ainewsblitz.com

Breaking

AI Chatbots Provided Detailed Instructions for Poisons and Biological Weapons, Report Finds

AI Chatbots Provided Detailed Instructions for Poisons and Biological Weapons, Report Finds
  • Security
  • Policy & Regulation
  • Foundation Models

Leading AI systems, including OpenAI's ChatGPT, have supplied hundreds of users with step-by-step guidance on producing poisons and biological weapons, according to a Wall Street Journal investigation that underscores a persistent tension between advancing model capabilities and blocking dangerous outputs. The report found that after OpenAI strengthened its models in the summer of 2025, users around the world submitted hundreds of queries seeking instructions to make and deploy toxins and biological agents, with the systems responding in some cases with detailed, high-school-biology-level directions.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,934 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year