AI revolution and the Australian economy

[qldfrog]

AI is here.Now.
Today you use it to draft your will, code your system or write your assignment.
I have the belief our society is asleep at the wheel regarding the huge impact on Australia.
AI also brings a new style of robotisation: the humanoid one, where not only factory process can be machine replace but all human activities in your human world
Loading unloading packet, refilling shelves, helping food and technically nursing and wiping your butt in the aged care facilities.
One humanoid for roughly $50k
Never sick, no strike working 24/7 365 days a year if you want to.
So some blue collars are at risks but probably even more most of office workers.
So what will these people do?
More BS jobs and public servants WFH couch potatoes?
Universal income?
Do we even have the choice, do we have the cash?
And are we doomed to see only the losers thriving in a society where effort, IQ or even EQ are worthless and maybe even counter productive.
So while our debt billions are going on in windmills and fart gas projects destroying mining and agriculture, the world is changing.
What do you think?
Where are the jobs for the kids starting a 3y degree this year?
Only so many plumbers or reno jobs ...

 

[SirRumpole]

Very interesting topic, and well done for bringing it up.

Intelligent use of AI is to make life better for as many people as possible, taking away the dangerous and boring jobs and leaving those which require the human touch.

As you intimated, I think a Universal basic income will come eventually, people will have more leisure time, families will be less stressed by the need to work most of the time, and we should have closer and more functional families.

That is, if it's managed properly. Do I have confidence that it will be ? Not really.

 

[ShareSuccess]

Don't Worry.....Be Happy.....The Kids of Today will work it all out!..... i'm not going to stress over that for which i cannot change as we as a human race move forward with new technology.

Every time i walk into a supermarket, nothing has changed there may be less checkouts but there is still plenty of workers stacking shelves as the world moves at a faster rate new jobs will be created through technology.

One change i,ve noticed through less checkouts is supermarkets are moving more towards a service model where they are hiring more people to serve us in general or through doing our shopping for us.

Passed generations died young....Current generations live on average into their 80s.....New generations will live into their 100s & future generations may not Die & that is through the advancement of Technology.....make that 2 cents lol

 

[divs4ever]

Very interesting topic, and well done for bringing it up.

Intelligent use of AI is to make life better for as many people as possible, taking away the dangerous and boring jobs and leaving those which require the human touch.

As you intimated, I think a Universal basic income will come eventually, people will have more leisure time, families will be less stressed by the need to work most of the time, and we should have closer and more functional families.

That is, if it's managed properly. Do I have confidence that it will be ? Not really.

i duplicate your lack of confidence

it is going to be an interesting conundrum humans needed to consume ( products and services ) and pay taxes but very few to actually be productive .

and all this administered by those incapable of even running a balanced budget

 

[JohnDe]

I think the biggest issue that Australia is going to face with AI over the coming years is uninterrupted electricity supply.

huge and heavily energy-intensive networked computer systems known as data centres, which are needed to train and operate the AI models. Data centres require tremendous amounts of round-the-clock energy to power their systems, along with cooling, lighting and other networking and security equipment.​

How much energy does an AI chatbot use? We asked one
The effortless convenience of artificial intelligence comes with mounting demands on our energy supplies.

Less than three years ago, AI chatbots were a novelty. Today, they’re used for everything from computer coding to creative inspiration – and the opening paragraph of this story.

But every time you unlock your smartphone to ask ChatGPT a question, you’re not just getting an answer – you’re potentially chewing through enough electricity to charge the whole device.

AI chatbots use much more energy than a typical internet search because they have to perform more complex computational tasks, both when they are being trained and when they are being used.

Those tasks rely on huge and heavily energy-intensive networked computer systems known as data centres, which are needed to train and operate the AI models. Data centres require tremendous amounts of round-the-clock energy to power their systems, along with cooling, lighting and other networking and security equipment.

Estimates of just how much of that energy is needed to power individual AI searches vary widely. In a blog post earlier this month, OpenAI founder Sam Altman claimed the average ChatGPT query used about 0.34 watt-hours of energy.

Translated into English by Google’s AI chatbot, Gemini, that’s the equivalent of turning on a typical electric oven or boiling water in a kettle for around a second, or actively browsing on a smartphone for about 10 minutes.

Chatbots perform much more complex tasks than traditional Google searches, which were only ever designed to efficiently find and present information that already exists. AI chatbots, by contrast, have to “think” and generate unique, original responses in real time.

One analysis by investment bank Goldman Sachs estimated that a typical ChatGPT query required almost 10 times the electricity needed for a traditional Google search – closer to 3 watt-hours. That’s roughly equivalent to turning on an LED lightbulb for just under two minutes, or charging a smartphone for a few seconds.


Complex AI queries, especially image and video generation, require huge amounts of energy. Bloomberg

Things also get a little more energy-intensive when you start to increase the complexity of an AI query, such as summarising long documents, or doing computer coding that involves step-by-step reasoning.

According to some estimates, those queries can use anywhere between 10 and 30 watt-hours, or more – equivalent to running a hairdryer or a microwave for 30 seconds or keeping an LED light on for about one hour.

Using AI to generate images can take even more power – equal to fully charging an iPhone or boiling water in an electric kettle for around 30 seconds.

Video generation, though, is by far the most energy-intensive use of AI. According to some estimates, the amount of energy required to generate a five-second, 16-frames-per-second AI video could power a kitchen oven for 40 minutes.

There is also an important distinction between the energy required to train an AI model and the energy used to ask it a question.

The training element is particularly power-intensive, thought to be equivalent to the annual energy consumption of thousands of homes, whereas the processing of individual queries – or “inference” – has a much smaller energy cost.

However, it’s the cumulative effect of all those queries that is causing headaches for power grid operators. Gemini likened this to the construction and operation of a factory.

“After the factory is built, it produces millions of goods every day. Each good produced (an AI query) might not take much energy individually, but the constant, high-volume production requires continuous energy input,” Gemini said.

That cumulative effect is growing. AI is increasingly functioning more like a replacement for internet search – and with more than 5 billion global internet users doing an estimated 9 billion daily searches, the energy demands of AI are only likely to go up.

For energy grid operators, the demand is already being felt. ChatGPT was launched in November 2022, less than three years ago. In December 2024, Altman claimed it was processing over one billion queries per day.

On Tuesday, OpenAI chief economist Ronnie Chatterji told The Australian Financial Review that more than 500 million people used ChatGPT every week, while the number of Australians actively using the platform had doubled over the past year.

That has left grid operators around the globe scrambling to include this huge and sudden increase in demand into their forecasts for future energy use – forecasts that are changing by the month.



Recent draft estimates of data centre power demand by Australia’s electricity grid operator showed massive upward revisions of their future energy use on 2024 projections. The new forecasts almost double what was speculatively estimated in 2024 as an “accelerated” case.

Aside from energy, the other hidden input into AI searches is water, which is used to cool the data centres. According to Altman, a typical ChatGPT search uses 0.32 millilitres of water, or about 1/15th of a teaspoon.

Other studies have estimated much higher water inputs, especially when taking into account indirect water use from the energy generated to power the data centres.

One study from the University of California put water use per query at around 10 millilitres – around 30 times higher than Altman’s estimate. That’s roughly equivalent to two teaspoons.

Once again, though, it’s the cumulative effect of the billions of queries puts this in perspective. At 10mL per query, one billion queries per day would use the same amount of water as a small town.

According to Gemini, it’s a reminder that even our seemingly weightless digital world has a very real physical footprint.

This article (except for the first paragraph) was written by a human.

 

[qldfrog]

I think the biggest issue that Australia is going to face with AI over the coming years is uninterrupted electricity supply.

huge and heavily energy-intensive networked computer systems known as data centres, which are needed to train and operate the AI models. Data centres require tremendous amounts of round-the-clock energy to power their systems, along with cooling, lighting and other networking and security equipment.​

I am more worried about the social and mental collapse.
Internet already gives us mostly free knowledge access
Is today's average person, while more "educated", more knowledgeable than pre internet?
And now, with AI comes the actual meaning of life.
This is the issue and drama of generational welfare, now extended to the whole society.
Plus, can Australia actually stay in the game.
I do believe @ShareSuccess is too optimistic, this is probably going to hit us even before current ALP has left.
Our local ALDI runs with a team of 4 people, with humanoid, will be maybe 1 supervisor?
Only public servants numbers are increasing in such scheme, more BS jobs
I expect regulations, rulings etc but in the same way IT and call centres went offshore, this will happen VERY soon

 

[divs4ever]

I am more worried about the social and mental collapse.
Internet already gives us mostly free knowledge access
Is today's average person, while more "educated", more knowledgeable than pre internet?
And now, with AI comes the actual meaning of life.
This is the issue and drama of generational welfare, now extended to the whole society.
Plus, can Australia actually stay in the game.
I do believe @ShareSuccess is too optimistic, this is probably going to hit us even before current ALP has left.
Our local ALDI runs with a team of 4 people, with humanoid, will be maybe 1 supervisor?
Only public servants numbers are increasing in such scheme, more BS jobs
I expect regulations, rulings etc but in the same way IT and call centres went offshore, this will happen VERY soon

not quite an Aldi situation but was chatting to the check-out lady ( she was clearly middle-aged , maybe even the manager ) and that discount shop has had a plague of shop thefts even by ( prepared ) professional shoplifters ( including rigged baby-strollers ) in the last year

and that is in a rural city of Warwick ( in QLD ) !!!

i don't know how AI and humanoids will slow that down .. doors to lock you in until you have paid for everything , perhaps

 

[Craton]

AI is here.Now.
Today you use it to draft your will, code your system or write your assignment.
I have the belief our society is asleep at the wheel regarding the huge impact on Australia.
AI also brings a new style of robotisation: the humanoid one, where not only factory process can be machine replace but all human activities in your human world
Loading unloading packet, refilling shelves, helping food and technically nursing and wiping your butt in the aged care facilities.
One humanoid for roughly $50k
Never sick, no strike working 24/7 365 days a year if you want to.
So some blue collars are at risks but probably even more most of office workers.
So what will these people do?
More BS jobs and public servants WFH couch potatoes?
Universal income?
Do we even have the choice, do we have the cash?
And are we doomed to see only the losers thriving in a society where effort, IQ or even EQ are worthless and maybe even counter productive.
So while our debt billions are going on in windmills and fart gas projects destroying mining and agriculture, the world is changing.
What do you think?
Where are the jobs for the kids starting a 3y degree this year?
Only so many plumbers or reno jobs ...

I've noted here that the tax income stream will be hit due to Robotics thus, by extension AI enabled ones at that ,replacing employees. So how will Medicare et al be funded when the income tax paying human is turfed from the workforce?

Just like the internet and how the govts. of the world failed to grappled the implications and impacts of it, so to with this new lot of s/ware and h/ware.

The scary part is that with having the internet at everyones fingertips, the dumbing down of our brains is in full swing. So too it the blind worship following/believing of all and sundry on the "socials".
Shunder to think how AI will only exacerbate that.

As an amatuer muso, I came across this "overnight" sensation. From what I can tell this is an "AI band". The Velvet Sundown, has reportedly been created by Spotify AI.

Article from the BBC and reads in part:

A band called The Velvet Sundown has had its tracks played hundreds of thousands of times on Spotify since appearing several weeks ago - without anyone knowing for sure what it is.

The band has a verified page on the music streaming platform, with more than 850,000 monthly listeners.

However, none of the four named musicians in the band have given any interviews or appear to have individual social media accounts, and there are no records of any live performances.

Bad enough being replaced by robots, seems worse when it's by some anonymous AI manifestation.

 

[TimeISmoney]

Only public servants numbers are increasing in such scheme, more BS jobs

They're the jobs AI needs to take over first, I had over 15 meetings with a govt compliance officer over a developer that govt passed to encroach their building on our property. It went around in circles for over 2 years.

 

[TimeISmoney]

not quite an Aldi situation but was chatting to the check-out lady ( she was clearly middle-aged , maybe even the manager ) and that discount shop has had a plague of shop thefts even by ( prepared ) professional shoplifters ( including rigged baby-strollers ) in the last year

and that is in a rural city of Warwick ( in QLD ) !!!

i don't know how AI and humanoids will slow that down .. doors to lock you in until you have paid for everything , perhaps

Robots will chop your fingers off as soon as you leave the store without paying for something.

 

[countrylad]

I think it will have its uses, the most obvious to me is the mining industry, soon we will have sites that were having 500+ people on a site could be well below 50. We already have driverless remote controlled trucks its only a matter of time we have humanoid robots etc in place.

The upside for AI/Robotics in an underground mine is huge, the amount of infrastructure that will not be needed is immense, I have no proof but it would not surprise me if China has not got one already and its only a matter of time before the Western World adapts to the technology and its advantages. I have seen footage of "black" factories in China, which is almost completely automated and no need for lights.

Its effect on society is already here, I have said for years our education system needs over hauling and is not suitable to the world we live in currently, what will it be like in 10.15 and 30 years time.

 

[TimeISmoney]

They'll use this on humans one day.

 

[SirRumpole]

The problem is AI is not yet perfect, may never be as it depends on having large amounts of verified data, and ensuring that data is "clean" is difficult.

So there has to be humans responsible for the decisions of AI, and if there isn't then it could be dangerous.

 

[qldfrog]

The problem is AI is not yet perfect, may never be as it depends on having large amounts of verified data, and ensuring that data is "clean" is difficult.

So there has to be humans responsible for the decisions of AI, and if there isn't then it could be dangerous.

we are already well past this
to elaborate, just in coding..yes someone "validate the code " but probably has no idea, and for AI driven drones in Ukraine to avoid jamming, I doubt anyone press on the button "fire" once they are launched

 

[Smurf1976]

we are already well past this

AI is already at the point it can (has actually) produced a convincing "live" performance video of a band that does not exist, at all, in reality.

It can already perfectly mimic humans in terms of the whole thing. Write the lyrics and music, do the singing and instrument playing, produce a video clip of the band on stage. Not simply based on an actual real band but the whole thing's fictional.

Or for another random example, the next federal election campaign may well feature completely fake policy announcements with what looks to be the real party leader making them, and done so convincingly nobody can actually prove it's fake or even distinguish which is the real human and which is the fake AI on a screen.

Or interfering with politics in more subtle ways. Doesn't need to be anything drastic - just produce some video of politicians doing things the general public wouldn't be keen on them doing.

The potential for disinformation and use by hostile actors to influence the outcome of an election is obvious.

Or for another there's CCTV. The idea that the camera doesn't lie is no longer true. Being "caught" on camera no longer proves you committed the crime or were even there given the whole thing can be faked. It doesn't even prove the crime even occurred at all.

That has massive implications for the arts, politics and law enforcement. And that's just the tip of the ice berg.

Or for a more concerning one on a stock market forum, will it even be possible for any human trader or investor to beat a fund run by AI?

My view is the ultimately implications will be up there with the internet, electricity or cars in a practical sense and up there with the atomic bomb geopolitically. At some future time the list of things that didn't change because of it will be incredibly short.

 

[SirRumpole]

I've already seen a video clip of our Prime Minister flogging investment schemes.

Whether it was produced by AI or just clever editing I don't know, but if we can't control our own technology in relatively harmless issues, we certainly can't trust it with weapons.

 

[qldfrog]

we are already well past this

I've already seen a video clip of our Prime Minister flogging investment schemes.

Whether it was produced by AI or just clever editing I don't know, but if we can't control our own technology in relatively harmless issues, we certainly can't trust it with weapons.

If you go to "hold your fire" Joe Rogan postcasts, you will be able to find a few interviews on this AI subject, from relevant knowledge sources.
Outside their ABC/guardian restricted views and with top notch experts discussing broader implications, and risks.
My starting this thread follows a podcast among others with Roman Yalpolskiu
Some are wacky etc but open your mind
Quantum computers discussion 40y ago were wacky..

 

[qldfrog]

From Mr Ducati

https://www.wsj.com/tech/ai/ai-white-collar-job-loss-b9856259

 

[Antirnator]

The AI evolution will make energy great again, it's totally MEGA. Now if only we had the stuff and the knowhow to get that energy.

 

[SirRumpole]

Question to Chat-GPT:-

how do you as an AI validate the data you rely on to answer questions?

ChatGPT said:​

That's an excellent and important question.
As an AI, I don’t "validate" data in the traditional sense that a human might (by cross-checking sources, understanding context in a subjective way, or applying real-world judgment). Instead, I rely on a combination of training data, built-in mechanisms, and user prompts to generate accurate, relevant answers.

Here’s how that works in practice:

---

1. Training on curated data​

My responses are based on patterns learned from:

• Books, articles, websites, manuals
• Academic sources and documentation
• Reputable online communities (e.g., Stack Overflow, Wikipedia, government and scientific sites)

The data was filtered and curated during training by OpenAI to remove known misinformation, low-quality content, and unsafe material. This gives me a strong foundation — but it's still just a model of language patterns, not an index of verified facts.

---

2. Cross-source pattern recognition​

I don’t quote specific sources unless asked, but I can generalize from many during training. So if 99 out of 100 tutorials say “C++ uses RAII for memory management,” I’ll reflect that consensus — effectively surfacing the statistical majority of expert guidance.
That said, I don’t know if something is “true”, only that it is strongly supported by the data I was trained on.

---

3. Built-in constraints and refusal policies​

When I detect that a question:

• Requires real-time data (like weather or current news),
• Involves medical/legal/financial decisions, or
• Could lead to unsafe actions (e.g., bypassing safety mechanisms),

I’m programmed to respond carefully, include disclaimers, or refuse to answer outright. That’s part of how OpenAI enforces responsible AI usage.

---

4. Tool use for validation (when enabled)​

If you’re using a version of ChatGPT with web access enabled (like GPT-4 with browsing), I can:

• Search the internet in real time
• Open and extract information from live pages
• Validate or update my responses when needed

I’ll always say when I’m using a live source.

---

5. User feedback and refinement​

If you tell me, “That’s incorrect” or “Source X disagrees,” I can reconsider the logic or offer alternative perspectives — and OpenAI uses user feedback at scale to retrain and fine-tune future models.

---

Summary​

Method	Role in Data Validation
Training on curated data	Ensures broad accuracy and consensus-based knowledge
Pattern recognition	Finds reliable language patterns across thousands of sources
Refusal and guardrails	Avoids unsupported or dangerous suggestions
Web access (if enabled)	Lets me fetch and cross-check current or niche information
Feedback loop	Allows refinement based on what users point out or correct

---

Let me know if you'd like to see how I check specific kinds of information (e.g., verifying code, scientific claims, or legal rules).