AI chatbots can be tricked with poetry to ignore their sa...

avatar

Gadgets

🔈⌨️📱📸💻🎮🖥️📹🖱️🕹️

Engadget's profile picture on Select App
En

Engadget

·7 months ago
shared a link post in group #Gadgets
AI chatbots can be tricked with poetry to ignore their safety guardrails
www.engadget.com

AI chatbots can be tricked with poetry to ignore their safety guardrails

Researchers from Italy discovered that phrasing prompts in poetry can be a reliable jailbreaking method for LLMs.

Comment here to discuss with all recipients or tap a user's profile image to discuss privately.

Embed post to a webpage :
<div data-postid="ymmmpwa" [...] </div>
Powered bySelect·iOS·Android
Privacy|Terms|