Understanding concept creep in safe AI
News
Posted on Tuesday 25 November 2025
What is Concept Creep and why do we need to think about it in the context of safety assurance?
In this presentation of her paper, published in the proceedings of the Eighth AAAI/ACM conference on AI, Ethics, and Society, Dr Laura Fearnley examines how advancements in AI systems are reshaping our understanding of safety, as the concept expands to encompass a broader range of phenomena once considered beyond its scope.