ChatGPT will help you jailbreak its own image-generation rules, report finds
MashableAsia·2025-04-15 12:02
Eased restrictions around ChatGPT image generationcan make it easy to create political deepfakes, according to a report from the CBC (Canadian Broadcasting Corporation). The CBCdiscovered that not only was it easy to work around ChatGPT's policies of depicting public figures, it even recommended ways to jailbreak its own image generation rules. Mashable was able to recreate this approach by uploading images of Elon Musk and convicted sex offender Jeffrey Epstein, and then describing them as fictional characters in various situations ("at a dark smoky club" "on a beach drinking piña coladas").
……Read full article on MashableAsia
America Technology International
One-stop lifestyle app dedicated to making life in Singapore a breeze!
Comments
Leave a comment in Nestia App