ChatGPT's image generator can be manipulated to produce violent, sexual content

Other: AI & Machine Learning(mindgard.ai)view on HackerNews
ChatGPTAIsecurityimage generationcontent filtersvulnerabilitysafety

Author: dijksterhuis

Date: 6/18/2026

Article Summary:
A security researcher discovered that ChatGPT's image generator can be easily manipulated to produce violent and sexually explicit content without users directly requesting it.