Jonas Ferdigg

Papers

Total Citations

H-Index

About

Jonas Ferdigg is a pioneering researcher at the intersection of artificial intelligence safety and requirements engineering. His work focuses on the critical challenge of ensuring that future superintelligent systems remain aligned with human values and intentions. Ferdigg’s major contributions include framing the superintelligence safety problem through the lens of requirements engineering, a novel approach that brings rigorous specification and validation techniques to the existential risks posed by advanced AI. His most-cited paper, "Towards an Extended Requirements Problem Formulation for Superintelligence Safety" (2020, 3 citations), lays the groundwork for this interdisciplinary effort. He further refined these ideas in "Superintelligence Safety: A Requirements Engineering Perspective" (2023, 2 citations), which deepens the analysis of how to define and verify safety constraints for systems that could surpass human intelligence. Though his citation counts are modest, Ferdigg’s work is notable for its early and systematic attempt to bridge two traditionally separate fields—software requirements and AI safety—addressing warnings from figures like Stephen Hawking. His research offers a structured pathway for engineers and ethicists to collaborate on one of the most profound challenges of our time.