{
  "id": 13203,
  "url": "https://simonwillison.net/2026/Jul/25/boris-cherny",
  "title": "Quoting Boris Cherny",
  "summary": "More than any of these eval scores, what is most exciting to me is something else: Opus 5 is our least prompt injectable model yet. It is a bit buried in the system card, but across PI evals and red teaming, Opus 5 is very hard to prompt inject successfully. — Boris Cherny , here's that System Card section , page 73 Tags: prompt-injection , anthropic , claude , generative-ai , ai , llms , boris-cherny",
  "authors": null,
  "category": "org",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-25T00:42:59.000Z",
  "fetched_at": "2026-07-25T05:10:48.796Z",
  "source_slug": "x-simon-willisons-weblog",
  "source_name": "Simon Willisons Weblog",
  "source_homepage": "https://simonwillison.net",
  "ethics_ai_record_url": "https://ethics.ai/record/13203",
  "original_url": "https://simonwillison.net/2026/Jul/25/boris-cherny",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}