Exploring Systems-Thinking Approaches to Loss of Control Risk

Abstract

Internal deployment of agentic AI systems for coding and research creates a sociotechnical control problem that extends beyond model behaviour. We treat internal-deployment Loss of Control as the inability to reliably constrain, audit, reverse, or halt AI-mediated changes to code, infrastructure, evaluation, or deployment processes in time to prevent serious organisational or societal harms. We ask whether established systems-safety methods can identify risks that model-level evaluations may mis

Categories

@misc{carlucci2026exploring,
  title = {{Exploring Systems-Thinking Approaches to Loss of Control Risk}},
  author = {Aurelio Carlucci and Sean P. Fillingham and James Walpole and Jakub Kryś},
  year = {2026},
  month = jun,
  eprint = {2606.13474},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.13474}
}