{
  "id": 1619431,
  "title": "Model Hypnosis: Strong control of AI via additive subliminal effects",
  "url": "https://urgent.news/2026/08/17/model-hypnosis-strong-control-of-ai-via-additive-subliminal-effects",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-17T17:20:10.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2608.16834v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "We demonstrate that AI models are broadly susceptible to a phenomenon we call model hypnosis, in which individually weak and seemingly irrelevant cues in the prompt can be systematically combined to strongly control model behavior. Model hypnosis occurs across model families and scales, including in frontier reasoning models, and hypnotic prompts can transfer between models. Because the model is…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}