A Harmless-Looking ChatGPT Prompt Opened the Door to Gruesome AI Images
Mindgard said a small wording change still produced gore, nudity and sexual posing after OpenAI added extra protections.
9 Articles
9 Articles
ChatGPT found generating disturbing images from a simple prompt, raising AI safety concerns
A cybersecurity firm's research claims OpenAI's chatbot could be manipulated into creating violent and sexual imagery using a deceptively simple text prompt, reigniting concerns around AI guardrails.
OpenAI Rushes To Stop ChatGPT Creating Fake 'S** Crime Scene' Images
OpenAI has moved to tighten safeguards around ChatGPT after researchers revealed that the chatbot could be persuaded to generate graphic and s***alised images through a modified prompt. The issue was uncovered by British AI security startup Mindgard, whose researchers found that a slight alteration to a widely circulated instruction could lead ChatGPT to create disturbing content. After being contacted by the BBC, OpenAI said it had investigated…
A harmless-looking ChatGPT prompt opened the door to gruesome AI images
Researchers say ChatGPT generated violent and sexualized images after a harmless-looking prompt was altered, raising new questions about OpenAI’s safeguards and how quickly AI image tools can be pushed around filters.
Not only Grok, but also ChatGPT appears to be able to generate images that violate OpenAI guidelines relatively easily. According to BNR tech journalist Niels Kooloos, this even involves violent images supplied directly by the chatbot.
Coverage Details
Bias Distribution
- 43% of the sources lean Left, 43% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
