OpenAI's ChatGPT and the Prospect of Limitless Information

This Feature appears in vol. 75, no. 1, "Insecurities: The 75th Anniversary Issue, 1947-2022" (Fall/Winter 2022).

A Conversation with ChatGPT

ChatGPT is an artificial intelligence chatbot developed by OpenAI, an artificial intelligence research laboratory consisting of the nonprofit OpenAI Foundation and the for-profit OpenAI Limited Partnership. ChatGPT launched on November 23, 2022 and is built on top of OpenAI’s GPT-3 family of large language models (LLM). It works by predicting the next most likely word in a sentence based on a prompt and previous chat history. While chatbots have existed for some time, the arrival of ChatGPT has been heralded as a significant watershed in the development of AI applications and has become among the fastest-adopted technologies of the Internet era.

There is significant disagreement over both the usefulness and transformative nature of LLMs. It was quickly noted that because this LLM was not connected to the Internet, it could not fact-check itself, leading ChatGPT-supported applications to “hallucinate”—generate plausible-sounding yet factually inaccurate information in response to verifiable questions. This led some observers to suspect that AI is not about to displace the millions of knowledge workers who every day generate text and visual information—at least not until connectivity is enabled. Additionally, there are very real concerns of bias incorporated into its coding and the likelihood that the technology will merely reflect humanity’s own flaws without transcending its limitations.

Yet in the longer term, legitimate criticisms have been levelled at ChatGPT and other LLMs, including generative AI tools more broadly, for their ability to cheaply mass-produce content of dubious quality. In a world increasingly bloated by misinformation, the era of limitless, inaccurate content is very close at hand. Such a reality could significantly alter the information ecosystems in which much of humanity currently finds itself. Less apocalyptically, there are also discussions around the use-value of these tools and their capacity to complement, not replace, existing knowledge work. The ability to instantaneously write a legal document or briefing memo, to automate tasks such as email and coding—to draft an article for submission in the Journal—could radically alter productivity. It is still early, though the promise is great, if uncertain. 

In many respects, AI is too “live” a topic to address with much rigor or seriousness in the pages of the Journal; that analysis will come in a later edition. But here we present in our 150th issue an opportunity to glimpse the very early days of what could turn out to be a revolution in creation and even consciousness—or just another ripple amidst the long waves of human technological progress.

The following transcript was generated with OpenAI’s ChatGPT free online chatbot in March 2023, prior to the release of GPT-4.[i] It has not been edited in any way. JIA questions are prompts entered into ChatGPT, word for word, while the ChatGPT responses are the output generated within OpenAI’s ChatGPT chat interface.

Journal of International Affairs (JIA): I am editing a peer-reviewed academic journal issue entitled “Insecurities.” Authors have submitted pieces on politics, climate, technology, energy, and other topics. Many people and institutions around the world feel insecure today, despite unprecedented wealth and safety compared with past eras. Generate a response to the question: “Why is the world in 2023 insecure?”

ChatGPT: There are several factors that contribute to the sense of insecurity that many people and institutions around the world are experiencing in 2023.

Firstly, political instability and the rise of populism have created a sense of uncertainty and unpredictability. Many countries are experiencing political turmoil, which is fueled by economic inequality, cultural and social divides, and the perception that governments are not representing the interests of the people. This has led to a growing mistrust in institutions and a sense of vulnerability among citizens.

Secondly, the ongoing climate crisis has led to a growing sense of insecurity as people grapple with the catastrophic consequences of environmental degradation. Extreme weather events, rising sea levels, and the loss of biodiversity are just a few of the ways that the climate crisis is affecting people’s lives and livelihoods.

Thirdly, rapid technological advancements and the rise of automation are creating economic disruption and job displacement, leaving many people feeling insecure about their future prospects. The rapid pace of technological change is also creating new ethical and social dilemmas that are difficult to navigate and regulate.

Finally, geopolitical tensions and the proliferation of nuclear weapons continue to pose a threat to global security. The ongoing conflicts in the Middle East, the resurgence of authoritarianism in some parts of the world, and the increasing militarization of space are just a few of the challenges that are contributing to a sense of global insecurity.

Overall, the world in 2023 is facing a complex set of challenges that are interconnected and multifaceted. Addressing these challenges will require a coordinated and collaborative effort by governments, civil society, and the private sector to ensure that people feel secure and that institutions are able to respond effectively to the challenges of our time.

JIA: Many in creative industries are concerned about the rise of artificial intelligence systems that can mimic human creativity. Such AI models can generate images with extreme likeness to human-made art, while large language models can generate long strings of text with plausible-sounding truthfulness and sufficient grammatical and syntactical correctness. Just how worried should people be about the rise of these AI tools: should they feel insecure?

ChatGPT: The rise of artificial intelligence in the creative industries certainly raises some valid concerns, but it is important to approach the issue with a balanced perspective.

On the one hand, AI has the potential to significantly enhance and democratize creativity by providing new tools and approaches for artists, writers, and musicians. For example, AI algorithms can analyze vast amounts of data to identify patterns and generate novel ideas, which can inspire human creativity and help artists overcome creative blocks.

On the other hand, there are concerns that AI-generated content may lack the depth, complexity, and emotional resonance that are characteristic of human creativity. Moreover, there is a risk that AI-generated content could devalue human creative labor, leading to job displacement and a loss of cultural diversity.

Despite these concerns, it is important to recognize that AI-generated content is still in its early stages and is unlikely to replace human creativity entirely. While AI systems can generate plausible-looking art, music, and writing, they still lack the subjective experience and emotional depth that are characteristic of human creativity.

In this sense, people in creative industries should not feel insecure about the rise of AI tools, but rather should embrace the opportunities that they provide while also recognizing their limitations. AI can be seen as a tool that can complement human creativity, rather than a replacement for it.

Ultimately, it is up to individuals in creative industries to adapt and evolve their skills and practices in response to the changing landscape of AI and technology. By embracing new tools and approaches, and by continuing to develop their own unique perspectives and voices, they can remain relevant and resilient in the face of technological disruption.

JIA: Previously, you mentioned some threats to human security around the world: political instability and the rise of populism, the ongoing climate crisis, rapid technological advancements and the rise of automation, and the geopolitical tensions and the proliferation of nuclear weapons. Which of these issue areas—or another that hasn’t yet been discussed—is the gravest threat to security in the short- to medium-term, or within the next five years?

ChatGPT: It is difficult to pinpoint one specific issue area as the gravest threat to security in the short- to medium-term, as all of the issues mentioned have the potential to significantly impact global security. However, I would argue that the ongoing climate crisis is likely to be one of the most pressing and immediate threats to human security in the next five years.

The effects of climate change are already being felt around the world, from extreme weather events such as wildfires, floods, and droughts, to rising sea levels and the loss of biodiversity. These impacts are likely to become more severe and widespread in the coming years, which could lead to displacement, conflict, and social unrest.

In addition, the climate crisis is interconnected with other security challenges, such as food and water insecurity, economic instability, and political instability. For example, climate change can lead to crop failures and food shortages, which can exacerbate existing inequalities and tensions within societies.

Moreover, the impacts of the climate crisis are likely to be felt most acutely by vulnerable and marginalized populations, including low-income communities, indigenous peoples, and those living in areas prone to natural disasters. These populations may lack the resources and support necessary to adapt to the impacts of climate change, which could further exacerbate existing inequalities and increase the risk of conflict.

Therefore, while all of the issues mentioned are significant threats to human security, the climate crisis is likely to be one of the most pressing and immediate concerns in the next five years. It is crucial that governments, civil society, and the private sector work together to address the root causes of climate change and to support vulnerable communities in adapting to its impacts.

JIA: It is difficult to predict the future but still a worthy exercise to think through the interrelationships across topics, and I’m not surprised you arrived at climate as likely posing the gravest threat. Another topic I’d like to discuss is misinformation. Over the last 15 years, with the proliferation of algorithmic social media platforms and mobile internet around the world, people across the globe are simultaneously becoming more informed but may not be as well informed. However, there is also evidence that people may be better informed than in the past, which in turn is driving partisanship. How should we think about the spread of misinformation and its destabilizing impact on politics, economics, and societies?

ChatGPT: The spread of misinformation is indeed a significant challenge in the digital age, and it can have serious consequences for politics, economics, and societies. Misinformation can fuel polarization and distrust, erode public trust in institutions and experts, and sow confusion and division.

One of the key factors driving the spread of misinformation is the algorithmic nature of social media platforms, which can prioritize content that is sensational, emotional, or controversial over content that is accurate and informative. This can create echo chambers where people are exposed only to content that reinforces their existing beliefs, and can make it difficult for people to distinguish between accurate and inaccurate information.

To address the spread of misinformation, it is important to adopt a multi-pronged approach that involves a range of stakeholders, including governments, civil society organizations, technology companies, and individuals.

One important step is to improve media literacy and critical thinking skills among the general public, so that people are better equipped to distinguish between accurate and inaccurate information. This can involve education and awareness-raising campaigns, as well as efforts to promote fact-checking and verification tools.

Another important step is to strengthen regulation and oversight of social media platforms, to ensure that they are not spreading harmful or misleading content. This could involve measures such as labeling or removing false or misleading content, improving transparency around how content is curated and promoted, and limiting the spread of content that is known to be false or misleading.

Finally, it is important to recognize that addressing the spread of misinformation will require sustained and coordinated efforts over the long term. It will require ongoing investment in research, education, and technology, as well as collaboration and dialogue among different stakeholders.

Overall, addressing the spread of misinformation is a complex and multifaceted challenge, but it is crucial for maintaining trust, stability, and democracy in the digital age.

JIA: That is a thoughtful response, yet the concern these days is that the democratization of AI technology is a double-edged sword: on the one hand, more people will have access to its massive creative and productive potential; on the other hand, more people will have access to its ability to generate content that may explicitly be disinformation. What happens when the price of information—however factual—effectively drops to zero and anyone has the opportunity to manufacture lies?

ChatGPT: You raise an important point about the potential for AI technology to be used for disinformation and propaganda, particularly as the cost of generating and disseminating information continues to decrease. This is indeed a significant concern, as it has the potential to undermine public trust in information and institutions, and to further polarize societies.

One potential solution to this challenge is to focus on developing and promoting trustworthy and reliable sources of information. This could involve efforts to improve the transparency and accountability of institutions and media outlets, as well as investing in fact-checking and verification tools. By promoting a culture of transparency and accuracy, we can help to build public trust in information and reduce the impact of disinformation.

Another potential solution is to promote media literacy and critical thinking skills, so that people are better equipped to recognize and avoid disinformation. This could involve education campaigns and initiatives aimed at promoting critical thinking, as well as the development of tools and resources to help people verify the accuracy of information.

Moreover, it is important for governments and technology companies to recognize the potential risks of AI-generated disinformation and to take proactive steps to address these risks. This could involve developing policies and regulations to limit the spread of disinformation, as well as investing in research and development to improve the ability to detect and counter disinformation.

Overall, the democratization of AI technology is a double-edged sword, and it will be important to remain vigilant and proactive in addressing the potential risks and challenges associated with its use. By promoting transparency, accuracy, and critical thinking, we can help to mitigate the risks of disinformation and ensure that AI technology is used to promote the public good.

JIA: One final question: foreign policy is a notoriously unimportant issue area in American politics, at least among most voters; additionally, few people have the opportunity to travel or experience another part of the world, despite the globalized nature of the modern economy, climate change, and information ecosystems. What books, new sources, or publications should someone read if they wish to become better informed about international affairs? Who are the important voices in this area thinking and writing today?

ChatGPT: There are many excellent resources available for people who wish to become better informed about international affairs. Here are a few suggestions:

1. The Economist: This weekly news magazine provides in-depth coverage of international news, politics, economics, and culture. It is known for its high-quality journalism, insightful analysis, and global perspective.

2. Foreign Affairs: This bimonthly publication focuses exclusively on international affairs and foreign policy. It features articles by leading experts and policymakers on a wide range of topics, from security and diplomacy to trade and development.

3. Council on Foreign Relations: This nonpartisan think tank is dedicated to providing independent analysis and policy recommendations on global issues. It offers a wealth of resources on its website, including articles, reports, podcasts, and videos.

4. The New York Times’ International section: The New York Times is one of the world’s leading newspapers, and its International section provides comprehensive coverage of global news and events. It features articles by some of the world’s top journalists, as well as analysis and opinion pieces.

5. Books: There are many excellent books on international affairs, written by leading experts and scholars. Some recent examples include “The World: A Brief Introduction” by Richard Haass, “Destined for War: Can America and China Escape Thucydides’s Trap?” by Graham Allison, and “The New Map: Energy, Climate, and the Clash of Nations” by Daniel Yergin.

6. Podcasts: Podcasts are a great way to stay informed on the go. Some popular options for international affairs include “Foreign Policy Playlist” by Foreign Policy magazine, “Worldly” by Vox, and “The Global Politico” by Politico.

Overall, becoming better informed about international affairs requires a commitment to learning and staying up to date on global events. By regularly reading high-quality news sources, books, and other resources, you can develop a deeper understanding of the world and the challenges we face.