AI ONE ON ONE. Episode 8: In the Hot Seat: ChatGPT Speaks Out on Privacy and Safety Concerns

Aleksandra Przegalinska?and?Tamilla Triantoro?started a blog?“AI One on One” to discuss the advantages and limitations of current AI systems and explore the possibilities of using AI for good.

AI ONE ON ONE. Episode 8: In the Hot Seat: ChatGPT Speaks Out on Privacy and Safety Concerns

As generative AI technologies become more integrated into our daily routines, concerns have been raised regarding its impact on society. In this episode, we will examine recent events related to AI. These include complaints against OpenAI's ChatGPT chatbot, calls for a halt in the development of advanced AI systems, investigations by data protection agencies, and the ongoing debate around the regulation of AI.?

The Center for AI and Digital Policy (CAIDP) submitted a?formal complaint?to the Federal Trade Commission (FTC) about GPT-4 product developed by OpenAI, urging the FTC to investigate the matter and calling for transparency and empirically sound data and models. The CAIDP expressed concerns about disinformation, influence operations, proliferation of weapons, and cybersecurity risks.?

More than 1,000 technology leaders have initially signed an?open letter?and called for a halt in the development of advanced AI systems due to the risks to humanity. Thousands of concerned individuals followed. The letter highlights the concerns that powerful AI tools could be unpredictable and uncontrollable, emphasizing that progress should only be made once the technology's positive effects are guaranteed and risks managed. The list of signatories includes prominent figures such as Elon Musk, Steve Wozniak, Yuval Noah Harari, Andrew Yang, and others.

UNESCO has responded to the open letter by tech leaders by?calling on all countries?to immediately implement its Recommendation on the Ethics of Artificial Intelligence. This global framework was adopted by 193 Member States and aims to ensure responsible AI development.?

OpenAI's ChatGPT chatbot is?facing restrictions in Italy?after potentially violating data privacy laws. The Italian data protection authority has imposed a temporary ban on the processing of Italian users' data by OpenAI and has launched an inquiry into the matter. The company has been prohibited from continuing to process data until the issue is resolved.

Europol warns?that tools such as ChatGPT can be used for fraudulent activities, cybercrime, social engineering, and dissemination of disinformation. They say that although large language models may enable individuals with limited technical know-how to carry out unlawful activities, they could also assist law enforcement agencies in investigating and anticipating crimes.?

After hours of heated debate and endless cups of coffee, we decided to go straight to the source and ask ChatGPT what it thinks about recent events and the future of human-AI interaction. Here is what ChatGPT had to say:

Human:?what is your take on all these recent events?

ChatGPT: As an AI language model, I don't have personal feelings or opinions. However, I can say that these recent events highlight the need for careful consideration and regulation of AI technologies to ensure their safe and ethical development and deployment. While AI has the potential to bring numerous benefits to society, it also poses significant risks if left unchecked. Therefore, it is essential for governments, organizations, and individuals to work together to ensure that AI is developed and used responsibly, with appropriate safeguards in place to protect public safety, privacy, and security.

Human:?Should humans be scared of AI?

ChatGPT:?Humans do not need to be scared of AI as long as it is developed and used responsibly and ethically. However, it is important to remember that AI is just a tool developed by humans, and it operates based on algorithms and data that people create. The behavior of AI systems is determined by the data it is trained on and the goals it is given. Therefore, it is important that humans are involved in the development and deployment of AI to ensure that it is aligned with human values and priorities.

Human:?Do you think ChatGPT should be banned?

ChatGPT:?As an AI language model, I don't have personal opinions or desires. Whether or not ChatGPT should be banned is a decision that depends on various factors and considerations, such as how it is being used, the impact it has on individuals and society, and the ethical and legal implications of its use. Ultimately, it is up to human decision-makers to determine whether or not to restrict the use of ChatGPT or any other technology.

Human:?What do you think of Elon Musk and the Future of Life Institute open letter to postpone the work on generative AI?

ChatGPT:?Elon Musk and the Future of Life Institute have written open letters calling for the postponement of research on generative AI. They have expressed concerns about the potential risks associated with the development of advanced AI systems, such as the risk of AI systems becoming too powerful and difficult to control. They have also suggested that there should be more focus on the development of safety measures and ethical guidelines for AI. The debate around the risks and benefits of AI research is complex and involves a wide range of stakeholders. While some experts share these concerns and believe that more attention should be given to the safety and ethical implications of AI, others argue that the potential benefits of AI development outweigh the risks and that responsible development can mitigate the risks. Ultimately, the decision about whether to postpone research on generative AI or not will depend on a variety of factors, including the views of stakeholders, the potential risks and benefits of AI, and the ethical and legal implications of AI development.

The current moment is marked by significant turbulence in the development of AI. Just a couple of weeks ago, the excitement about generative AI was at an all-time high, but now the dark side of AI is being brought to light. Ultimately, it is up to humans to decide how AI and chatbots like ChatGPT should be governed. As with any powerful technology, there are risks and potential benefits to consider to ensure that AI is used for the greater good. This involves creating ethical frameworks and regulations that provide safeguards against potential harms, while also fostering innovation and the development of beneficial AI applications.

About the authors:

Aleksandra Przegalinska?-?Associate Professor and Vice-President of Kozminski University, responsible for International Relations and ESR as well as Senior Research Associate at the Harvard Labour and Worklife Program.?Aleksandra is the head of the?Human-Machine Interaction Research Center?at Kozminski University, and the Leader of the AI in Management Program. Until recently, she conducted post-doctoral research at the Center for Collective Intelligence at the Massachusetts Institute of Technology in Boston. She graduated from The New School for Social Research in New York. She is the co-author of?Collaborative Society?(The MIT Press), published together with Dariusz Jemielniak.

Tamilla Triantoro?- Associate Professor at Quinnipiac University and the leader of the Masters in Business Analytics program. Tamilla is an author, speaker, and researcher in the fields of artificial intelligence, data analytics, user experience with technology, and the future of work. She received her PhD from the City University of New York where she researched online user behavior. Tamilla presents her research around the world, attempting to explain the complexity of today's digital world and to make it understandable and relevant.