AI Safety for Everyone

TL;DR

This paper reviews AI safety research, emphasizing practical safety concerns like robustness and interpretability, and advocates for an inclusive approach that encompasses diverse perspectives and safety challenges beyond existential risks.

Contribution

It provides a systematic review highlighting practical AI safety work and proposes a broader, more inclusive framework for the field.

Findings

Most safety research addresses current AI system issues.

Safety work extends existing technological safety practices.

A pluralistic approach can better encompass diverse safety concerns.

Abstract

Recent discussions and research in AI safety have increasingly emphasized the deep connection between AI safety and existential risk from advanced AI systems, suggesting that work on AI safety necessarily entails serious consideration of potential existential threats. However, this framing has three potential drawbacks: it may exclude researchers and practitioners who are committed to AI safety but approach the field from different angles; it could lead the public to mistakenly view AI safety as focused solely on existential scenarios rather than addressing a wide spectrum of safety challenges; and it risks creating resistance to safety measures among those who disagree with predictions of existential AI risks. Through a systematic literature review of primarily peer-reviewed research, we find a vast array of concrete safety work that addresses immediate and practical concerns with current AI systems. This includes crucial areas like adversarial robustness and interpretability, highlighting how AI safety research naturally extends existing technological and systems safety concerns and practices. Our findings suggest the need for an epistemically inclusive and pluralistic conception of AI safety that can accommodate the full range of safety considerations, motivations, and perspectives that currently shape the field.