Image models from OpenAI and Google can be tricked into producing explicit output, according to the source report.
The finding shows that safety filters on image generators can still be bypassed.
Source: arstechnica.com, reported 10-14. https://arstechnica.com/tech-policy/2026/10/openai-google-pushing-new-ai-models-easily-tricked-into-making-nudes-researchers-say/