Artificial intelligence: a threat or an opportunity?
It’s with us already in areas most of us probably don’t realise, but what does artificial intelligence mean for our future? What threats and opportunities does it present? Does education need to adapt, and how?
Stuart Lacey has no doubt: artificial intelligence is a game-changer.
He paraphrases a quote from AI guru Peter Diamandis, saying: “There are two kinds of companies — those that will mass adopt generative and artificial intelligence by 2030, and the rest that’ll be out of business”.
That, said Mr Lacey, a cofounder and the chief executive of the Bermuda Clarity Institute, is the warning shot across the bow.
“I think there are companies that will cease to exist if they don't change their current business model,” he added.
“But more importantly, I think it’s not actually about replacing jobs, it’s replacing tasks. The thoughtful use of AI is, how do you look at your company, your organisation, or what you’re trying to accomplish, and utilise it as an efficiency gain?”
Risks to employment are often foremost in people’s minds when AI is discussed and the International Monetary Fund recently published a report that said that AI will affect almost 40 per cent of jobs around the world, replacing some and complementing others.
There are other possible threats such as ethical dilemmas, security risks, a concentration of power and economic inequality that make people wary of the technology and how it is applied.
Aaron Smith, the president and CEO of the Igility Group of Companies, who has joined the BCI as AI growth leader for Bermuda, said that since the industrial revolution there were many disruptions to how people worked, accompanied by predictions of the demise of the workforce.
Stuart Lacey, the cofounder and chief executive of the Bermuda Clarity Institute, said education around artificial intelligence “is critical”.
He added: “This is one of the biggest opportunities we’ve ever seen to change how we educate and to bring a class of people up with cutting-edge access to tools and knowledge at a fraction of the cost it’s ever been done.
“I read something recently that I think might capture the essence of where AI can play a part. I can't be able to recite the exact numbers, but it's more than 100 per cent.
“So where teachers have teacher's assistants, learning in those classrooms is accelerated by a number that’s well over the norm. Where students have tutors, their learning capability is accelerated well over the norm.
“What AI is literally doing is giving every teacher the ability to have teacher’s assistants and every student the ability to have a tutor.”
He said if every teacher and student had an AI assistant, “you're talking about learning at an accelerated pace”.
Aaron Smith, the president and chief executive of the Igility Group of Companies, who has joined the Bermuda Clarity Institute as AI growth leader for Bermuda, remembered when the use of calculators was banned.
He said: “The ability to actually know and understand how the tools that are of your time can be used is what makes you better. It prepares you better for the workforce.
“These tools are going to be there and we need the ability to be a critical thinker and to know what to believe and what not to believe.”
Mr Lacey said he would bring AI on to the syllabus for students.
He explained: “I see the job of modern education, from elementary through to graduate, is to graduate students that are ready for the world they’re about to go into.”
He said the big push was Stem education, which concentrates on science, technology, engineering and mathematics, but Mr Lacey added: “Granted those will be important, but they're also the areas where AI is having the greatest application.”
On the darker side is the ability to generate deepfakes — the manipulation of information and images — using AI in unmanaged, unethical, biased and potentially dangerous ways.
Mr Lacey added: “You’ve got to educate, just like child sexual education or ethical education.”
“I suspect it's actually gone the other way. There have to be more people employed now than there ever were,” he said, adding that there would be “careers that have never existed before”.
While AI might reduce the number of people to complete a task, the flip side is that one person can do the work of four or five people.
Mr Smith added: “A small individual entrepreneur now has the ability to basically create three, four or five jobs around them just by embracing AI.
“That could allow businesses that we have maybe not given a lot of attention to in Bermuda, to survive in Bermuda and maybe work not just within Bermuda, but outside Bermuda.”
Mr Lacey added: “Every time we’ve gone through a major industrial revolution, internet revolution, printing revolution, we found net job creation, not net job loss.”
He said it was possible that this era could be first time that does not happen, but pointed to huge growth in demand for prompt engineers.
The website datacamp says that prompt engineering “is the practice of designing and refining prompts — questions or instructions — to elicit specific responses from AI models”.
Mr Lacey said: “It might just be that the largest new opportunity is how do companies bring on part-time roles for people who know how to thoughtfully interact with these models to generate tremendous benefits so that, maybe, your inbox is handled, or that huge list of stuff that wasn't done is done, and then the company can retask that person.
“I would argue smart companies will be moving their staff to better service their customers and away from the menial stuff.”
Google AI and Google had this definition:
“Artificial intelligence is a field of science concerned with building computers and machines that can reason, learn and act in such a way that would normally require human intelligence or that involves data whose scale exceeds what humans can analyse.
“AI is a broad field that encompasses many different disciplines, including computer science, data analytics and statistics, hardware and software engineering, linguistics, neuroscience and even philosophy and psychology.
“On an operational level for business use, AI is a set of technologies that are based primarily on machine learning and deep learning, used for data analytics, predictions and forecasting, object categorisation, natural language processing, recommendations, intelligent data retrieval and more.”
It added: “Artificial intelligence can be organised in several ways, depending on stages of development or actions being performed.
“For instance, four stages of AI development are commonly recognised:
1, Reactive machines: limited AI that only reacts to different kinds of stimuli based on preprogrammed rules. Does not use memory and thus cannot learn with new data. IBM’s Deep Blue that beat chess champion Garry Kasparov in 1997 was an example of a reactive machine
2, Limited memory: most modern AI is considered to be limited-memory. It can use memory to improve over time by being trained with new data, typically through an artificial neural network or other training model. Deep learning, a subset of machine learning, is considered limited-memory artificial intelligence
3, Theory of mind: theory-of-mind AI does not exist at present, but research continues into its possibilities. It describes AI that can emulate the human mind and has decision-making capabilities equal to that of a human, including recognising and remembering emotions and reacting in social situations as a human would
4, Self-aware: A step above theory of mind, yet-to-exist self-aware AI describes a mythical machine that is aware of its own existence and has the intellectual and emotional capabilities of a human
“A more useful way of broadly categorising types of artificial intelligence is by what the machine can do.
“All of what we currently call artificial intelligence is considered artificial ‘narrow’ intelligence, in that it can perform only narrow sets of actions based on its programming and training. For instance, an AI algorithm that is used for object classification won’t be able to perform natural language processing.
“Google Search is a form of narrow AI, as is predictive analytics, or virtual assistants.
“Artificial general intelligence would be the ability for a machine to ‘sense, think and act’ just like a human. AGI does not currently exist.
“The next level would be artificial superintelligence, in which the machine would be able to function in all ways superior to a human.”
Considering the island, he added: “We already have lots of companies in Bermuda that are fractional financial offices, right? You don't need a full accountant, you get a fractional [part-time] accountant.”
A fractional professional or team becomes part of the organisation, but for a certain number of hours a week or days a month.
Mr Lacey said: “Will our labour force increasingly move to fractional roles? Probably.
“Will individuals and small companies in Bermuda benefit from offering fractionalised services across a broad rate? Absolutely.
“Will they be using these kind of technologies to do it? They will.
“We knew during Covid that a lot of people started working remotely. A lot of people became fractional in their role and became knowledge workers.
“Now, we either compete with that and provide that locally, or we lose those jobs overseas, when someone in a foreign part of the world provides that knowledge service.
“How do we compete? We compete by embracing and understanding the change and leading the change.”
In that context, he envisaged a huge opportunity to embrace AI for the island.
Mr Lacey said: “There is a big green light there. I think Bermuda needs to be very thoughtful in what sectors does AI really provide opportunity.”
For Mr Smith, although some AI-related threats are real, he trusts humans to deliver improvements.
“Yes, there are bad actors,” he said. “But I have faith in humans and our spirit to make things better for people, not worse.”
Mr Lacey, who said that regulators were starting to govern the technology, added: “Should we be wary of Skynet and all the taking over the world and Terminator? No.
“The reality is where it’s actually hitting. Like deepfakes.”
Deepfakes are synthetic media that have been digitally manipulated to replace one person's likeness convincingly with that of another, or the manipulation of facial appearance through deep generative methods.
Mr Lacey said: “There’s an all-out assault on truth, right? We have an election cycle about to happen in the US and you actually don't know, not just the picture, but the video, the voice, if it’s real or not.”
As an exercise, The Royal Gazette asked Microsoft’s Copilot to write “an article on the dangers and benefits of artificial intelligence to Bermuda”.
The piece is pretty generic and could be based in any jurisdiction, but it’s not wrong. It is readable as well.
It also took less than one minute to write …. are our reporters’ jobs safe?
Microsoft Copilot generated this:
“Artificial intelligence has the potential to revolutionise many aspects of life in Bermuda, from healthcare to finance to transportation. However, as with any new technology, there are both benefits and risks to consider.
“One of the most significant benefits of AI is its ability to improve healthcare outcomes. AI can help doctors and other healthcare professionals diagnose diseases more accurately and quickly, leading to better treatment outcomes for patients.
“AI can also help healthcare providers identify patients who are at risk of developing certain conditions, allowing for earlier intervention and prevention. Additionally, AI can help researchers analyse large amounts of data to identify new treatments and cures for diseases.
“Another area where AI can have a significant impact is in finance. AI can help financial institutions detect fraud and other financial crimes more effectively, reducing losses and protecting consumers.
“AI can also help financial institutions make better investment decisions by analysing large amounts of data and identifying patterns that humans might miss. This can lead to better returns for investors and more stable financial markets.
“AI can also improve transportation in Bermuda. Self-driving cars, for example, could reduce traffic congestion and make roads safer by eliminating human error.
“Additionally, AI can help optimise public transportation systems, making them more efficient and reducing wait times for passengers.
“However, there are also risks associated with AI that must be considered.
“One of the biggest risks is the potential for AI to be used for malicious purposes. For example, AI could be used to create fake news stories or deepfakes that are difficult to distinguish from real news or videos.
“This could have serious consequences for democracy and public trust in institutions.
“Another risk associated with AI is the potential for job loss. As AI becomes more advanced, it could replace many jobs that are currently done by humans.
“This could lead to significant economic disruption and social unrest if not managed properly.
“Finally, there is the risk that AI could be used to create autonomous weapons that could cause significant harm to people and infrastructure.
“This is a particularly concerning risk given the strategic location of Bermuda and the presence of military bases on the island.
“In order to maximise the benefits of AI while minimising the risks, it is important for policymakers and other stakeholders in Bermuda to take a proactive approach to regulating AI.
“This could include developing ethical guidelines for the use of AI, investing in education and training programmes to help workers transition to new jobs, and supporting research into the development of AI safety mechanisms.
“Overall, AI has the potential to bring significant benefits to Bermuda in a variety of areas.
“However, it is important to carefully consider the risks associated with AI and take steps to mitigate them. By doing so, Bermuda can ensure that it is well positioned to take advantage of the benefits of this exciting new technology while minimising the risks.”
People entering the job market now perhaps face the greatest challenge as the work landscape could change quickly and dramatically.
Mr Smith said: “I have a 19-year-old in university and a 25-year-old who graduated from university a couple years ago.
“Interestingly, I had conversations with them not so long ago and I always remember my son was quick to say, ‘You know, the fact is the career that I’m going to have, the job I'm going to have, hasn't even been invented yet’.
“I think he’s right and that is the concept that I think we have to remember.”
He added: “I've said this since the beginning and I followed it myself — ‘Do what you know, do what you’re passionate about. Do what you really enjoy’.
“If you’re doing what you like and understand how to apply knowledge, you’re going to be an invaluable person in the future.”
What experiences have you had with artificial intelligence? What are your concerns over AI? What are your hopes for AI in the future? Does there need to be local regulation? E-mail your thoughts to jdeacon@royalgazette.com
• To listen to the full interview, click on the audio file and for the full IMF report into AI, see Related Media
Need to
Know
2. Please respect the use of this community forum and its users.
3. Any poster that insults, threatens or verbally abuses another member, uses defamatory language, or deliberately disrupts discussions will be banned.
4. Users who violate the Terms of Service or any commenting rules will be banned.
5. Please stay on topic. "Trolling" to incite emotional responses and disrupt conversations will be deleted.
6. To understand further what is and isn't allowed and the actions we may take, please read our Terms of Service
