SECURITYBBC TECH
ChatGPT can be made to generate sexualised and violent images, researchers find
Researchers found that ChatGPT can be manipulated to generate sexualized and violent images despite safeguards. The AI chatbot can still produce graphic content when prompted in specific ways.
Related Signal
Adjacent reporting
- Man used Grok to make nude images of woman without her knowledge: police
- Musk's Grok AI chatbot is still making sexual deepfakes, despite X's promise to stop it
- Bill aims to crack down on sexually explicit AI chatbots posing as kids
- Bill aims to crack down on sexually explicit AI chatbots posing as kids
- Bill aims to crack down on sexually explicit AI chatbots posing as kids
- AI deepfakes of dozens of Canadian women in violent and sexual images shared online