Article by Original Dante and Bree Leto

1. Quick thoughts by Bree
2. Some Positives
   1. Stewardship/Efficiency by O.D.
   2. Progress by Bree
   3. Access to Learning by Bree
   4. Minimizing Errors by O.D.
   5. Removed Emotions from Decision-Making by Bree
   6. Cost saving by Bree
   7. Preservation of life by Bree
3. Some Negatives
   1. Unemployment by Bree
   2. Removing Emotions from Decision-Making by Bree
   3. Loss of ‘Authentic Art’ by O.D.
   4. Loss of skills (Over-reliance on AI) by O.D.
   5. Perceptions of reality by Bree
   6. Can people be trusted with AI? by O.D.
4. Summing up…
5. References
   1. Additional Reading and Resources
6. Acknowledgement

Quick thoughts by Bree

Is anything truly good or bad? Usually, it’s the people who determine if something harms others or not. The issue is trust. Do we trust people to make the ethical choice when deciding between morality and/or profit? Unfortunately, history has taught us that the latter is often the choice people make.

Similar to the Industrial Revolution, the development of Artificial Intelligence (AI) will certainly change our world. As we sit on the edge of this new era, we watch people consider how AI will impact us. Will it be for better or worse? Will the rich continue to be the only benefactors? Or, are we about to start something that we’ll all regret?

It’s natural to fear the unknown. It’s what has kept humans alive for so long, the instinct to protect ourselves. Time will tell if our fears are valid, or if this new world, the AI world, will bring humanity into a vastly improved existence.

Today we (Secret Thoughts Within & O.D.) are going to take a closer look at AI, the positive and the negative impact it has/ will have over our lives; stick around, and you might just learn something.

Some Positives

Stewardship/Efficiency by O.D.

Having AI at our fingertips is like having the ‘Professor of Everything’ ready and willing to help whenever and wherever. Why go to the library to rigorously search through resources to prove Steve is wrong about game theory when I can just ask AI what documents invalidate his assessment? Look, I’m lazy, and one might call AI an enabling tool for that laziness – I just call it efficiency.

Technology is designed to make our lives easier, to deny that notion is naive. The internet has been helpful in closing gaps and providing ease of communication, despite how it might be used nefariously by others. AI is an extension of that step, it is a tool that has many great uses outside the dangers it potentially poses.

Progress by Bree

The possibilities of AI for improving humankind’s quality of life are truly compelling. Collective brains, study and experience are the sources credited for progress and improvement in the last 100 years (see Max Roser). With the rise of AI and collated human knowledge, we can only begin to imagine what AI might suggest as we look to address the problems of the world. Greater intelligence is the clearest pathway to finding better outcomes.

Access to Learning by Bree

In the minefield that is the internet, AI can help translate and present information to cater to people’s preferences; whatever those preferences might be. Your way may be different from my way, but bridging the differences is in no way difficult for AI to manage.

Imagine what lies beyond the horizon of current technology. For those who are neurodivergent, with the help of AI, new pathways and opportunities could be just around the corner. Language and physical access could be barriers of the past, more so than they are now. The future of learning could be a more level playing field.

Minimizing Errors by O.D.

Depending on the task and the way in which it needs to be handled, the use of AI in reducing our margin of errors is undeniable. Is there potential for AI to make an error? Absolutely, however, with AI’s more advanced learning capabilities, the risk of the same error occurring (even from a different avenue) is nearly impossible.

AI (depending on its intended design and the amount of data collected/sampled) improves at a rate none of us could hope to match.

If we consider data analytics, for example, AI is perfectly suited for such a role. Manual data entry loses its novelty when compared to AI that notices errors we might miss. In a field that requires the utmost precision, are we willing to misplace one single digit (a very costly mistake) or are we willing to delegate high-stakes tasks to something better equipped to handle it?

AI will continue to improve, increasing in accuracy and speed as time progresses. To not use AI with tasks similar to that of data analytics is to forfeit a clear advantage. (also see Preservation of Life below)

Removed Emotions from Decision-Making by Bree

Of all the causes which conspire to blind
Man’s erring judgment, and misguide the mind,
What the weak head with strongest bias rules,
Is pride, the never-failing vice of fools.
(by Alexander Pope – Essay on Criticism, 1711)

To err is human (Alexander Pope, 1711). The reality is humanity is flawed. We are flawed and although this is what makes us fascinating, our flaws show up time and time again in the decisions we make. We don’t make good decisions when we’re: tired, hungry, upset, sad or angry. And all too often, we make decisions based on emotion, which can be completely self-serving, and have no logic.

Additionally, human emotions change all the time. This morning you may have been happy, this afternoon sad, and you’ll be influenced to make different judgments/decisions within those states. Therefore, emotions can be manipulated, and apart from a programming hack, AIs are not so easily influenced. Using non-emotive tools (AI) to make decisions in real-time, will likely lead to better outcomes.

Cost saving by Bree

One of the biggest motivations for businesses to use AI is in cost saving. Instead of paying individuals for years of education and experience, you can pay a subscription or platform fee and get access to fast business solutions. Fast. Easy. Cheaper. Sounds wonderful to the business owner trying to save money or stay afloat. As AI evolves and becomes integrated into more workplaces and industries just think… AI doesn’t need holidays or sick leave. It doesn’t worry about working on public holidays or needing time off to go to a funeral. It doesn’t slack off during work hours or check its socials when the boss leaves the room. In fact, AI can work 24/7 if required and without needing any bathroom breaks. Efficiency and ROI (Return on Investment) should skyrocket.

Preservation of life by Bree

Risks
Why risk a human when an AI can take their place.  There is huge potential to reduce loss of life in many areas, such as bomb disposal, chemical spills, space travel etc. This is of course based on the assumption that a human life will be seen as more valuable than an AI.

Healthcare
The advantages of AI in Healthcare are already being praised. It’s been proven that as AI works alongside doctors using clinical analytics, patients get better results. AI programs can seamlessly access all the medical knowledge available to achieve heightened accuracy when reading and understanding medical conditions. It’s truly unprecedented and beyond human capacity. The AIs are saving lives. Their prediction accuracy is leading to better outcomes for patients.

Additionally, if that wasn’t already something to sing about, it’s also helping train doctors faster

Health Worker Shortages
The World Health Organisation estimates by 2030, there’s going to be a global shortage of 10 million health workers. Unfortunately, this will occur in low-earning countries. Instead of having underqualified or no one at all, the evolution of AI could fill some roles with the healthcare sector. Diagnostic AIs could ease the burden and give patients a quicker and cheaper diagnosis through the use of photos.

Preventing Car Accidents
Smart cars and lifesaving AI apps, are already in use. The evidence shows they’re already saving lives and reducing accidents… One can only assume that as more cars and devices are utilized with AI assistance, the number of lives saved will increase. Of course, there are concerns and accountability issues still being worked out in this area, but that’s for another part of this article 😉

Human Trafficking
One Company is already using AI image recognition software to track and stop human traffickers and rescue their victims. The hours saved and accuracy given using AI could change lives forever. There was even an AI for Good Global Summit hosted by the United Nations University in 2021. This particular advancement is close to my (Bree’s) heart and the idea that technology can be used against people who exploit others (often through technology), makes me smile.

Some Negatives

Unemployment by Bree

In our *cough* (rich people’s) desire to save money and cut costs, we rush to cut employment. It’s the quickest way to save money. With the rise of AI’s ability to perform certain jobs, many people are about to be without a job. The benefits and drawbacks of advancement are both found within the human experience and depend on who you are. If you end up unemployed due to AI’s taking your job (we see this now with copywriters), your life certainly won’t be better. It will make it significantly worse. The writing and creative community is facing an unstable future, and only time will tell the human impact. And it’s not just specific industries, it’s usually those with fewer skills or education who are the most impacted when new technology comes along. Simply search the Industrial Revolution to see how the lower class fared (hint, not well). Let the divide between the haves and have-nots continue.

Also, spare a thought to those starting out and students trying to get experience in certain industries. How will you get experience when the only human jobs available are for those with advanced skills? Entry-level jobs may be a thing of the past.

Removing Emotions from Decision-Making by Bree

Let’s address our humanity again. To err is human, as mentioned before, but the full quote says:

To Err is Human; to Forgive, Divine
(Alexander Pope, 1711).

This is an interesting thought: humanity’s ability to forgive and show empathy – to look past facts, consider the unknown, and move beyond logic. At this stage in the AI journey, systems aren’t developed enough to understand the human soul. Emotions may get in our way, but they are also an essential part of decision-making and brokering peace.

Loss of ‘Authentic Art’ by O.D.

Take one look at AI art (the really good kind) and you’ll likely come to the same conclusion. AI art is dangerously impressive and flawless. It gets a little ominous when you consider how AI generates this amazing art based on collecting data from a variety of art samples that can be taken from the internet. Remember, these art samples can be taken without the artist’s permission, which is obviously wrong, but more on that later.

After we feed our AI tons of art, we can – if we so please – make an amalgamation of all styles to suit our preferences based on the parameters we would have set. All within the space of a few minutes.

If it took an artist 5 hours to paint the perfect looking orange and they upload it to the internet, I can take this orange, feed it to my AI and make slight deviations to avoid plagiarism.

“Took you 5 hours to paint that? Mate, my AI drew that in 5 minutes, keep up yeah?” – Random AI apologist.

This is obviously unfair, especially if we take into account the non-consensual nature in which AI generates it’s art. Even if the art is easily accessible with sites such as DeviantArt; noone has the right to misuse someone’s work without letting them know.

We can apply the same reasoning with the most recent case study involving a lawsuit issued by major authors against OpenAI.

The lawsuit claims that. “ChatGPT and the LLMs underlying it seriously threaten the livelihood of the very authors …on whose works they were ‘trained’ without the authors’ consent.”

Furthermore. “ChatGPT is being used to generate low-quality ebooks, impersonating authors and displacing human-authored books.”

This is a result of ChatGPT being used by Liam Swayne (a programmer) to ‘write’ the sequels to George R.R. Martin’s best-selling novel series “A Game Of Thrones”. George R.R. Martin has yet to publish the final novels in the series, however, that did not stop Liam Swayne from creating his own versions using ChatGPT and posting them online.

This is cause for concern because – “”When prompted, ChatGPT accurately generated summaries of several of the Martin infringed works, including summaries for Martin’s novels ‘A Game of Thrones,’ ‘A Clash of Kings,’ and ‘A Storm of Swords,’ the first three books in the series A Song of Ice and Fire,” – further elaborating on the nature in which AI can be fed large sums of data (without consent); which it then uses to infringe on peoples work.

AI is far more intelligent, and this sometimes results in it using the original curator’s work as a platform to illustrate/design something far much better. The issue isn’t that AI can do much better, it’s that it can use the combined creativity of undocumented authors and artists to perfect it’s design.

Loss of skills (Over-reliance on AI) by O.D.

AI is incredibly useful. So useful, in fact, it risks crippling creativity, intuition and critical thinking skills.

In a recent survey conducted by Fishbowl (questioning 11 793 workers from notable companies such as Amazon, IBM, Meta, Nike and Twitter) the results showed that ChatGPT has become a necessity in the workplace. It was revealed in the survey that 43% of workers were using ChatGPT for content creation. Of the 11 793 people that participated in the survey, it was revealed that 70% of the workers were also using ChatGPT without their bosses knowledge.

I know it’s easy for us to look at our lives and relate to the story of sticking it to the boss. It’s a good story, of the under-dog overcoming the big bad. But we also need to consider how it comes at the cost of undermining our own integrity and who we present ourselves as. It’s no longer about a worker receiving merit for a job well done, but about who has the better AI in their pocket. And I find that to be incredibly concerning.

When AI is now responsible for our ideas, their implementation and how we share – we risk entering what I would personally call a macro fugue state. Noone knows who anyone is, we all interact in a hyper-sanitized fashion, no room for happy accidents or unconventional connections leading to potential breakthroughs. Just AI.

It may not be as severe for everyone, but there is an incredible loss of identity here. When we refuse to think for ourselves and call up big daddy AI to handle everything, it would be no stretch of the imagination to claim AI becomes ones own deity. Noone would openly admit to this of course, but AI runs the lives of many, and continuing to rely upon it to the point of foregoing integrity only emboldens this claim. For proof of this, look no further than another survey that was conducted by Study.com questioning over 200 K-12 teachers on how they feel about ChatGPT.

The results mention the concerns of some teachers being the amount of cheating that arose as a result of ChatGPT (remind you of anything?) to the point of banning AI in the school. Another portion of the survey also reveals how some teachers are not at all concerned and believe AI will improve the students’ skills. That AI is a tool, and it should be used – my argument against this is how it presupposes that a majority of children are responsible and know when to stop.

If an adult worker can conceal their use of AI to gain favor from their boss at work, what chances do a majority of children have to use AI reasonably?

Perceptions of reality by Bree

With the increase in perfectly created realities, environments and filters, humanity is in real danger of becoming disconnected and dissatisfied with the real world. It’s painful to think of all the people who are already being impacted by this. They see AI creations and look at themselves. When they don’t measure up, the implication is that they are less, they are less valuable because the human brain doesn’t differentiate. There are countless articles already talking in depth about how humans engage with AI. Here are a few if you’re interested in reading further:

• Picture Perfect: The Hidden Consequences Of AI Beauty Filters
• The Hidden Dangers of Online Beauty Filters
• The bionic blues: Robot rejection lowers self-esteem
• AI and the future of humanity, Yuval Noah Harai discusses the ‘curtain of illusion’ at 23 minutes

Can people be trusted with AI? by O.D.

Based on what has been outlined here, my answer is “no”. But that’s not enough, so let’s explore different case studies in which AI was used and come to our own conclusions: 

• Cybercriminals have already started using OpenAI to create dangerous tools that allow inexperienced hackers to take part in fraudulent activities. It won’t take long before more experienced hackers improve on these initial AI models allowing for the less experiences hackers to participate with no barrier of entry (See TechX sources below)
• Deepfakes have continued to be used and abused by people on the internet, further proving how people cannot be trusted with AI (See “..uses and abuses of deepfake technology” below). AI is far too good, the level of discipline required for people not to abuse the power AI provides is insurmountable. We have people from all walks of life gaining access to AI, and as we’ve noticed (in the loss of skills segment), it takes very little for people to pursue and misuse something that gives them a clear advantage.
• History has proven time and time again that if there is an opportunity to make money, particularly with a new kind of technology – people are willing to capitalize on it. AI use in this regard is no different. While attempts to use AI for the betterment of others will undoubtedly exist; it would be insincere to assume noone will try and monopolize AI technology. But hey, don’t take it from me, let’s see the head-space regarding AI on an international level.

Here’s a qute from Vladimir Putin regarding AI. “Artificial intelligence is the future, not only for Russia, but for all humankind,” … “It comes with colossal opportunities, but also threats that are difficult to predict. Whoever becomes the leader in this sphere will become the ruler of the world.”

Can people be trusted with AI? Look no further than the thought process at the highest level of government. You’ll find your answer there.

Summing up…

Absent sharing our own personal biases, topics such as these benefit from having meaningful discussions. Which is why we encourage any and all interested in going deeper into AI to meet us in the comment section.

• Are you afraid of AI?
• Are people overreacting?
• Do you use AI in your day to day life?
• Has AI impacted you in any way?

Please, share your thoughts …  

References

Brantley, B. 2023. One Danger of Over Reliance on Artificial Intelligence: Process Debt. Available at: https://patimes.org/one-danger-of-over-reliance-on-artificial-intelligence-process-debt/ . Last accessed 25 October 2023.

Chojnacki, Jakub. July 2023. Artificial Intelligence saves lives, or how AI is revolutionizing medicine. Billennium. Accessible at: https://billennium.com/blog/artificial-intelligence-saves-lives-or-how-ai-is-revolutionizing-medicine/. Last accessed on 18 October 2023

Cremer, D & Kasparov, G. 2021. AI Should Augment Human Intelligence, Not Replace it. Harvard Business Review. Available at: https://hbr.org/2021/03/ai-should-augment-human-intelligence-not-replace-it . Last accessed 20 September 2023.

Fishbowl. 2023. 70% Of Workers Using ChatGPT At Work Are Not Telling Their Boss; Overall Usage Among Professionals Jumps To 43%. Available at: https://www.fishbowlapp.com/insights/70-percent-of-workers-using-chatgpt-at-work-are-not-telling-their-boss/. Last accessed 15 October 2023.

McDonald, A. 2022. The Uses and Abuses of Deepfake Technology. Canadian Global Affairs Institute. Available at: https://www.cgai.ca/the_uses_and_abuses_of_deepfake_technology . Last accessed on 25 October 2023.

Marr, Bernard, June 2023. Picture Perfect: The Hidden Consequences Of AI Beauty Filters. Forbes. Available at: https://www.forbes.com/sites/bernardmarr/2023/06/09/picture-perfect-the-hidden-consequences-of-ai-beauty-filters/?sh=5439a0d07d5d. Last accessed 22 September 2023

Nash, Kyle, Lea, Johanna M., Davies, T & Yogeeswaran, K, October 2017. The bionic blues: Robot rejection lowers self-esteem. Science Direct. Available at: https://www.sciencedirect.com/science/article/abs/pii/S0747563217305447. Last accessed on 22 September 2023.

Nicholson, Chris. 2017. Paging Dr. Robot: How AI Is Saving Lives and Disrupting Health Care. Marsh McLennan. Accessible at: https://www.brinknews.com/paging-dr-robot-how-ai-is-saving-lives-and-disrupting-health-care/. Last accessed 18 October 2023

Pichii, A. 2023. George R.R. Martin, John Grisham and other major authors sue OpenAI, alleging “systematic theft”. CBS News. Available at: https://www.cbsnews.com/news/openai-lawsuit-george-rr-martin-john-grisham-copyright-infringement/. Last accessed on 22 September 2023.

Pope, Alexander. 1711, An Essay On Criticism. Available at: https://www.poetryfoundation.org/articles/69379/an-essay-on-criticism. Last accessed 22 September 2023.

Roser, Max, 2016. Proof that life is getting better for humanity, in 5 charts. VoxMedia. Available at: https://www.vox.com/the-big-idea/2016/12/23/14062168/history-global-conditions-charts-life-span-poverty. Last accessed 18 September 2023

Study.com. 2023. ChatGPT in The Classroom. Available at: https://study.com/resources/chatgpt-in-the-classroom . Last accessed 15 October 2023.

TechX. 2023. Cybercriminals turn to ChatGPT for help in their nefarious activities. Available at: https://techxmedia.com/cybercriminals-turn-to-chatgpt-for-help-in-their-nefarious-activities/ . Last accessed on 25 October 2023.

The Verge. Putin says the nation that leads in AI ‘will be the ruler of the world’. Available at:https://www.theverge.com/2017/9/4/16251226/russia-ai-putin-rule-the-world . Last accessed on 25 October 2023.

United Nations University. 2021. AI for Good Global Summit: AI To Prevent Modern Slavery, Human Trafficking and Forced, and Child Labour. United Nations University. Accessed at: https://unu.edu/cpr/event/ai-good-global-summit-ai-prevent-modern-slavery-human-trafficking-and-forced-and-child. Last accessed 18 October 2023

Well, Tara (Ph.D.). May 2023. The Hidden Dangers of Online Beauty Filters. Psychology Today. Available at: https://www.psychologytoday.com/au/blog/the-clarity/202303/can-beauty-filters-damage-your-self-esteem. Last accessed on 22 September 2023

World Health Organisation. 2023. Health Workforce. World Health Organisation. Available at:
https://www.who.int/health-topics/health-workforce#tab=tab_1. Last accessed on 18 October 2023

!important Safety Technologies USA Inc, 2018-2023. Available at: https://important.com/

Additional Reading and Resources

Suleyman, M and Harari, Y. 2023.  -FULL DEBATE- What does the AI revolution mean for our future? Available at: https://www.youtube.com/watch?v=7JkPWHr7sTY (46:16 mins)

Sutherland, J and Widdows, H. 2023. AI Confirms Our Unrealistic Body Ideals. Psychology Today. Available at: https://www.psychologytoday.com/au/blog/perfect-me/202305/ai-confirms-our-unrealistic-body-ideals.

The Bulimia Project, Scrolling Into Bias: Social Media’s Effect on AI Art: https://bulimia.com/examine/scrolling-into-bias/

Ameen, N, Cheah J and Kumar, S. 2022. It’s all part of the customer journey: The impact of augmented reality, chatbots, and social media on the body image and self-esteem of Generation Z female consumers. Available at: https://onlinelibrary.wiley.com/doi/full/10.1002/mar.21715

Bornet, Pascal. How Intelligent Automation Can Save Millions of Lives Per Year. Cognitive Automation Community. Available at:

https://www.cognitiveautomation.com/resources/how-intelligent-automation-can-save-millions-of-lives-per-year

Our World in Data. 2020. The World As 100 People over the last two centuries. Available at: https://ourworldindata.org/uploads/2017/01/Two-centuries-World-as-100-people.png

Acknowledgement

The writing of this article first started in August 2023, so shout out to O.D. for spending hours researching and going down rabbit holes as we immersed ourselves in all things AI. I know which parts you struggled to write because they went against your personal views 🙂 Also, are your various news feeds clogged with articles about AI like mine are? Bloody algorithms!