained to end with what your audience to do). I have been using social media professionally for longer than the term has existed, but still learned some things.

Quantum AI for Defence at ANU

Dr. Nils Herrmann, 
 Quantum Brilliance

Greetings from the Australian National University where Dr. Nils Herrmann, from Quantum Brilliance is talking on Quantum Machine Learning on Diamond-based Quantum Computers. Quantum Brilliance is an Australia/German startup building quantum computers using diamond microchips. Their Canberra research center ios at the ANU. What got my attention, and probably did of governments and funders, is using the quantum effect for machine learning. Nils envisions a large quantum computer using training data and then a quantum computer on a plug in board in a desktop computer using the model created. The aim is to have a board rugged enough to be used in an aircraft, with obvious military applications. 

"This talk introduces the concept of Quantum Utility - Quantum Brilliance’s vision for practical quantum advantage - and presents early gate-based QML results achieved on an on-site, room-temperature quantum computer. It then highlights the work of the newly formed Quantum Utility and Exploration (QUTE) team, whose mission is to uncover utility through control modes that operate closer to the physical diamond-based hardware. The talk concludes with an introduction to quantum reservoir computing, showcasing QUTE’s latest simulations on future single- and multi-NV systems that establish a compelling platform for near-term, practical quantum machine learning."

McCusker Institute on ‘Shared Prosperity

Greetings from the McCusker Institute at the Australian National University in Canberra. Dr Katherine Trebeck, Economic Change Program Director at The Next Economy, is speaking on ‘Shared Prosperity: the economy we have, the one we need and what we can do to make it better’. This is at a university, so there are slides with references. But the message about the distribution of wealth. At the same time business leaders are talking to government, a few I'm away l. 

Katherine brought the issue by pointing to University of Technology Sydney referring staff being made redundant to stress relief advice. 

The solutions to some intractable problems seem so simple. We can reverse global warming with a carbon tax. Poverty can be eliminated by removing tax breaks for the rich to fund welfare. The solutions are easy but how do we incentivise to do this? 

As a retirement age person who owns the home I live in, with imputed shares and a tax free super balance, I feel guilty. I understand previous governments bribed older voters, but this has reached absurdly generous levels. Couldn't we add "average" to the tax breaks? So the average home, share dividends and super balance would get tax breaks. 

Katherine is presenting examples of companies with a social conscious. However, are these companies funding lobbyists to go to government and demand to pay more tax. 

I suggest universities can help. However, they need to also address their internal inequalities. A meritocracy doesn't have to be winner-takes-all. Only one of Australia's universities is a foreign owned for-profit company. The rest don't need to be run like a caraciture of 19th century capitalism. There are other models which combine academic traditions and social enterprise enterpurship. 

I am a member of my professional body, which employs people to get our views in front of policymakers. Many groups can't afford this, but perhaps students of politics, business and related disciplines could do this for their work experience.

Rebuilding the public service with AI

Image generated by Google Gemini,
for a pod based
interplanetary transport system

Greetings from the AI Colab at the Australian National University in Canberra, where I am taking part in "From red tape to algorithm: Reimagining the public service in an AI age". I am not exactly sure what the event or the AI Colab are, but as it is being hosted in the ANU College of Systems and Society, near my office, I thought I would come along. When I registered I though this was by the ASD-ANU Co-Lab, but apparently it is another collab. Last week I was at an event on AI and ACT Government. 

We were give the exercise to image a future service based on three randomly chosen cards. My team came up with pod based interplanetary travel. I asked Google Gemni for an image and presentation and it came up with the appended description and image. 

After another warm up exercise, we got on to actually talking about public service. In particular, in Australia we have three levels of government (in Canberra just two). I argue there is in effect a fourth level for many people, the cluster housing management where they live (I live in an apartment building which has two levels of management, for parks, energy, and waste disposal). 

One obvious, and for me overriding, point for me on AI and government is that the people who do it need to be trained in how to do AI. Some of the teams and interns aI am teaching are studying AI and implement projects using it for government. ?". 

At the end of the event I asked "What is the AI Colab?". Several people tried to explain it, without success. I found a website, but it still is not clear. I suggest a plain English description is needed.

The Pod Transport System

Here is a presentation outline for a pod-based interplanetary travel system, styled with a "NASA punk" aesthetic. This style combines the optimistic, analog-heavy feel of 1970s and 80s space exploration with a grittier, more lived-in, and often retro-futuristic edge. Think a mix of *Alien* and the Apollo program.

---

"## **Title Slide:**

**Title:** Project: Peregrine - A New Era of Interplanetary Travel

**Subtitle:** The Pod-Based System for Human Exploration

**Image:** A stylized, high-contrast image. On the left, a detailed drawing of a modular "Peregrine" pod, with visible welds, rivets, and a faint glow from its propulsion system. On the right, a silhouette of a massive, retro-futuristic "mother ship" in deep space. The background is a mix of star fields and faint, blueprint-like lines.

**Aesthetic:** NASA logo in a slightly distressed font, analog dials and gauges in the corners, text in a classic, bold, sans-serif font like Helvetica or similar.

---

## **Slide 2: The Challenge**

**Title:** The Interplanetary Problem

**Image:** A grainy, slightly distorted photo of a classic rocket launch (like the Saturn V), with a faded red filter over it. Overlayed text reads: "Long-Duration Missions. High Cost. Limited Flexibility."

**Bullet Points:**

* **Long Transit Times:** Current propulsion methods make journeys to Mars and beyond measured in years, not months.

* **High Development Costs:** Each new mission requires a bespoke, single-use vehicle, driving up costs and limiting mission frequency.

* **Crew Burnout:** Confinement in a single vessel for years on end leads to psychological and physiological stress.

* **Lack of Redundancy:** A single catastrophic failure can doom an entire mission.

**Aesthetic:** Blueprint-style diagrams of existing spacecraft, annotated with problem descriptions. "CLASSIFIED" or "INTERNAL USE ONLY" stamps in the corner.

---

## **Slide 3: Our Solution - Project Peregrine**

**Title:** A Paradigm Shift: Modularity & Reusability

**Image:** A clean, exploded-view diagram of the Peregrine system. It shows a central "mothership" or "hub," with multiple individual "pods" docking with it. Each pod is labeled with its function (Crew, Cargo, Science, Habitation).

**Bullet Points:**

* **Modular "Pod" System:** The core of our design. Individual, self-contained units for specific functions.

* **The *Aethel* Mother Ship:** A reusable, nuclear-thermal propulsion (NTP) vessel designed to transport pods between planetary orbits.

* **Efficient Mass Transport:** The pods are designed to be launched individually from Earth via conventional rockets or space elevators, then assembled in orbit.

* **Mission Flexibility:** The same system can be reconfigured for a Mars mission, an asteroid mining operation, or a deep-space science probe by simply swapping out pods.

**Aesthetic:** The diagram should look like a cross between an engineering schematic and a piece of concept art. Hand-written annotations, faded paper textures, and faint grid lines.

---

## **Slide 4: The Peregrine Pods**

**Title:** Anatomy of a Pod

**Image:** A detailed, cutaway view of a single "Crew Pod." The interior is visible, showing a small living space, a bunk, a control panel with chunky buttons and toggle switches, and a small porthole. The aesthetic is cramped but functional, with visible wiring and exposed pipes.

**Bullet Points:**

* **Crew Pods:** Accommodate 2-4 astronauts. Equipped with life support, individual bunks, and personal communication terminals. Designed for comfort and psychological separation.

* **Habitat Pods:** Larger pods with communal spaces, exercise equipment, a medical bay, and hydroponics for fresh food.

* **Science Pods:** Dedicated labs with specialized equipment for astrophysics, geology, or biology experiments.

* **Cargo Pods:** Simple, robust containers for equipment, supplies, and rover parts.

**Aesthetic:** The diagram should be highly detailed, almost photorealistic, but with a grainy, analog quality. Text labels should look like they were typed on a typewriter.

---

## **Slide 5: The Journey (Phase 1)**

**Title:** From Earth to Orbit

**Image:** A cinematic, slightly overexposed photo showing a series of Peregrine pods being launched into low-Earth orbit (LEO). They look like industrial, chunky capsules. The Earth is a beautiful blue orb in the background.

**Narrative:**

1.  **Launch:** Individual pods are launched from Earth using existing launch infrastructure. This distributes the massive weight and logistical burden.

2.  **Orbital Assembly:** The pods are then docked with a pre-positioned *Aethel* mother ship in LEO. Crew pods are the last to arrive, ensuring a shorter total time in space for the crew before the main journey.

3.  **Final Checks:** Systems are checked and re-checked by automated probes and the crew. Final trajectory is calculated.

**Aesthetic:** The images should be evocative and slightly cinematic. Faded colors, visible lens flare, and a sense of scale and ambition.

---

## **Slide 6: The Journey (Phase 2)**

**Title:** The Interplanetary Transit

**Image:** A high-resolution, artistic rendering of the *Aethel* mother ship in deep space. The NTP engines are glowing with a faint, blue-green light. It is a massive, complex structure with many pods attached. The image captures the loneliness and vastness of space.

**Narrative:**

1.  **Nuclear-Thermal Propulsion (NTP):** The *Aethel* uses its powerful, efficient NTP system to accelerate the entire assembly. This provides a much faster transit time than chemical rockets.

2.  **Crew Comfort:** During the journey, the crew can move between different pods, reducing the feeling of confinement. They have access to a larger hab pod and can conduct research in the science pods.

3.  **Redundancy:** In case of a major system failure on one pod, the crew can evacuate to another, or the affected pod can be jettisoned.

**Aesthetic:** The image should be beautiful and awe-inspiring, but with a sense of the gritty, industrial nature of the machine. Visible heat vents, solar panels that look slightly weathered, and the distinct, analog feel of the Peregrine design.

---

## **Slide 7: Arrival & Mission Deployment**

**Title:** Separation and Landing

**Image:** A diorama-like image showing a single, streamlined Peregrine pod detaching from the *Aethel* in orbit around Mars. Below, on the Martian surface, another landing pod is deployed, its retro-thrusters firing. The Martian landscape is red and dusty.

**Narrative:**

1.  **Orbital Detachment:** Upon arrival, individual pods are detached from the *Aethel* and placed into the target planet's orbit.

2.  **Surface Landing:** Specialized landing pods (with built-in heat shields and retro-thrusters) are used to transport crew and cargo to the surface.

3.  **The *Aethel*'s Role:** The mother ship remains in orbit, acting as a command and control hub, a resupply depot, and a reusable "bus" for the return journey.

**Aesthetic:** The image should have a sense of action and purpose. The colors are muted and realistic. A small, stylized NASA logo can be seen on the side of one of the pods.

---

## **Slide 8: The Return Journey**

**Title:** Reassembly and Return

**Image:** A final cinematic shot showing the *Aethel* mother ship, now with fewer pods attached, accelerating away from Mars. The image is a reverse of the journey to Mars, with the home planet as a distant, beckoning point of light.

**Narrative:**

1.  **Return to Orbit:** Crew and cargo are transported back to the *Aethel* in orbit.

2.  **Pod Recovery:** The *Aethel* can recover some of the pods, or they can be left behind to form the basis of a permanent colony.

3.  **The Return:** The *Aethel* begins its return journey to Earth, carrying the crew and mission-critical samples.

**Aesthetic:** A final, poignant image that evokes a sense of both accomplishment and the long, hard road ahead. The visual style remains consistent with the previous slides.

---

## **Slide 9: Why Peregrine?**

**Title:** The Future is Modular

**Image:** A split-screen image. On the left, a schematic of a traditional, monolithic rocket. On the right, a schematic of the Peregrine system, showing its modularity and interconnectedness. Text boxes highlight the advantages.

**Advantages:**

* **Cost-Effective:** Reusable *Aethel* mother ship dramatically reduces per-mission cost.

* **Scalable:** Missions can be scaled up or down by adding or removing pods.

* **Safer:** Multiple redundant systems and the ability to jettison failed pods.

* **Faster:** NTP system shortens transit times, reducing crew exposure to radiation and psychological stress.

* **Sustainable:** The system forms the basis for a permanent, interplanetary logistics network.

**Aesthetic:** Bold, impactful text. The schematics are clean and easy to understand. The overall tone is one of confident, optimistic progress.

---

## **Final Slide:**

**Title:** Project: Peregrine

**Subtitle:** The Next Step for Humanity.

**Image:** A striking, stylized logo for "Project Peregrine," looking like a cross between a NASA mission patch and a company emblem. Below it, the tagline: "Build. Explore. Return. Repeat."

**Contact Information:**

* Confidential NASA/Internal Use Only

* Date: July 28, 2025

**Aesthetic:** The final slide should feel like a powerful and memorable conclusion. A bold, simple design with a strong, optimistic message."

Hacking AI for Assessment or Hacking Assessment for AI?

Greetings from the Australian National University science teaching building, where Bert Verhoeven from University of Newcastle, is running us through an AI Assessment Hack-a-thon. The follows seamlessly from the EduTech Australia HE stream I chaired last week in Sydney and ACS TechUplift25 next month in Canberra. He suggests we need to learn about AI and use it in teaching. AI has limitations and Bert argues we need to teach students to use the tools critically.  

For the last few years I have been attending conferences, workshops and symposia on AI and education. Assuming I am convinced of the importance of this, where do I learn to use it for teaching? Can I sign up for a formal postgraduate university program in this, as I did to learn teaching and assessment? I did a quick search and neither of the institutions I got my most recent two qualifications in education were offering courses in AI for teaching (they did offer AI courses for computing students). There are some vocational education, but mostly for computer game development, some for business, none for education. I tried searching my friendly local TAFE, but "artificial intelligence" only comes up in the academic misconduct policy. 

There seems to be the opportunity to create courses on AI or education, perhaps also to educate academics about education. Many of the approaches to using AI in teaching and assessment are based on well known educational techniques. In effect AI is exposing poor teaching and assessment techniques. The solution is to use better techniques, which can incorporate AI.

Along the way there was discussion of program assessment structures where the student is given formative feedback in individual courses, then assessed at the end of their program. Such an approach makes sense in terms of education, but I suggest is not a viable product. As a student I am studying part time while working, so a bachelor's degree will take me six, or more, years. The risk of investing many tens of thousands of dollars for potentially no return (if I fail the final assessment) is unacceptable,. I want a return on my investment much quicker, at least within a year. As a result I will sign up where there are stacked credentials offered, even while grumbling about all the assessment. ;-)

ps: The environmental effects of AI came up. This amplifies the concern over data centers generally, in terms of energy and water use. It is not difficult to do back of the envelope calculations and I previously showed computer students how to do this. 

pps: I commented to Bert that I could not find any AI for teching courses and he suggested I ask Chat GPT to design one with the prompt "Write a course outline for a graduate course in Artificial Intelligence for Education to teach university academics in Australia.". Here is what it came up with:

Course Title:

Artificial Intelligence for Education

Course Level:

Graduate (Professional Development / Postgraduate Coursework)

Target Audience:

University academics, educational technologists, learning designers, and administrators in Australian higher education institutions.

Course Duration:

12 weeks (can be adapted to 6-week intensive format)

Delivery Mode:

Blended (Online + Optional In-Person Workshops)

---

Course Description:

This course equips university academics with a deep understanding of artificial intelligence (AI) and its transformative role in higher education. Participants will explore current and emerging AI technologies, pedagogical opportunities and risks, ethical considerations, policy implications, and practical strategies for integrating AI tools into learning, teaching, and assessment. Special emphasis is placed on the Australian higher education context, including alignment with TEQSA and national education policy frameworks.

---

Learning Outcomes:

By the end of the course, participants will be able to:

1. Explain foundational concepts and types of AI relevant to education.

2. Evaluate current AI applications in teaching, learning, and assessment.

3. Design AI-enhanced learning activities and assessments.

4. Critically assess ethical, legal, and social implications of AI use in education.

5. Interpret Australian higher education policy in relation to AI implementation.

6. Demonstrate leadership in responsible and innovative AI adoption at the institutional level.

---

Weekly Topics Overview:

Module 1: Foundations of AI in Education (Week 1–2)

• Introduction to AI, machine learning, natural language processing, generative AI.

• History and evolution of AI in education.

• Overview of current tools (e.g. ChatGPT, Copilot, AI tutors, predictive analytics).

• Case studies from Australian and global universities.

Module 2: AI in Learning and Teaching (Week 3–4)

• AI-supported personalised learning and adaptive systems.

• Intelligent tutoring systems and learning analytics.

• AI in online, blended, and face-to-face modalities.

• Impacts on curriculum design and academic roles.

Module 3: AI in Assessment and Academic Integrity (Week 5–6)

• Automated grading, feedback generation, and formative assessment.

• Designing AI-resilient and AI-enhanced assessments.

• Addressing academic integrity, contract cheating, and detection tools (e.g. Turnitin AI detectors).

• TEQSA guidance and institutional policies.

Module 4: Ethical and Societal Considerations (Week 7–8)

• AI bias, transparency, explainability, and fairness.

• Privacy, surveillance, and data protection (incl. Australian privacy laws).

• Inclusion, accessibility, and equity in AI adoption.

• Frameworks (e.g. UNESCO AI ethics, Australian AI Ethics Principles).

Module 5: Policy, Governance, and Strategic Leadership (Week 9–10)

• Institutional AI strategies in higher education.

• TEQSA, AQF, and other regulatory frameworks.

• Developing policies for AI governance in teaching and learning.

• Risk management and future-proofing universities.

Module 6: Capstone Project and Futures Thinking (Week 11–12)

• Scenario planning: the future of AI in higher education.

• Capstone: Propose a strategy, curriculum redesign, or policy for AI integration in your institution.

• Peer review and reflection.

• Pathways for ongoing development and institutional leadership.

---

Assessment Tasks:

1. AI Tool Evaluation Report (20%)
   Review and critically evaluate an AI tool relevant to teaching or assessment.

2. Discussion Journal (20%)
   Weekly reflections and engagement with peers on ethical, pedagogical, and technical issues.

3. Case Study Analysis (20%)
   Analyse a real-world use of AI in higher education, including risks, benefits, and improvements.

4. Capstone Project (40%)
   Develop a detailed proposal for implementing or evaluating AI in your teaching or institutional context, aligned with regulatory and ethical frameworks.

---

Learning Methods:

• Weekly asynchronous modules (videos, readings, quizzes)

• Interactive webinars with AI and education experts

• Collaborative projects and case-based learning

• Hands-on experimentation with AI tools (e.g. ChatGPT, Copilot, Perplexity, LMS-integrated AI)

• Online community of practice

---

Recommended Readings & Resources:

• Luckin, R. (2018). Machine Learning and Human Intelligence.

• Selwyn, N. (2021). Should Robots Replace Teachers?

• TEQSA & DET Reports on AI in Higher Education (Australia)

• UNESCO and OECD Guidelines on AI and Education

• OpenAI and Microsoft Copilot documentation

---

Optional Workshops (In-person or Online):

• “Designing Assessments in the Age of AI”

• “AI for Learning Designers and Educational Developers”

• “Ethics and Policy Roundtables: Creating AI Governance Models”