Monday, July 28, 2025

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."



Thursday, July 24, 2025

How can Local Government use AI to improve services?

Dr Tim Turner, Chairing the meeting
Greetings from the Canberra Innovation Network (CBRIN) where I am attending a meeting on "How can the ACT Government use AI to improve government services?" organised by the Pearcey Foundation. There are about 20 people in the room from government, industry and academia, with Dr Tim Turner chairing. I am not exactly sure why I am here, but when we went around the room I said I would teach this stuff, to students.

Each year, as well as sponsoring awards for Canberra entrepreneurs, the ACT Government sets a challenge for the Pearcey Foundation to address, with experts in Canberra. This year it is improving government services through AI. Apparently we are going to be doing brainstorming. 

Priority 1 is planning and development.

As it happens I know a little about ACT planning processes, as I chaired a local committee for redevelopment of the shopping center at Dickson. My suggestion was to train the staff to use AI, so they did not go off and use tools they should not, and put sensitive data into them. Also I suggested a tool to point citizens to other levels of government which provide relevant services. I am off to Singapore for Education and FinTech conferences in November, so did a quick search. I found the Singapore Government have had an AI for government plan since 2001, and have updated it since. So it would be worth looking at there experience (especially as Canberra is similar in some ways being a city state). One thing I put to the meeting was if AI could be used to improve social housing. As I was commenting on something another participant said, I commented "Like a smart patter book?". It turned out that wasn't what they meant, but perhaps this would be a good idea. NSW has a pattern book for cluster housing. If you use one of the designs it is pre-approved. The smart version would allow you to customise designs for different sizes and locations, but still meet planning requirements and get approved quickly. I then asked the meeting if there was an opportunity for small startup companies to provide AI products. It then dawned on me, this was why we were meeting at CBRIN. This raises the issue as to what is the role for government: do they need to build the software to do this, train the AI models, or can they just buy the service? Obviously Canberra's universities have teams of students who can build prototypes. 


I did the obvious, and asked Microsoft Copilot:

"The ACT Government can leverage artificial intelligence (AI) to improve public services by drawing on best practices and emerging trends from other jurisdictions. Here's a breakdown of how AI is being used and could be applied in the ACT:


---


### **1. Enhancing Service Delivery**

AI can streamline and personalize interactions between citizens and government services:

- **Customer Service**: AI-powered chatbots and virtual assistants can provide 24/7 support, answer FAQs, and guide users through complex processes like applying for permits or accessing health services[1](https://www.ncsl.org/technology-and-communication/artificial-intelligence-2025-legislation).

- **Healthcare Inspections**: AI can assist in analyzing inspection data to identify patterns and prioritize high-risk facilities for review[1](https://www.ncsl.org/technology-and-communication/artificial-intelligence-2025-legislation).

- **Road Safety**: AI can analyze traffic data to optimize road maintenance schedules and identify accident-prone areas[1](https://www.ncsl.org/technology-and-communication/artificial-intelligence-2025-legislation).


---


### **2. Responsible AI Governance**

Governments are increasingly adopting frameworks to ensure ethical and safe AI use:

- **Pilot Projects**: Many states start with pilot programs to test AI applications in public services before full-scale deployment[2](https://cdt.org/insights/state-government-use-of-ai-the-opportunities-of-executive-action-in-2025/).

- **AI Task Forces**: Creating cross-agency task forces helps coordinate AI strategy, assess risks, and ensure alignment with public values[2](https://cdt.org/insights/state-government-use-of-ai-the-opportunities-of-executive-action-in-2025/).

- **Impact Assessments**: Agencies are encouraged to conduct assessments to evaluate the societal, privacy, and equity impacts of AI systems[3](https://www.dlapiper.com/en-us/insights/publications/2025/04/white-house-releases-guidance-for-ai-acquisition-and-use-in-government).


---


### **3. Equity and Civil Rights Protections**

AI systems must be designed to avoid bias and protect vulnerable communities:

- **Bias Mitigation**: Guidelines can require agencies to evaluate AI tools for potential discriminatory outcomes, especially in high-impact areas like housing, employment, and education[2](https://cdt.org/insights/state-government-use-of-ai-the-opportunities-of-executive-action-in-2025/).

- **Transparency**: Publishing inventories of AI tools and their use cases helps build public trust and accountability[2](https://cdt.org/insights/state-government-use-of-ai-the-opportunities-of-executive-action-in-2025/).


---


### **4. Workforce and Procurement Strategy**

AI adoption should support—not replace—public sector workers:

- **Workforce Impact**: Agencies should assess how AI affects staff roles and ensure it enhances rather than displaces human work[2](https://cdt.org/insights/state-government-use-of-ai-the-opportunities-of-executive-action-in-2025/).

- **Smart Procurement**: Governments are updating procurement policies to ensure ethical sourcing of AI tools, protect data rights, and avoid vendor lock-in[3](https://www.dlapiper.com/en-us/insights/publications/2025/04/white-house-releases-guidance-for-ai-acquisition-and-use-in-government).


---


### **5. Legislative and Regulatory Frameworks**

The ACT can learn from other states that have enacted AI-specific laws:

- **Transparency Laws**: Requiring agencies to disclose their use of automated decision-making tools publicly[1](https://www.ncsl.org/technology-and-communication/artificial-intelligence-2025-legislation).

- **Worker Protections**: Ensuring AI does not undermine existing labor rights or collective bargaining agreements[1](https://www.ncsl.org/technology-and-communication/artificial-intelligence-2025-legislation).

 

Here’s a tailored proposal for how the ACT Government could implement AI to improve services across health, transport, and education:


1. Health

AI Applications

Predictive Analytics for Hospital Demand: Use AI to forecast patient admissions and optimize resource allocation.

Virtual Health Assistants: Provide 24/7 support for mental health and chronic disease management via chatbots.

Medical Imaging Analysis: Deploy AI to assist radiologists in detecting anomalies in scans faster and more accurately.

Implementation Steps

Partner with Canberra Health Services to pilot AI triage tools in emergency departments.

Collaborate with universities for ethical AI research in diagnostics.

Ensure compliance with privacy laws and conduct regular audits for bias.

2. Transport

AI Applications

Smart Traffic Management: Use AI to analyze traffic flow and adjust signals dynamically to reduce congestion.

Predictive Maintenance: Monitor infrastructure (roads, bridges, buses) to predict failures and schedule maintenance.

Public Transport Optimization: Analyze commuter patterns to adjust bus routes and schedules.

Implementation Steps

Integrate AI with existing Transport Canberra systems for real-time traffic updates.

Launch a pilot with AI-powered predictive maintenance for ACTION buses.

Use anonymized MyWay card data to train models for route optimization.

3. Education

AI Applications

Personalized Learning: AI tutors can adapt content to individual student needs and learning styles.

Administrative Automation: Streamline tasks like enrollment, grading, and feedback.

Early Intervention: Identify students at risk of disengagement or poor performance using predictive models.

Implementation Steps

Partner with ACT public schools to trial AI learning platforms in STEM subjects.

Train educators on ethical AI use and data literacy.

Establish a student data governance framework to protect privacy.

Cross-Cutting Recommendations

Create an ACT AI Taskforce: Include representatives from government, academia, industry, and civil society.

Develop an AI Ethics Framework: Ensure transparency, accountability, and fairness in all deployments.

Public Engagement: Host forums and consultations to build trust and gather feedback."


Thursday, July 3, 2025

Teaching Online in Response to Climate Change

Australasian Campuses Towards Sustainability (ACTS) have released the report Navigating Climate Change – Scenarios for Australia’s Tertiary Education Sector (June 2025). 

ACTS recommend universities:

  1. "Provide educational capabilities that ensure that future generations are resilient, creative and can provide the leadership Australia needs to navigate the challenges ahead.
  2. Undertake research that helps find the technological, societal, political and environmental solutions to the challenges ahead, thereby attracting increasing levels of research funding.
  3. Connect with their communities to support adaptation.
  4. Connect with local authorities in responding to extreme weather events."
More specifically ACTS says one way universities can address climate change is by educating students about it, and another is with online learning. The Australian Computer Society (ACS) commissioned me to design and run an online course for computer students, to teach them to address the problem of global warming. The course was first run in 2009 for ACS, then by ANU (as COMP7310). One of my ANU students adapted the course for Canada, where it is still offered by Athabasca University today. I suggest universities could run more such courses for relevant professions, making them available online, and as micro-credentials.  

Wednesday, July 2, 2025

Ten years of Innovation Connection in Canberra: trash & tea

 


Greetings from the 10th anniversary Canberra Innovation Network, First Wednesday Connect. Mr Michael Pettersson, Minister for Business is doing the honours. In the audience is a delegation from a Chinese university, hosted by University of Canberra. The minister entered into the spirit by keeping their speech short, on topic and ending with a call to action to entrepreneurs.

One of the entrepreneurs is "bin chicken" who has an instrumented bin here. The system has just been purchased by Canberra Institute of Technology. Also there is non-alcoholic drinks tasting by local brewers.

Tuesday, July 1, 2025

Industrial Design and Prototyping Info Session

Greetings from the Industrial Design and Prototyping Info Session at Canberra Innovation Network. I am not making a gadget but it helps me to know what some of my students do (the unis & CIT have maker spaces). The ACT Government is funding vouchers to pay for a startup's prototype making locally. This complements other schemes to refine the business idea first. 

Those interested in the ACS Prototyping voucher can:

  1. Learn more: https://cbrin.com.au/act-prototyping-voucher-pilot/
  2. Book a one-on-one chat : Project Coordinator Meeting
  3. Submit an application: https://podio.com/webforms/29783323/2477415

It was surprising to learn US companies use Canberra designers and Sydney plastic manufacturers. Another was the suggestion to start at a high price point with small production run for a small company.

One interesting comment from Formswell, the design company involved with the scheme, was having Aldi copy your product it is a compliment. The example given was a curved two handed pizza cutter, which looks like a Bat'leth from Star Trek.