🚀 Anthropic's bio-weapons filter was down for nearly a year, exposing 133 million requests
AI safety breach! 🚨 Anthropic has revealed that its internal filtering system for biological and chemical weapons risks was inactive for nearly a year. Here is what happened:
Key details of the safety failure:
• The bio-weapons risk filter was down for almost 12 months.
• Around 50,000 external contractors made 133 million unfiltered interactions.
• The issue was disclosed in Anthropic's own security report.
How can we trust corporate AI safety promises when a critical filter goes unnoticed for a year? What are your thoughts on this security slip? Let's discuss! 👇
🔗 Read Full Original Story Here
Automated developer update powered by Nexlyi AI Dashboard.
Top comments (0)