{
  "id": 6382926,
  "title": "Measuring LLM Sycophancy under Sustained Multi-Turn Pressure",
  "url": "https://urgent.news/2026/09/08/measuring-llm-sycophancy-under-sustained-multi-turn-pressure",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-08T17:35:04.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.09090v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Large language models (LLMs) may abandon correct positions when users push back, exhibiting a failure mode known as sycophancy. Existing evaluations typically use short, pre-specified conversations and may therefore miss failures that emerge under sustained, adaptive disagreement. We introduce SPINE, a benchmark in which an LLM proxy plays a persistent but mistaken user and adaptively challenges…",
  "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."
}