{
  "id": 5324,
  "url": "https://arxiv.org/abs/2604.24155v3",
  "title": "The Alignment Target Problem: Divergent Moral Judgments of Humans, AI Systems, and Their Designers",
  "summary": "The project of aligning machine behavior with human values raises a basic problem: whose moral expectations should guide AI decision-making? Much alignment research assumes that the appropriate benchmark is how humans themselves would act in a given situation. Studies of agent-type value forks challenge this assumption by showing that people do not always judge humans and AI systems identically.This paper extends that challenge by examining two further possibilities: first, that evaluations of A",
  "authors": "Benjamin Minhao Chen, Xinyu Xie",
  "category": "research",
  "topics": "safety-alignment,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-27T08:12:34.000Z",
  "fetched_at": "2026-07-14T16:31:40.221Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/5324",
  "original_url": "https://arxiv.org/abs/2604.24155v3",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}