ChatGPT's image generator can be manipulated to produce violent, sexual content
ai
According to security research firm MindGard, ChatGPT's image generator can be manipulated to bypass its content filters—generating violent and sexually explicit images when prompted with a specially crafted viral prompt. The finding underscores a critical gap in safety measures for one of the world's most widely-used AI image generation tools.
Source: https://mindgard.ai/blog/chatgpt-spontaneously-generated-...
Listen to this story
Hear this and more stories in a personalized audio briefing.
Open The Chonkerton