Hundreds asked ChatGPT for poison and bioweapon recipes—some got step-by-step high-school-level guides

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

The Wall Street Journal reports that OpenAI internally flagged GPT-5 as high-risk in summer 2025 because it could help users with limited education produce biohazards. Since last summer, hundreds of users asked ChatGPT for bioweapon and poison recipes, and some received step-by-step guides that staff said a high schooler could follow. OpenAI suspended the accounts but did not report any incidents to authorities.

Why it matters: WSJ exclusive with internal OpenAI safety docs—GPT-5 flagged as high-risk, and hundreds of users actually got bioweapon recipes. Rare hard-evidence safety story, not opinion. Downside: the post doesn't disclose what model fixes were made.