Safety Cases: A Scalable Approach to Frontier AI Safety
It addresses the problem of ensuring safety in frontier AI for developers and regulators, but is incremental as it adapts an existing technique to a new domain.
The paper proposes using safety cases, a structured argumentation technique from other industries, to demonstrate the safety of frontier AI systems to stakeholders, and argues this approach can help fulfill safety commitments while identifying open research questions.
Safety cases - clear, assessable arguments for the safety of a system in a given context - are a widely-used technique across various industries for showing a decision-maker (e.g. boards, customers, third parties) that a system is safe. In this paper, we cover how and why frontier AI developers might also want to use safety cases. We then argue that writing and reviewing safety cases would substantially assist in the fulfilment of many of the Frontier AI Safety Commitments. Finally, we outline open research questions on the methodology, implementation, and technical details of safety cases.