Regulations, Risks & Ethical Considerations and Opportunities of Generative AI
Mehmet Karakaya
Head of Sustainability at Siemens | Energy Performance Contracts | Digital Transformation | Digital Solution Sales | Generative AI
In the scope of Sabanci University – Data Analytics Graduate Program DA-522 Information Law and Data Ethics Final Project, I kindly share my study for whom may it concern:
Then let's start with Contents:
Contents
1. Introduction
Generative artificial intelligence (GenAI) represents a branch of AI that specializes in the creation of various forms of content, including text, images, and other multimedia. By analyzing the patterns and structures found within the input training data, Generative AI models are able to synthesize new data that bears resemblance to the original. This process involves complex algorithms and statistical methods, allowing the models to understand and replicate intricate details.
During the early part of the 2020s, the field of Generative AI witnessed significant advancements, particularly with the development of transformer-based deep neural networks. These innovations led to the creation of several prominent Generative AI systems, such as large language models like ChatGPT, Bing Chat, Bard, and LLaMA. Additionally, text-to-image AI art systems like Stable Diffusion, Midjourney, and DALL-E emerged, pushing the boundaries of creativity and technology. These systems have not only demonstrated the ability to generate human-like text but also to translate textual descriptions into visual art.
The applications of Generative AI extend across a multitude of industries, encompassing areas such as art, writing, software development, product design, healthcare, finance, gaming, marketing, and fashion. The early 2020s saw a significant increase in investment in Generative AI, with tech giants like Microsoft, Google, and Baidu, as well as many emerging startups, actively developing and implementing Generative AI models. This surge in interest and funding has led to rapid advancements and widespread adoption. However, alongside the positive impact, concerns have arisen regarding the potential misuse of Generative AI. Issues such as cybercrime, the creation of fake news, and the production of deepfakes, which can deceive or manipulate individuals, have become pressing challenges that require careful consideration and regulation. [1]
In the context of this graduation project, a comprehensive examination will be conducted on the Regulations, Risks, Ethical Considerations, and Opportunities associated with Generative AI. This will include a detailed evaluation of the significant risks that accompany the use of Generative AI technologies, as well as an exploration of the potentially transformative effects that major breakthroughs in this field could have on our daily lives. The project aims to provide a balanced perspective, highlighting both the promising potentials and the critical concerns that must be addressed to ensure responsible and beneficial utilization of Generative AI.
2. Regulations
In the past years and especially in recent months, we have seen that many countries and even unions have started to publish laws, rules and regulations in line with the rapidly developing Generative AI technologies within the scope of AI regulations. We can examine a picture of the countries and country associations trying to catch up with the Generative AI landscape, which is developing very rapidly with its various phases until January 2023, from the image below. [2]
European Union
EU AI Act: The first regulation on artificial intelligence around the world. As a pioneer of this regulations the most comprehensive and detailed version of studies has been done by European Union.[3][4]
EU AI Act initiative describes that different level of risks.
Unacceptable risk:
Unacceptable risk AI systems are systems considered a threat to people and will be banned. They include:
High risk:
AI systems that negatively affect safety or fundamental rights will be considered high risk and will be divided into two categories:
Generative AI:
Generative AI, like ChatGPT, would have to comply with transparency requirements:
Limited risk:
Limited risk AI systems should comply with minimal transparency requirements that would allow users to make informed decisions. After interacting with the applications, the user can then decide whether they want to continue using it. Users should be made aware when they are interacting with AI. This includes AI systems that generate or manipulate image, audio or video content, for example deepfakes.
United States
National AI Initiative Act (U.S. AI Act):
The National AI Initiative Act (U.S. AI Act) ?was enacted in January 2021. It was established to provide “an overarching framework to strengthen and coordinate AI research, development, demonstration, and education activities across all U.S. Departments and Agencies.”
The NIST AI Risk Management Framework (AI RMF):
The NIST AI Risk Management Framework (AI RMF) ?is designed to improve the ability to incorporate trustworthiness considerations into the design, development, usage and evaluation of AI products, services and systems.
Local Law 144 (the AI Law):
Local Law 144 ?is the first law in the United States to address the use of AI and other automated technology in the hiring process. Local Law 144 would require businesses to conduct bias audits on automated employment decision tools, including those that use artificial intelligence and related technology, and to publish specific notices about such tools to employees or job candidates in the city.
The California Privacy Rights Act (CPRA):
The CPRA, which became effective on January 1, 2023, directly addresses automated decision-making. Under?the Act , consumers have the right to understand (and opt out of) automated decision-making technologies, which include profiling consumers based on their “work performance, economic status, health, personal preferences, interests, reliability, behavior, location or movements.”
领英推荐
Canada:
AI regulations entered a new era following the Canadian Government’s announcement of a digital charter as part of a bigger revamp of the country’s data privacy landscape. Part three of?Bill C-27 , the Digital Charter Implementation Act, 2022, seeks to create the Artificial Intelligence and Data Act (AIDA), which would be Canada’s first AI legislation. Let’s take a closer look at it.
Artificial Intelligence and Data Act (AIDA):
In general, AIDA and the EU AI Act are both focused on limiting the risks of bias and harm caused by AI while attempting to strike a balance with the need to encourage technical innovation. Both?AIDA and the EU AI Act ?define “artificial intelligence” in a technology-neutral manner, so as to be “future-proof” and to keep up with breakthroughs in AI.
United Kingdom:
There is more to do to address the complex challenges that the emerging technologies present. In its?National AI Strategy , drafted in 2022, the government committed to developing a pro-innovation national position on governing and regulating AI.
Instead of delegating responsibility for AI governance to a single regulatory body, as the EU is doing through its AI Act, the UK government’s proposals will allow different regulators to take a tailored approach to the use of AI to boost productivity and growth simultaneously.
3. Risks and Ethical Considerations
According to the research of Salesforce research, many senior IT leaders see generative AI as a ‘game changer’ and a tool to better serve customers. The majority of senior IT leaders (57%) believe generative AI is a ‘game changer.’ They believe the technology has the potential to help them better serve their customers, take advantage of data, and operate more efficiently. This outlook is echoed even among the skeptics — 80% of those who say the technology is ‘over-hyped’ agree that generative AI will help them better serve their customers.?[5]
Ethical, operational concerns draw skepticism and additionally security risks, integration, and siloed data are top barriers to generative AI implementation.
Businesses aren’t yet prepared for successful implementation: 65% of senior IT leaders can’t justify the implementation of generative AI at the moment. Surveyed leaders report major barriers to using generative AI successfully within their organization, and security barriers are particularly top of mind among those currently using the technology.
There are some key guidelines that prominent companies like Salesforce using to guide the development of trusted generative AI [6]:
Generative AI Platforms and tools must provide verifiable results that balance accuracy, precision, and recall in the models. The results should be reliable.
In order not to create any bias within models or responses taken as an output from Generative AI tools. Explainability, robustness and privacy needs to be taken into consideration by all users.
We need to respect data provenance and ensure that we have consent to use data (e.g., open-source, user-provided). We must also be transparent that an AI has created content when it is autonomously delivered (e.g., chatbot response to a consumer,?use of watermarks )
To get better from our daily basis repetitive jobs, we should learn how to use these kinds of technologies. Additionally, these technologies like cars which disrupts carts and horses more than 100 years ago.
The effects of carbon emissions is tremendous and harms our environment and world. Creating complicated and enormous models does not mean that we have always a better solution for our problem. The profiles like data scientist, data analyst, data engineer or anyone who is taking care of creating models via Generative AI platforms must use less resources.
4. Opportunities
We can start with an example of how to effect Generative AI platforms to all over the businesses. It is a great example of McKinsey consultants below example which shows how is the potential disruptive effect of this technology [7]::
McKinsey Consultant Prompt:
Write the opening paragraph for an article about how transformative generative AI will be for business, in the style of McKinsey & Company.
ChatGPT Response:
The rise of generative AI has the potential to be a major game-changer for businesses. This technology, which allows for the creation of original content by learning from existing data, has the power to revolutionize industries and transform the way companies operate. By enabling the automation of many tasks that were previously done by humans, generative AI has the potential to increase efficiency and productivity, reduce costs, and open up new opportunities for growth. As such, businesses that are able to effectively leverage the technology are likely to gain a significant competitive advantage.
Above example is not only impressive but also mimicking the specific company or a specific person. This is something unusual.
Generative AI has the potential to influence a wide range of business functions, but its impact is particularly pronounced in certain areas when assessed in terms of the technology's effect relative to the functional cost (as illustrated in Exhibit 3). Through an extensive analysis of 16 distinct business functions, our study has pinpointed just four specific areas where Generative AI's influence is most substantial. These areas include customer operations, where AI can enhance customer service and engagement; marketing and sales, where it can personalize campaigns and improve targeting; software engineering, where it can automate coding and testing processes; and research and development, where it can accelerate innovation and product development. Collectively, these four functions could represent approximately 75 percent of the total annual value derived from the application of generative AI use cases. This finding underscores the significant role that Generative AI can play in transforming key aspects of business operations, leading to increased efficiency and potentially substantial cost savings.
And last but not least figure that I have already use in my company’s client presentations, and according to McKinsey’s below exhibit all of the sectors and nearly all of the business functions will be affected by Generative AI technologies [8]. It is clearly seen that the total industry revenues and the impact level of Generative AI technologies will be add more layer and surplus value to its beneficiaries.
5. Conclusion
In this graduation project, where we examine Generative AI technology from various perspectives, we recognize that it will cause significant variations from country to country, industry to industry, company to company, and even from individual to individual who will be its users. Perhaps a metaphor would best describe this new technology, as it will lead to a better understanding. In the past, disruptive technologies have completely transformed the existing conditions, influencing the landscape and the relevant ecosystem of the day, and ultimately enabling us to evolve into a more efficient state.
Inspired by Clayton Christensen's book "Disruptive Innovation," we are in an era where we are welcoming a brand-new technology that, although initially emerging slowly and not carrying significant opportunities to change current technology and the world, has, in a very short time, transformed industries, companies, people, and consequently humanity from start to finish. The S-curve mentioned illustrates this gradual yet profound transformation, marking a pivotal moment in technological advancement [9].
With this awareness, we can have the courage to be pioneers of change, not fearing the nightmares that innovations may bring, but embracing the immense power they offer. Whether personally, professionally, or in terms of feasibility, we now possess things we never had before, and the opportunities presented to us far outweigh the inherent risks. We stand on the brink of a new era, where the vast potential of change is at our feet, ready to be harnessed.
Let's conclude with my always-used motto: #GoFurtherforBetter. This encapsulates the spirit of embracing change, pushing boundaries, and striving for excellence, all of which are central to the exploration and responsible implementation of Generative AI and other transformative technologies. It's a call to action, urging us to look beyond the present and to innovate for a better future.
6. References
Senior Partner @ BTS&Partners; Part-time Lecturer @ ?stanbul Bilgi University - Sabanc? University
1 年Sevgili Mehmet. Bu harika ?al??ma i?in tekrardan seni tebrik ediyorum. Konuyla ilgilenen herkese ufuk tutacak ?ok de?erli bir eser olmu?. Nazik s?zlerin i?in de ayr?ca ?ok te?ekkür ederim. Kariyerinde ba?ar?lar diliyorum.