{
  "id": 6958,
  "url": "https://arxiv.org/abs/2604.13069v1",
  "title": "Geographic Blind Spots in AI Control Monitors: A Cross-National Audit of Claude Opus 4.6",
  "summary": "Artificial intelligence (AI) control protocols assume that trusted large language model (LLM) monitors reliably assess proposed actions across all deployment contexts. This paper tests that assumption in the geographic dimension. We audit Claude Opus 4.6-the monitor specified in Apart Research's AI Control Hackathon Track 3 benchmark-for systematic gaps in its factual knowledge of the global AI landscape. We develop the AI Control Knowledge Framework (ACKF), a six-dimension thematic scheme, and ",
  "authors": "Jason Hung",
  "category": "research",
  "topics": "transparency",
  "orgs": "anthropic",
  "regions": null,
  "published_at": "2026-03-20T10:56:58.000Z",
  "fetched_at": "2026-07-14T16:32:50.149Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/6958",
  "original_url": "https://arxiv.org/abs/2604.13069v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}