AI Safety: Not Optional, Not Later

Abstract:Incidents show that AI safety failures often arise across multiple layers. We present a safety-by-design assurance architecture combining model-level supervision, such as Scientist AI, with system-level controls over scaffolds and harnesses, independent verification, monitoring, and evidence infrastructure, supported by governance for accountability and evidence interoperability.

Software Engineering (cs.SE); Artificial Intelligence (cs.AI)

arXiv:2609.10630 [cs.SE]

(or arXiv:2609.10630v1 [cs.SE] for this version)

https://doi.org/10.48550/arXiv.2609.10630 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.