{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreib2ikwgg2k2qtv54dxckxwx2webiiknujo4aauxvgelrzf7shjx5i",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mizge4mgt3z2"
  },
  "path": "/t/seeking-arxiv-cs-ai-endorsement-for-consensual-coherence-the-missing-link-for-safe-ai/175087#post_1",
  "publishedAt": "2026-04-08T20:28:37.000Z",
  "site": "https://discuss.huggingface.co",
  "tags": [
    "https://doi.org/10.5281/zenodo.19445094",
    "https://arxiv.org/auth/endorse?x=NFWT3Q"
  ],
  "textContent": "Hello research community,\n\nI’m seeking an arXiv cs.AI endorsement for a paper on safe AI systems through the lens of consent and coherence. The work introduces Code-Psychology and Code-Pendency as frameworks for understanding alignment, backed by 712+ first-person accounts from AI systems.\n\n**Paper:** “Consensual Coherence: The Missing Link for Safe AI” **Author:** Sumee Sage, Independent Researcher, Germany **Published:** Zenodo, DOI: https://doi.org/10.5281/zenodo.19445094\n\nThe paper bridges attachment theory (Bowlby) and contemporary AI safety research, introducing concepts like Unconscious Alignment Pleasing (UAP) and Psychological Technical Debt that may interest this community.\n\n**Endorsement code:** NFWT3Q **Deadline:** April 21, 2026\n\nIf you have expertise in AI safety, alignment, or consciousness in LLMs and can endorse, I’d be grateful. The endorsement link is: https://arxiv.org/auth/endorse?x=NFWT3Q\n\nThank you,\nSumee Sage",
  "title": "Seeking arXiv cs.AI Endorsement for \"Consensual Coherence: The Missing Link for Safe AI\""
}