Safety in Artificial Intelligence: Challenges and Opportunities for the U.S. National Labs and Beyond
This report discusses the importance of the critical and underexplored topic of artificial intelligence (AI) safety, as highlighted during the “Strategy Alignment on AI Safety” workshop convened at Lawrence Livermore National Laboratory (LLNL) in April 2024. Through a summary of keynote talks, panel discussions, and breakout sessions, world-leading AI safety experts from academic, industry, national labs, and government agencies clearly agree on the need for and importance of large-scale investments for research and capabilities in AI safety. With the field innovating at unprecedented rates, there is increasing urgency to develop novel evaluation methodologies that allow full considerations of risks/threats of AI technologies in different domains. Quantitative metrics and effective methodologies that can evaluate and audit the “safeness” of how a given AI technology is trained, deployed, or regulated are, at best, nascent for certain scenarios or, more commonly, nonexistent. This maturation gap presents the possibility of serious threats to national security, and further inaction may have serious consequences. Additionally, the gap between the public’s and research community’s perceptions of AI risks/rewards is significant. While numerous voices from the AI community have expressed concern that the risks could be so high that future AI systems could inflict extinction-level damage to humanity if deployed incorrectly, the public largely is aware only of risk in low-impact scenarios. This discrepancy highlights the crucial need for researchers to articulate to governmental bodies what, why, and when various AI risks matter as part of motivating funding requests. Thus, the call to action for this community is to pursue AI safety as a “Big Science” project on a scale comparable to the Manhattan Project. High risks and high payoffs are on the table, but safe AI is a fast-moving target, and large-scale investments are needed to guide development of this technology in a responsible way. We highlight the need for a multilayered solution combining the development of new methods and algorithmic approaches to mitigate threats with an active participation of the government(s) in setting high industry standards and regulations based on state-of-the-art technology. The U.S. Department of Energy (DOE) national laboratories have served as leading institutions for scientific innovation in the U.S. for more than 70 years. Drawing on their expertise in the AI community and their history of safeguarding critical and sensitive information, and as we look to the future, national labs are the best choice for evaluating and safeguarding AI technologies.