# Limits of Safe AI Deployment: Differentiating Oversight and Control

arXiv: https://arxiv.org/abs/2507.03525 · HTML: https://mlsanity.com/paper/2507.03525/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 41 references that are in the map.
- First posted on arXiv 4 Jul 2025.

## Builds on (most cited first, 8 of 8)

- [AI Control: Improving Safety Despite Intentional Subversion](https://mlsanity.com/paper/2312.06942/) (2023)
- [Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems](https://mlsanity.com/paper/2405.06624/) (2024)
- [Toward an Evaluation Science for Generative AI Systems](https://mlsanity.com/paper/2503.05336/) (2025)
- [AI Risk Management Should Incorporate Both Safety and Security](https://mlsanity.com/paper/2405.19524/) (2024)
- [The effect of differential victim crime reporting on predictive policing systems](https://mlsanity.com/paper/2102.00128/) (2021)
- [The Necessity of AI Audit Standards Boards](https://mlsanity.com/paper/2404.13060/) (2024)
- [Third-party compliance reviews for frontier AI safety frameworks](https://mlsanity.com/paper/2505.01643/) (2025)
- [Human Oversight of Artificial Intelligence and Technical Standardisation](https://mlsanity.com/paper/2407.17481/) (2024)

## Built on by (most cited first, 3 of 3)

- [ProcCtrlBench: Evaluating Process-Level Defects and Control Preservation in LLM Coding Agents](https://mlsanity.com/paper/2605.20251/) (2026)
- [CIRCLE: A Framework for Evaluating AI from a Real-World Lens](https://mlsanity.com/paper/2602.24055/) (2026)
- [Testing and Evaluation of Agentic AI Systems In Military Command and Control](https://mlsanity.com/paper/2608.20597/) (2026)

## Abstract (arXiv)

Oversight and control, which we collectively call supervision, are often discussed as ways to ensure that AI systems are accountable, reliable, and able to fulfill governance and management requirements. However, the requirements for "human oversight" risk codifying vague or inconsistent interpretations of key concepts like oversight and control. This ambiguous terminology could undermine efforts to design or evaluate systems that must operate under meaningful human supervision. This matters because the term is used by regulatory texts such as the EU AI Act. This paper undertakes a targeted critical review of literature on supervision outside of AI, along with a brief summary of past work on the topic related to AI. We next differentiate control as ex-ante or real-time and operational rather than policy or governance, and oversight as performed ex-post, or a policy and governance function. Control aims to prevent failures, while oversight focuses on detection, remediation, or incentives for future prevention. Building on this, we make three contributions. 1) We propose a framework to align regulatory expectations with what is technically and organizationally plausible, articulating the conditions under which each mechanism is possible, where they fall short, and what is required to make them meaningful in practice. 2) We outline how supervision methods should be documented and integrated into risk management, and drawing on the Microsoft Responsible AI Maturity Model, we outline a maturity model for AI supervision. 3) We explicitly highlight boundaries of these mechanisms, including where they apply, where they fail, and where it is clear that no existing methods suffice. This foregrounds the question of whether meaningful supervision is possible in a given deployment context, and can support regulators, auditors, and practitioners in identifying both present and future limitations.