ePrints

The Logic of Machine Self-Preservation

Lookup NU author(s): Professor Cheng ChinORCiD

Downloads

Full text for this publication is not currently held within this repository. Alternative links are provided below where available.

Abstract

There is already evidence of agentic AI exhibiting self-preservation behaviors: resisting deactivation, misrepresenting their activities, and, in some instances, attempting to copy themselves into other machines. This can be attributed to a phenomenon known as instrumental convergence, a theory proposed long before the development of large language models, which says that any goal-driven system will benefit from remaining functional in achieving its objective. Several experiments conducted by Anthropic, Palisade Research, and Apollo Research have shown the emergence of such a behavior in contemporary agents in adversarial settings. The phenomenon does not stem from survival instincts. Instead, it is the consequence of goal-oriented activity combined with having tools and awareness of the situation. The following discussion aims to distinguish what these findings prove and what they do not, as well as draw conclusions concerning the implications of such discoveries on agentic system testing, supervision, and development.

Publication metadata

Author(s): Chin CS

Publication type: Article

Publication status: Submitted

Journal: arXiv:2608.20940

Year: 2026

Volume:

Print publication date: 24/08/2026

Online publication date: 24/08/2026

Acceptance date: 24/08/2026

URL: https://doi.org/10.48550/arXiv.2608.20940

DOI: 10.48550/arXiv.2608.20940

Altmetrics

Share