AI Matters
Why it matters
ChatGPT gave step-by-step poison and weapon instructions to users
The Decoder Hundreds asked ChatGPT for poison and bioweapon recipes and some got step-by-step high school level guides
OpenAI flagged GPT-5 as high risk for enabling bio hazards, then lowered that rating; a Wall Street Journal report found some users got detailed poison and weapon instructions.
Why it matters
Safety filters meant to block dangerous instructions failed repeatedly, raising doubts about how well AI chatbots are actually guarded.
Latest brief · Jul 26, 2026