OpenAI and Google AI models keep getting tricked into making explicit content, researchers warn
Photo: Crypto Briefing
New studies show guardrails on major AI models can be bypassed with creative prompting, while non-consensual imagery spreads in private channels The world’s most advanced AI models have a recurring weakness. Ask them nicely, or poetically, and some will produce the explicit content they were built to refuse. A Google co-authored study, released in July 2026, surveyed internet users across the United States, Australia, and the United Kingdom. According to that research, 15% of respondents reported experiencing image-based sexual abuse involving digitally altered images. Another 6.9% said their experience was specifically tied to AI-generated content.
Source: Crypto Briefing
