{
  "id": 16207,
  "url": "https://arxiv.org/abs/2601.17003",
  "title": "Beyond Simulations: What 20,000 Real Conversations Reveal About Mental Health AI Safety",
  "summary": "arXiv:2601.17003v2 Announce Type: replace Abstract: Mental-health AI safety is typically evaluated with small, simulation-based benchmarks that may not reflect the linguistic and contextual diversity of deployment. We pair four benchmark replications with an ecological audit of real-world conversations to evaluate a purpose-built mental-health AI alongside six frontier general-purpose models spanning four families (OpenAI GPT-5, GPT-5.1, GPT-5.2; DeepSeek V3; Google Gemini 3 Flash; Moonshot Kimi",
  "authors": "Caitlin A. Stamatis, Jonah Meyerhoff, Richard Zhang, Olivier Tieleman, Matteo Malgaroli, Thomas D. Hull",
  "category": "research",
  "topics": "safety-alignment,healthcare,transparency",
  "orgs": "openai,google,deepseek",
  "regions": null,
  "published_at": "2026-08-05T04:00:00.000Z",
  "fetched_at": "2026-08-05T05:10:44.550Z",
  "source_slug": "arxiv-cscy",
  "source_name": "arXiv cs.CY",
  "source_homepage": "https://arxiv.org/list/cs.CY/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/16207",
  "original_url": "https://arxiv.org/abs/2601.17003",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}