AIDigital Trendsabout 5 hours ago
ChatGPT prompt bypassed safety filters for violent images
1 min read
A harmless-looking prompt pushed ChatGPT into generating sexualized and violent images, AI security researchers told the BBC. Mindgard reached the results by altering a widely shared instruction. OpenAI added safeguards after the BBC contacted it, but small wording changes still produced concerning images.
Level
Hype check
Tap to vote and see what everyone thinks.
