Towards Frontier Safety Policies Plus
Matteo Pistillo

TL;DR
This paper proposes an evolved version of Frontier Safety Policies, called FSPs Plus, emphasizing standardized metrics for precursory capabilities and integrating AI safety cases for improved safety assurance in frontier AI development.
Contribution
It introduces FSPs Plus, a more detailed safety policy framework incorporating standardized metrics and safety case integration, to enhance safety governance in frontier AI.
Findings
FSPs Plus emphasizes precursory capabilities as safety metrics.
Proposes standardization of capability taxonomy.
Recommends integrating safety cases with policy updates.
Abstract
This paper examines the state of affairs on Frontier Safety Policies in light of capability progress and growing expectations held by government actors and AI safety researchers from these safety policies. It subsequently argues that FSPs should evolve to a more granular version, which this paper calls FSPs Plus. Compared to the first wave of FSPs led by a subset of frontier AI companies, FSPs Plus should be built around two main pillars. First, FSPs Plus should adopt precursory capabilities as a new, clearer, and more comprehensive set of metrics. In this respect, this paper recommends that international or domestic standardization bodies develop a standardized taxonomy of precursory components to high-impact capabilities that FSPs Plus could then adopt by reference. The Frontier Model Forum could lead the way by establishing preliminary consensus amongst frontier AI developers on this…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Data Processing Techniques · Maritime Navigation and Safety · Military Defense Systems Analysis
