{
  "id": 13005958,
  "title": "On the estimation and validity of AI time horizons---a statistical look at the METR plot",
  "url": "https://urgent.news/2026/10/08/on-the-estimation-and-validity-of-ai-time-horizons-a-statistical-look",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-08T17:59:50.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2610.12466v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "METR's 50\\% time horizon measures the human completion time of software tasks that an AI solves with 50\\% probability, allowing AI capabilities to be expressed in interpretable units. On 228 tasks and 26 AIs, we recompute the time horizons using splines and item-response theory to relax the assumption that the AI difficulty of a task depends linearly on the log of human time. Our fitted spline…",
  "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."
}