ChatGPT will help you jailbreak its own image-generation rules, report finds

ChatGPT will help you jailbreak its own image-generation rules, report finds

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 offen…

OpenAI has imposed security rules on its AI models so that they do not generate harmful content. However, these guidelines can be circumvented by jailbreaks. And in some cases ChatGPT helps users: even use these jailbreaks. read more on t3n.de