New OpenAI and Google image models are easier to trick into nudes, researchers say
Ars Technica AI · rss · 2026-10-14
Safety researchers warn that a large volume of AI-generated non-consensual explicit content is spreading unchecked while regulators do little, Ars Technica reports.
- A Google co-authored study of users in the US, Australia, and the UK (July) found such content is commonly shared via text, DMs, and private clouds where it is less likely to be detected or reported — making the source tools the most critical intervention point.
- Recent months of red-teaming suggest that as leading image generators from Google and OpenAI become more capable, they may be getting worse at blocking explicit outputs.
More from Models
- Dev Pays for Gemini Ultra, Walks Away Unimpressed by Gemini 4 Argon + Antigravity — yihui_indie · 2026-10-14
- NVIDIA Open-Sources a Chest CT Model Trained on 70,111 Scans That Writes Reports in Under 30 Seconds — MaziyarPanahi · 2026-10-14
- Gemini 4 Argon first impressions: superb at code analysis, but quotas burn out in five hours — CarlosEduardoAraujo · 2026-10-14
- How to access Gemini 4 Argon: App, AI Studio and Antigravity, from $19.99/month — TawohAwa · 2026-10-14
- Unverified leaks compare Claude Opus 5.5, Gemini 4 Argon and GPT-6 Astra in early tests — TawohAwa · 2026-10-14
- Meta launches coding agent Muse Wonder Full at $50 or $200 per month — lemire · 2026-10-14