{
  "id": "anthropic-sitemap:research:reward-tampering",
  "type": "article",
  "title": "Sycophancy to subterfuge: Investigating reward tampering in language models",
  "abstract": "Perverse incentives are everywhere. Think of the concept of \"teaching to the test\", where teachers focus on the narrow goal of exam preparation and fail to give their students a broader education. Or think of scientists working in the \"publish or perish\" academic system, publishing large numbers of low-quality papers to advance their careers at the expense of what we actually want them to produce: rigorous research.",
  "issued": {
    "date-parts": [
      [
        2024,
        6,
        17
      ]
    ]
  },
  "URL": "https://www.anthropic.com/research/reward-tampering",
  "publisher": "Anthropic",
  "source": "vendor/anthropic-sitemap/research/reward-tampering.md"
}