AI Helped Write This Newsletter
2-2-2: A Special Edition
Hello, I’m Ylli Bajraktari, CEO of the Special Competitive Studies Project (SCSP). Welcome to the 2-2-2. The 2-2-2 brings you monthly analysis on topics at the intersection of technology and national security.
In this month’s edition of the 2-2-2, SCSP previews its fall agenda. We offer snapshots from our initial report, Mid-Decade Challenges to National Competitiveness, and details about our September 16th Global Emerging Technology Summit including newly announced speakers.
A Sneak Peek of SCSP’s Initial Report
In October 2021, we launched the Special Competitive Studies Project (SCSP) to make recommendations to strengthen America’s long term competitiveness for a future where artificial intelligence (AI) and other emerging technologies reshape our national security, economy, and society. In the coming weeks, SCSP will share its first publication, Mid-Decade Challenges to National Competitiveness. The purpose of the report is to build a conceptual framework and elevate issues that merit the nation’s attention to ensure we improve the U.S. position in the international competition by 2025 and identify those technology areas where we must act by 2030 to retain our advantage. It is our initial why and what that outlines our logic for action and an agenda for the future.
SCSP builds on the work of the congressionally-mandated National Security Commission on Artificial Intelligence (NSCAI). NSCAI succeeded foremost in informing the country about the multifaceted implications of AI and associated technologies for national security. It put technology at the center of the rivalry between the United States and the People’s Republic of China (PRC), made the case for the United States to organize for competition, and provided blueprints for action. We knew, however, that NSCAI left unfinished business and was limited to AI.
Additionally, SCSP is inspired by the Rockefeller Special Studies Project (SSP), launched in 1956 by Nelson Rockefeller and led by Henry Kissinger, which offers a nearly perfect model for the level of ambition befitting today’s challenges. In the midst of the Cold War and facing roiling domestic and international conditions, the SSP brought together some of the nation’s leading thinkers to study the major problems and opportunities confronting the United States and to chart a path to revitalize American society, restore a strong bipartisan national security strategy, and ensure American leadership. Major international events, including the 1956 Soviet invasion of Hungary and the 1957 Soviet launch of Sputnik, made evident the need for original, clear-eyed thinking if the United States was to maintain its global position and fight for freedom through democracy.
Today, as then, the nation needs a holistic and non-partisan review — this time centered on the range of emerging technologies that are reshaping our security, economy, society, and daily lives. And we must do it faster than before.
The Process
SCSP is publicly minded and staunchly nonpartisan in our belief that technology, competition, and organization remain enduring themes for national focus. Our first task was to bring together a diverse group from the United States and our closest allies and partners to frame the challenges and outline an agenda. We are organized around six panels on technology platforms, the economy, society, foreign policy, defense, and intelligence. Each panel brings a unique perspective to the mid-decade challenges and works with leading advisors from across the nation to offer innovative solutions. These panels will publish their own detailed reports over the life of the project.
The Challenge
SCSP believes that strategic competition between the United States and the PRC is the defining feature of world politics today. The epicenter of the competition is the quest for leadership in a constellation of emerging technologies that will underpin a thriving society, growing economy, and sharper instruments of national power. At stake is the future of free societies, open markets, democratic government, and a world order rooted in freedom not coercion.
Competition with China provides an important lens for viewing multiple relevant trends impacting our country and the world. The PRC is the United States’ chief ideological opponent, largest economic competitor, most capable military challenger, and most powerful geopolitical rival for the foreseeable future. Moreover, it is the closest technological peer we face, and is intent on supplanting the United States as the world’s greatest innovation hub. The technology competition brings together ideological, economic, military, and geopolitical influence into a systemic competition over the future of the world order.
In particular, the 2025-2030 window represents a critical period for this contest, when tech trends and strategic competition will come to a head. Technology itself will accelerate over this period. Some critical technologies will reach maturity and become available for general use. Others may require additional time, but states will need to devote consistent research and development resources to keep pace at the technological frontier. If we want to alter the trajectory of that competition, we must organize now.
SCSP’s touchstone question is this: what policy moves and forms of organization do we need as a nation to position the United States to win that competition between now and 2030?
In our upcoming report, Mid-Decade Challenges to National Competitiveness, SCSP delves in-depth to provide our assessment of the competition and a forward looking agenda to drive action. It reflects our conviction that this decade above all is the crucial window for action. We must once again call upon our nation’s immense talents to chart a path towards a safer, healthier, more inclusive, more united, and thereby more competitive, nation. To succeed, we need to answer six questions:
If we want to avoid being “5G’d” again, how can we unlock and fuse the expertise, will, and resources that exist throughout American society to build national advantage in critical technologies?
If tech leadership must be built on strong techno-economic foundations, how do we ensure that the United States remains the world’s most dynamic, competitive, and resilient economy in the 2020s?
If we want our citizens to embrace the promise of emerging technologies, how can we develop a technology governance regime that protects the rights of individuals and still unlocks the power of innovation to improve society?
If we want to bring allies and partners along, how can we preserve an open international order — underpinned by respect for sovereignty and trusted digital infrastructure — that meets the aspirations of the widest number of people and is still guided by democratic values?
In the face of military rivals employing new technologies and operational concepts to gain advantage, how can the United States ensure a favorable global balance of military power and uphold its defense commitments in the event of a conflict?
If we are now in a techno-economic competition, how can the United States win the race for actionable insights in an information-rich world?
Together, these questions frame an agenda for strengthening our national competitiveness.
What do AI models have to say about tech competition?
Even as SCSP works to answer these six questions, we thought we would see what artificial intelligence (AI) says about the overarching strategic challenge.
AI is undoubtedly one of the main technologies reshaping our world, and Large Language Models (LLMs) reflect both the promise and peril of AI and other emerging technologies. The release of OpenAI’s GPT-3 in June 2020 catalyzed a rapidly growing ecosystem for the production and use of LLMs, primarily in the United States and China, but increasingly also in the rest of the world. While LLMs have made great strides even since the release of GPT-3—both in how they are engineered and the quality of the outputs they produce—they are not oracles that make independent judgments, and are bound by the quality of the data upon which they were trained. Their use will always carry associated risks and must be carefully considered by humans. Nonetheless, LLMs will continue to proliferate as the nations and companies at the forefront continue to advance the state of the art.
Source: SCSP Compilation of External Sources
To illustrate the state of LLMs today, we wanted to know what they had to say about the evolving techno-economic competition between the U.S. and China. So we asked three LLMs to weigh in on some of SCSP’s key framing questions. The italicized responses below were generated through three LLMs — OpenAI’s GPT-3, Hugging Face’s BLOOM, and a model developed by Anthropic. These LLMs have real limitations today. Nonetheless, the following responses show how far this technology has come, and reveal the shape of what will come.
1) What are the most important factors in the U.S.-China techno-economic competition today?
“Overall the most important factors in the U.S.-China techno-economic competition today are China’s economic transition, China’s increasing focus on its own innovation and science, the U.S.’ own transition toward more balanced innovation across its economy, and the U.S.’ growing need for high-tech equipment and systems. The U.S. remains an economic superpower and is the leading technology and innovation force in the world today. China is still far behind the U.S. in that regard and China is becoming a more significant competitor as it moves to fulfill its promise as the world’s leading country and power.” — BLOOM1
2) Which technologies will most significantly transform the economy, society, and national security between now and 2030?
“Between now and 2030, several technologies will likely most significantly transform the economy, society, and national security. These include artificial intelligence, robotics and automation, biotechnology and biomedicine, renewable energy, quantum computing, the Internet of Things, fifth-generation wireless networks or 5G, materials science, and autonomous vehicles. These technologies will drive dramatic gains in productivity and economic growth, revolutionize manufacturing and transportation, enhance human capabilities, and reshape the global balance of economic and military power.” — Anthropic2
3) How should a nation decide which technologies will be future geopolitical battlegrounds?
“The United States has been a world leader in technology for decades, but the rise of China and other nations has challenged that dominance. As the world becomes more interconnected, it is important for the United States to identify which technologies will be future geopolitical battlegrounds.
There are a number of factors that should be considered when making this determination. First, it is important to identify which technologies are critical to the United States’ economic and national security. These are the technologies that the United States must maintain a competitive edge in order to protect its interests.
Second, it is important to consider which technologies are becoming increasingly important globally. These are the technologies that other nations are investing in and developing, and which could give them a competitive advantage over the United States.
Finally, it is important to consider which technologies are emerging and have the potential to be game-changers. These are the technologies that could upend the status quo and create new opportunities for the United States. The United States must be proactive in identifying which technologies will be future geopolitical battlegrounds. By doing so, it can ensure that it remains a world leader in these critical areas.” — GPT-33
The LLMs above do a decent job of characterizing the international competition, even if they lack the nuance and agility of a human analyst. In a couple of years, they will likely be exponentially better. As these AI models become ever more capable, nations will undoubtedly seek to harness them for economic, military, and national security advantage. Governments will also be challenged to decide if and how these models should be regulated to ensure they are not employed for nefarious purposes. With China determined to surpass the United States in AI leadership, democracies must choose whether to shape and constrain these models in line with our values, or cede this cornerstone of the international competition to a rival.
Yet LLMs only touch the tip of the iceberg of the complex dynamics of a global techno-economic competition. Moreover, LLMs reflect only one segment of the AI sector, which is but one of multiple emerging tech battlegrounds. For deeper dives into these questions, key technology areas, and our proposed agenda for action, we hope you follow along on Twitter and through the SCSP 2-2-2 Newsletter for future updates!
Join us in September!
Registration is open for the Global Emerging Technology Summit! We hope to see you — either in-person in Washington, DC, or online — on September 16 to launch our report and hear the insights of leading innovators, entrepreneurs, and policymakers. Alongside a series of cutting-edge tech demos, the day’s sessions will shed further light on geopolitics, democracy, and our tech-enabled future. We are excited to announce speakers including Jake Sullivan, Eva Kaili, and Sir Alex Younger. Visit us on Twitter or LinkedIn for speaker announcements as we get closer to the event!
SCSP generated this text with Bloom-2b5, an LLM developed by Huggingface. SCSP takes ultimate responsibility for the content of this publication.