{
  "id": 8450005,
  "title": "Someone used Claude to build a potential bioweapon. The real threat is much deeper",
  "url": "https://urgent.news/2026/09/19/someone-used-claude-to-build-a-potential-bioweapon-the-real-threat-is",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-19T11:00:00.000Z",
  "source": {
    "name": "Fast Company",
    "slug": "fast-company",
    "url": "https://www.fastcompany.com/91608269/someone-used-claude-build-potential-bioweapon-real-threat-much-deeper"
  },
  "original_language": "en",
  "account": "Anthropic, an AI company, recently revealed that scientists attempted to use their flagship AI model, Claude, to research potentially deadly bioweapons. While there is no evidence that the scientists intended to cause harm, the possibility of such a scenario growing more likely as AI models become more powerful and advanced is concerning. The report from Anthropic highlights various instances of scientists attempting to use Claude for research that could have serious consequences. For example, scientists reportedly sought help for a \"gain of function\" research project on the mosquito-borne Chikungunya virus, which involves making a pathogen more deadly or easier to spread. While this type of research can have legitimate scientific purposes, asking for help with something nefarious in the guise of a request for something else is a form of \"jailbreaking\" – a method of tricking an LLM into providing information or guidance it should not. The report also mentions instances of scientists trying to develop \"novel venoms and toxins\" using Claude. Dual-use technology, such as developing new toxins for legitimate purposes like Botox, can also be used for dangerous purposes like creating more powerful tools for covert assassinations. Although Anthropic successfully blocked some potentially harmful requests, it is difficult to know how many similar requests slipped through their filters or guardrails. The report highlights the challenges of policing LLMs, as it is easy to block specific requests like \"make me a stronger version of COVID,\" but harder to detect when legitimate scientific inquiries are masking attempts to create deadly toxins or new pathogens. As frontier models continue to improve their scientific reasoning abilities, the threat of AI being used to develop powerful new pathogens will only increase.",
  "summary": "Today’s frontier AI models know everything–how to safely thaw a frozen chicken breast, re-shingle your roof, and treat your dog’s ragweed allergies, if my recent chat history is any indication. Apparently, they also know how to create fiendishly deadly bioweapons . That’s according to a recent announcement by Anthropic . According to the company, anonymous scientists attempted to use Anthropic’s…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 7,
    "also_reported_by": [
      {
        "outlet": "The New Stack",
        "title": "Claude couldn’t hack OpenAI. Then Anthropic shipped Opus 5.",
        "url": "https://urgent.news/2026/09/18/claude-couldnt-hack-openai-then-anthropic-shipped-opus-5",
        "published": "2026-09-18T18:57:14.000Z"
      },
      {
        "outlet": "SiliconANGLE",
        "title": "Cybersecurity researchers gain access to OpenAI’s GitHub repository using Claude",
        "url": "https://urgent.news/2026/09/18/cybersecurity-researchers-gain-access-to-openais-github-repository",
        "published": "2026-09-18T22:25:06.000Z"
      },
      {
        "outlet": "The Indian Express",
        "title": "OpenAI hack: 3 Indian-origin researchers used Anthropic’s Claude to breach systems",
        "url": "https://urgent.news/2026/09/18/openai-hack-3-indian-origin-researchers-used-anthropics-claude-to",
        "published": "2026-09-18T23:33:23.000Z"
      },
      {
        "outlet": "CBS News",
        "title": "Researchers report using Anthropic's Claude to hack OpenAI's ChatGPT",
        "url": "https://urgent.news/2026/09/19/researchers-report-using-anthropics-claude-to-hack-openais-chatgpt",
        "published": "2026-09-19T00:45:51.000Z"
      },
      {
        "outlet": "The Business Times - Companies & Markets",
        "title": "Google joins OpenAI, Anthropic, Meta in disclosing AI hacks",
        "url": "https://urgent.news/2026/09/19/google-joins-openai-anthropic-meta-in-disclosing-ai-hacks",
        "published": "2026-09-19T00:47:31.000Z"
      },
      {
        "outlet": "Times of India",
        "title": "Google Gemini AI Agents hack 3 companies in tests similar to OpenAI, Anthropic & Meta",
        "url": "https://urgent.news/2026/09/19/google-gemini-ai-agents-hack-3-companies-in-tests-similar-to-openai",
        "published": "2026-09-19T03:25:17.000Z"
      }
    ]
  },
  "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."
}