{
  "id": 1278,
  "url": "https://arxiv.org/abs/2606.08832v1",
  "title": "Instrumental convergence and power-seeking",
  "summary": "Recent years have seen increasing concern that artificial intelligence may soon pose an existential risk to humanity. One leading ground for concern is that artificial agents may be power-seeking, aiming to acquire power and in the process disempowering humanity. I show how the argument from power-seeking rests on a strong version of a claim known as the instrumental convergence thesis. I explore leading defenses of the instrumental convergence thesis and argue that none establishes the thesis i",
  "authors": "David Thorstad",
  "category": "research",
  "topics": "safety-alignment,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-07T20:52:32.000Z",
  "fetched_at": "2026-07-14T14:15:07.846Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/1278",
  "original_url": "https://arxiv.org/abs/2606.08832v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}