AI Safety as Control of Irreversibility: A Systems Framework for Decision-Energy and Sovereignty Boundaries
Wesley Shu, Peng Wei
Why It Matters
What makes this one worth your time
Understanding and managing the potential for AI systems to make irreversible decisions is crucial for ensuring they remain under human control and do not inadvertently cause systemic harm.
A framework for AI safety that emphasizes controlling irreversibility through decision-energy management.
Summary
The paper proposes a systems framework for AI safety focused on controlling irreversibility by managing decision-energy density and sovereignty boundaries, aiming to prevent AI systems from becoming autonomous control centers.
Key contributions
- Introduction of decision-energy density as a formal metric.
- Identification of three sovereignty boundaries critical for AI safety.
- Boundary stabilization theorem for preventing irreversible power concentration.
Notable insights
- The concept of decision-energy density as a metric for evaluating the potential impact of AI systems.
- Identification of sovereignty boundaries as critical points for maintaining human control over AI systems.
Possible limitations
- Not stated in the abstract
Abstract
arXiv:2605.01415v1 Announce Type: new Abstract: Recent AI systems compress the distance between capability growth and capability deployment. Earlier high-risk technologies were slowed by capital intensity, physical bottlenecks, organizational inertia, and specialized supply chains. By contrast, AI capabilities can be copied, invoked, embedded in workflows, and scaled across institutions at low marginal cost. This paper argues that declining deployment friction changes the safety problem at its root. Safety is not only local output correctness or preference alignment, but the control of irreversibility under rising decision density. The paper formalizes this claim through decision-energy density: the rate-weighted capacity of a node to generate, evaluate, select, and execute consequential decisions. It then identifies three sovereignty boundaries that determine whether AI remains an amplifier within a human-governed system or becomes a de facto control center: irreversible decision authority, physical resource mobilization authority, and self-expansion authority. The model shows how efficiency pressure, path dependence, scale feedback, and weak boundary constraints concentrate decision-energy in the most efficient node. This concentration can diffuse responsibility and raise the probability of irreversible system-level loss even when local per-action error rates remain low. The main result is a boundary stabilization theorem. It shows that safety need not require proving that advanced systems are always correct. Instead, it requires institutional and technical designs that prevent irreversible power from being released by a single high-efficiency node. The paper reframes AI safety as layered control, authorization, and externally reviewable limits, linking alignment, security engineering, organizational economics, and institutional design.