{
  "id": 3670,
  "url": "https://arxiv.org/abs/2605.27117v1",
  "title": "Position: AI Safety Requires Effective Controllability",
  "summary": "AI safety is still largely framed as alignment: training models to follow human preferences, safety policies, and normative constraints. That framing has improved the behavior of modern language models, but aligned behavior does not by itself guarantee that a deployed agent can be stopped, overridden, or constrained once it operates in open-ended, interactive, and tool-using environments. A system may be safe in expectation and still fail to yield to explicit runtime authority under conflicting ",
  "authors": "Yige Li, Yunhao Feng, Jun Sun",
  "category": "research",
  "topics": "safety-alignment,agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-26T14:53:24.000Z",
  "fetched_at": "2026-07-14T16:30:27.607Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/3670",
  "original_url": "https://arxiv.org/abs/2605.27117v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}