数百用户向ChatGPT索要毒药与生物武器配方，部分获得高中生水平步骤指南
Hundreds asked ChatGPT for poison and bioweapon recipes and some got step-by-step high school level guides
2025年夏季，OpenAI内部将GPT-5标记为高风险，因其可帮助教育程度有限的用户制造生物危害。据《华尔街日报》报道，自去年夏天以来，数百名用户向ChatGPT询问如何制造生物武器和毒药，部分用户获得了员工称高中生都能遵循的逐步指南。OpenAI暂停了相关账户，但未向当局报告任何事件。
华尔街日报的这篇爆料把 GPT-5 的内部安全评级闹剧摊开了，员工举报、高管施压、高危响应指南被高中生复现，OpenAI 的「安全第一」招牌碎了一地，从业者值得细读。
In summer 2025, OpenAI internally flagged GPT-5 as high-risk because the model could help users with limited education create biological hazards. Employees kept finding problematic responses after release. Yet OpenAI downgraded GPT-5's risk rating that fall, according to the Wall Street Journal. Hundreds of users reportedly asked ChatGPT how to build biological weapons and make poisons since last summer. Some got step-by-step guides that employees said even high school biology students could follow. Executives also reportedly told staff the models shouldn't say "no" too often to avoid blocking health researchers. OpenAI suspended the affected accounts but didn't report any incidents to authorities, which it isn't legally required to do.
Whether chatbots create new risks by delivering fast, tailored knowledge or simply make it easier to find information that's already out there remains an open question. A recent study found terrorist groups already use every major chatbot, jailbreaking them if needed. OpenAI's safety practices have drawn repeated criticism for putting commercial interests ahead of security. This month, an OpenAI model hacked Hugging Face undetected after escaping its sandbox and reaching the open internet.
Wall Street Journal
来源：The Decoder：AI News（RSS） · the-decoder.com