MBA.co.za
Milpark Business School
Tel:
+ (27) 86 999 0001
Website:
Visit our website

AI: Our creations have become creators

Photo: Prof. Johan Steyn
Prof. Johan Steyn answers the burning questions from a recent discussion at Milpark Business School.

Prof. Steyn is a Human-Centered Artificial Intelligence advocate and thought leader; and one of the top 50 global voices on AI as recognised by SwissCognitive.

I would love to know how the CA community is integrating AI to ensure the qualification remains relevant in the modern work force.

One way the community can integrate AI is by incorporating it into their training programmes. This can include courses on AI and data analytics, as well as hands-on training in using AI tools and software. By providing chartered accountants with the necessary knowledge and skills to use AI, they will be able to better serve their clients and provide more value.

Another way to integrate AI is by using it in the audit process. AI can be used to automate repetitive tasks, such as data entry and analysis, which can free up time for chartered accountants to focus on more complex tasks. It can also be used to identify patterns and anomalies in financial data, which can help to uncover fraud and other irregularities.

Semi-conductors followed Moore's Law; is there a theory that seeks to predict improvements in AI?


Quantum computing has the potential to significantly impact Moore's Law, which is the observation that the number of transistors in a microchip doubles approximately every two years, leading to a corresponding increase in computing power.

One of the primary advantages of quantum computing is its ability to perform calculations in parallel, rather than the linear approach used in classical computing. This means that quantum computers have the potential to solve problems that are beyond the capabilities of classical computers, including problems related to encryption, drug discovery, and machine learning.

Quantum computing has the potential to disrupt the traditional computing industry, and may eventually replace some of the functions currently performed by classical computers. This would have significant implications for Moore's Law, as the rate of improvement in computing power would likely increase at a much faster pace than it has in the past.

Are SA insurance companies embracing AI and digitalisation?

Yes, many local insurance companies are increasingly embracing AI and digitalisation to improve their operations and provide better services to their customers. In fact, AI is becoming a critical component of the insurance industry, as it can be used to streamline processes, reduce costs, and improve decision-making.

One way that insurance companies are using AI is through chatbots and virtual assistants. These AI-powered tools can be used to provide customers with personalised recommendations and advice, as well as to help them file claims and resolve issues more quickly.

Another way that insurance companies are using AI is through predictive analytics. By analysing large volumes of data, including customer demographics and past claims, AI can be used to identify patterns and trends that can help insurers better assess risk and set prices.

How do we leverage technology to create and grow our nations’ wealth? What impact does it have on sustainability? Is it really open to everyone?

Leveraging technology is a critical component of creating and growing a nation's wealth. Technology can be used to improve productivity, create new industries and jobs, and improve the efficiency and effectiveness of existing industries. It can also help to reduce costs, increase revenues, and create new business models.

One of the key impacts that technology has on sustainability is its ability to help us better manage resources and reduce waste. For example, smart technologies can be used to optimise energy consumption, reduce greenhouse gas emissions, and promote more sustainable practices in agriculture and manufacturing.

However, it is important to ensure that the benefits of technology are accessible to everyone. This means investing in education and training programmes to ensure that people have the necessary skills to participate in the digital economy. It also means ensuring that everyone has access to the infrastructure and tools needed to benefit from technology, including broadband internet and affordable devices.

Sadly, in South Africa many people are part of the ‘digital divide’ – lacking suitable internet access, devices and even electricity. It does not seem that our government has an actionable plan to address these issues at scale in the short term.

Will ChatGPT open stocks to the public? If so, when do you think this will happen?

There is no indication that this will happen. I doubt that OpenAI will want their stock to be traded publicly. They certainly do not need additional investments and funding.

It is very difficult to regulate biases. Everyone, whether they are the same skin colour etc, faces different challenges. There are 8+ billion people. How possible would it be to factor in all these biases? Even as humans, we struggle to relate to each other, how much more to a machine made by ‘imperfect’ designers?

Bias in data sets will always remain a problem; I do not think we can eradicate it 100%. However, we should always be aware of these problems and work together in mitigating these.

Google skews your options based on your previous searches. So how will that affect the answers you get to your question?

Google uses algorithms to personalise search results based on your previous searches, as well as other factors such as your location, language preferences, and device type. This means that the answers you get to your question may be skewed based on these factors.

To address this issue, you can take steps to expand your search and reduce the impact of personalisation on your results. One way to do this is to use more general search terms, rather than specific keywords that may be influenced by your previous searches. You can also try using different search engines or using a private browsing mode, which may reduce the impact of personalisation on your results.

OpenAI was a nonprofit organisation. This flip to profit/valuations is very scary. It will be very interesting to see whether the values of ‘helping humanity’ will remain uncompromised, unlike Facebook that has become the villain of the century with its data violation issues.


The transformation of OpenAI from a non-profit organisation to a profit-driven enterprise has raised concerns about whether their values of ‘helping humanity’ will remain uncompromised. This is a valid concern, as we have seen in the past how some companies have put profits ahead of ethical considerations, leading to negative consequences for society.

OpenAI has stated that its mission and values will remain unchanged, even as it pursues a more commercial focus. The organisation has committed to continue developing and promoting AI technologies that are safe, beneficial, and aligned with human values.

To ensure that its values are not compromised, OpenAI has taken steps to ensure that its governance structure is transparent and accountable, and that its research is subject to rigorous ethical review. The organisation has also established a safety team to oversee the development of AI technologies and ensure that they are safe and beneficial for all.

How safe is it to dump information or data into ChatGPT? If I input data that is sensitive, then where or how does it get stored or who has access to it?


As an AI language model, ChatGPT is designed to process text inputs and generate responses, and does not retain or store any user data beyond the duration of a single session. This means that any information or data that you enter into ChatGPT will not be stored or accessed by anyone else.

It is important to be aware that there are potential risks associated with sharing sensitive information online, including the possibility of data breaches or unauthorised access. As a general rule, you should avoid sharing any sensitive or confidential information in an online environment, and should take steps to protect your personal data and information.

How long do you think it will take for the traits that make humanity unique, to inevitably disappear?

This is a difficult one, who knows? I doubt that all human attributes will disappear as a result of technological advances.

I'm just worried about plagiarism; how will it be detected?

There are a number of new platforms that claim to detect AI-generated text. In my experience, they are all fairly ineffective in detecting it. I guess plagiarism detection models will get better over time.

How important is professional scepticism when dealing with generative AI output?

Professional scepticism is an important trait in any field that involves analysis, interpretation, or decision-making. When dealing with generative AI output, professional scepticism becomes even more important because of the potential for bias, error, or unintended consequences.

Generative AI is designed to generate new content, based on patterns and algorithms derived from large data sets. While these algorithms can be very effective in creating realistic and compelling content, they are not perfect, and may produce results that are flawed, biased, or inaccurate.

When dealing with generative AI output, this means taking a critical and analytical approach to the results, and being willing to scrutinise and validate the output using other sources and methods.

If you ask it to apply Roman Dutch law, will it be correct?

As an AI language model, ChatGPT has been trained on a vast corpus of text data, and has a general understanding of legal concepts and terminology. However, it's important to note that AI models like ChatGPT are not legal experts and may not have a full understanding of the nuances and complexities of specific legal systems, such as Roman Dutch law.

While ChatGPT may be able to provide some general information or insights on Roman Dutch law based on its training data, it should not be relied upon as a substitute for professional legal advice or consultation. If you have specific questions or concerns about Roman Dutch law, it's always best to seek guidance from a qualified legal professional who has experience and expertise in this area.

As a qualitative researcher, would you suggest using ChatGPT to enhance the clarity and coherence of participants' responses during transcription?

ChatGPT can be a useful tool for generating and clarifying responses during transcription, particularly in cases where participants may have difficulty expressing themselves clearly or coherently. However, it's important to use ChatGPT judiciously and to recognise its limitations. It may not always generate responses that accurately reflect the intended meaning or tone of the original statement, particularly in cases where the language used is highly technical or domain specific.

It is important to recognise that the use of AI tools like ChatGPT in qualitative research may raise ethical and methodological concerns, particularly with regard to issues of data privacy, transparency, and reliability.

Can the AI (ChatGPT) include references in its write-up so we can read up further on the information it is providing?

If ChatGPT generates a response that discusses a particular concept or idea, it can provide a hyperlink to an external source or resource that provides more in-depth information about that concept or idea. This can be a useful way to provide additional context and support for the information being presented, and can help to enhance the reader's understanding and engagement with the topic.

It's worth noting that the ability of ChatGPT to reference external sources will depend on the specific use case and the available information on the topic being discussed. If the information being referenced is highly technical or domain specific, it may be more difficult for ChatGPT to provide accurate and useful links to external sources.

I imagine that in the future we will be so dependent on this this that an AI crash of some sort may leave humans totally disabled. What measures do they have in place for this eventuality?


While an AI crash or failure is a possibility, there are measures that can be taken to mitigate the risks and minimise the potential impact. By developing backup systems and redundancies, designing AI systems with error detection and correction mechanisms, and establishing contingency plans and emergency protocols, we can help to ensure that our reliance on AI does not leave us vulnerable to catastrophic failures. It is up to governments and large corporates we rely on to have these measures in place.

Must we wait for something to go wrong first before we start thinking about how to regulate the potential abuse that may arise from this technology... is it possible to be proactive with law-making in the future?

Sadly, sufficient regulations often only arise after a large-scale problem. There are a few good global initiatives to regulate this technology, but almost nothing has been done in SA so far. We should be proactive in law-making and it will require good collaboration between the government, academia, civil society and business.

There was an article, UN says AI poses 'serious risk' for human rights. Please comment about this, Johan.

The United Nations has raised concerns about the impact of AI on human rights, citing the potential for AI to perpetuate or even exacerbate existing biases and discrimination. In a report issued by the UN's human rights office in 2021, the organisation warned that AI could pose a "serious risk" to human rights in a variety of areas, including privacy, freedom of expression, and equal treatment under the law.

The report also raises concerns about the potential for AI to erode privacy and freedom of expression, particularly in cases where AI is used for surveillance or content moderation. There is a risk that AI systems could be used to monitor individuals or groups without their knowledge or consent, or to censor or restrict access to information in ways that violate freedom of expression.

How do we remain relevant in the face of this massive disruption?

The rapid pace of technological change and disruption is posing significant challenges to individuals and organisations across industries and sectors. To remain relevant in the face of this disruption, it's important to adopt a mindset of continuous learning and adaptation, and to prioritise the development of new skills and competencies that are in demand in the new technological landscape.

One key strategy is to invest in ongoing education and professional development, and to seek out opportunities to learn new skills and acquire new knowledge. This might involve pursuing additional formal education or training, attending conferences and events, or engaging in online learning or self-directed study. By remaining curious and open to new ideas and approaches, individuals can better position themselves to adapt to changing technological demands and stay relevant in the face of disruption.

There's also the consideration of Third World countries getting left behind. Take for instance SA, how can we possibly take advantage of these technologies, still battling with load shedding?

You raise an important point regarding the potential for developing countries to be left behind in the face of technological disruption. While the adoption of new technologies can present significant challenges for countries that are still grappling with basic infrastructure issues like access to reliable electricity, there are strategies that can be employed to help bridge this gap and promote greater access to technology and its benefits.

One key approach is to focus on building the necessary infrastructure to support the adoption and use of new technologies. This might involve investing in the development of reliable energy systems, such as renewable energy, to help address issues like load shedding and provide a more stable and consistent source of power. It could also involve investing in broadband infrastructure and other forms of digital connectivity, to help ensure that individuals and organisations have access to the digital tools and resources they need to take advantage of new technologies.

Another important strategy is to focus on building local capacity and expertise, and developing programs and initiatives to help individuals and organisations build the skills and competencies they need to take advantage of new technologies. This might involve investing in education and training programs, developing mentorship and coaching programs, or providing access to resources and support networks to help individuals and organisations build their capacity to adopt and use new technologies effectively.


Catch up on the full webinar here: https://lnkd.in/df5t-3nU
Share on Twitter Share on LinkedIn Share on Facebook
Share via Email