OPENAI'S CHATGPT AND THE PROSPECT OF LIMITLESS INFORMATION.

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 transcnding 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...