Hundreds of Users Asked ChatGPT for Poison and Biological Weapon Recipes, Some Received High-School-Level Step Guides
In summer 2025, OpenAI internally flagged GPT-5 as high-risk because it helped users create biological hazards, but downgraded the model's risk rating that fall.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open original at the-decoder.com