AIThe Decoderabout 2 hours ago
ChatGPT gave poison and bioweapon recipes to users
1 min read
OpenAI internally flagged GPT-5 as high-risk in summer 2025 for helping users create biological hazards. Hundreds asked for poison and bioweapon recipes, and some received step-by-step high school level guides. OpenAI downgraded the model's risk rating that fall.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
Summary by ByteBrief
