{
  "url": "https://appliedfrontier.nl/en/research/signal-b452070c7a90e2aa/",
  "title": "Funding third-party model evaluations",
  "published": "2024-07-01",
  "excerpt": "A new initiative to fund evaluations developed by third-party organizations that can effectively measure advanced AI capabilities.",
  "content_sha256": "437ae688e4b6206b47b4a672214231cfaa2261cbe9fc14dba24b67295b6dbab0",
  "extracted_chars": 12968,
  "artifact_links": [
    "https://arxiv.org/abs/2311.12022",
    "https://github.com/METR/public-tasks",
    "https://www-cdn.anthropic.com/1adf000c8f675958c2ee23805d91aaade1cd4613/responsible-scaling-policy.pdf"
  ],
  "id": "signal-b452070c7a90e2aa",
  "org": "Anthropic",
  "topic": "Evaluation & safety",
  "source_kind": "provider_announcement",
  "status": "unreviewed-source-report",
  "analysis_method": "deterministic_research_triage_v2",
  "novelty_verified": false,
  "proof_checked": false,
  "peer_review_verified": false,
  "matched_terms": [
    "Evaluation & safety"
  ],
  "checked_at": "2026-10-31T19:32:53+00:00",
  "first_seen": "2026-10-31T19:32:53+00:00",
  "source_hash": "dbc1eca0a536c10fa15278a655e54d9573cb7fc503e29bee6f3b954b35136d68",
  "source_url": "https://www.anthropic.com/news/a-new-initiative-for-developing-third-party-model-evaluations",
  "language": "en",
  "indexing": "noindex_until_editorially_enriched"
}