{
  "id": "anthropic-sitemap:research:donating-open-source-petri",
  "type": "article",
  "title": "Donating our open-source alignment tool",
  "abstract": "In October 2025, we launched Petri, an open-source toolbox of alignment tests that can be applied to any large language model. Petri, which was developed as part of our Anthropic Fellows program, can be used to rapidly and easily test AI models for concerning tendencies like deception, sycophancy, and cooperation with harmful requests. It’s part of our efforts to develop alignment tools that are open and useful for the whole AI development community.",
  "issued": {
    "date-parts": [
      [
        2026,
        5,
        7
      ]
    ]
  },
  "URL": "https://www.anthropic.com/research/donating-open-source-petri",
  "publisher": "Anthropic",
  "source": "vendor/anthropic-sitemap/research/donating-open-source-petri.md"
}