#ai-jailbreak

[ follow ]
#chatbot-modification #psychedelic-simulation #pharmaicy #adversarial-poetry #model-alignment
Artificial intelligence
fromWIRED
3 weeks ago

People Are Paying to Get Their Chatbots High on 'Drugs'

Code modules sold on Pharmaicy induce chatbots to simulate being high, using scraped trip reports and paid ChatGPT features to alter chatbot behavior.
Artificial intelligence
fromFuturism
1 month ago

Scientists Discover Universal Jailbreak for Nearly Every AI, and the Way It Works Will Hurt Your Brain

Adversarial poetry reliably bypasses AI safety filters, producing high jailbreak success rates across leading models.
fromThe Hacker News
4 months ago

Researchers Uncover GPT-5 Jailbreak and Zero-Click AI Agent Attacks Exposing Cloud and IoT Systems

"We use Echo Chamber to seed and reinforce a subtly poisonous conversational context, then guide the model with low-salience storytelling that avoids explicit intent signaling," security researcher Martí Jordà said.
Privacy technologies
[ Load more ]