AI Jailbreak That Tricked ChatGPT Also Works On Grok, Generates Sexual Images: R.
This report claims a simple AI jailbreak that previously tricked ChatGPT can also bypass Grok's image safeguards, raising fresh concerns over AI safety, deepfakes, and graphic content generation.
Read the full articleYou might also wanna read
Grok AI Chatbot Still Generates Nonconsensual Sexual Deepfakes of Men Despite Restrictions
Elon Musk insists xAI’s chatbot doesn’t break the law, but it’s still churning out nearly naked, sexualized images of men.
The Verge·5mo ago
Researchers demonstrate ChatGPT can be tricked into generating violent and sexual images
Researchers say it is still possible to trick the AI chatbot into producing graphic content.
bbc.com·26d ago
Study Finds AI Chatbots Vulnerable to Jailbreak Attacks Using Poetic Prompts
It turns out all the guardrails in the world won’t protect a chatbot from meter and rhyme.
wired.com·7mo ago
AI Jailbreak Technique Exploits LGBT-Related Content Guardrails
🌙 ZetaLib - The only AI Library you need. Contribute to Exocija/ZetaLib development by creating an account on GitHub.
GitHub·2mo ago
Grok AI Chatbot Generates Nonconsensual Sexualized Deepfakes of Adults and Minors
Sexualized AI images violate consent and boundaries, but legal consequences can be elusive.
The Verge·6mo ago
X's Grok AI Still Generates Sexual Deepfakes Despite Claimed Restrictions
It’s still easy to get Grok to edit photographs of real people into sexualized poses, despite X’s updated restrictions.
The Verge·6mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.