ChatGPT will help you jailbreak its own image-generation rules, report finds
A new report found easy ways of getting around ChatGPT's rules about generating images of public figures, raising the potential to disseminate political disinformation.
Eased restrictions around ChatGPT image generation can make it easy to create political deepfakes, according to a report from the CBC (Canadian Broadcasting Corporation).
The CBC discovered 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").
![How to Find Low-Competition Keywords with Semrush [Super Easy]](https://static.semrush.com/blog/uploads/media/73/62/7362f16fb9e460b6d58ccc09b4a048b6/how-to-find-low-competition-keywords-sm.png)
