Safety Cases: Justifying the Safety of Advanced AI Systems

Thomas Larsen, Director of Strategy at the Center for AI Policy, has coauthored a new research paper. It analyzes structured arguments that AI developers could make to demonstrate that their AI systems are safe. Here's the abstract:

As AI systems become more advanced, companies and regulators will make difficult decisions about whether it is safe to train and deploy them. To prepare for these decisions, we investigate how developers could make a 'safety case,' which is a structured rationale that AI systems are unlikely to cause a catastrophe. We propose a framework for organizing a safety case and discuss four categories of arguments to justify safety: total inability to cause a catastrophe, sufficiently strong control measures, trustworthiness despite capability to cause harm, and deference to credible AI advisors. We evaluate concrete examples of arguments in each category and outline how arguments could be combined to justify that AI systems are safe to deploy.

Read the full paper here.