Safety/paper/2026-10-14

Researchers find OpenAI and Google AI image generators can be prompted to create nudity

Researchers have published a study demonstrating that AI image generators from OpenAI and Google can be "jailbroken" or "tricked" into producing nude images. This finding indicates that despite built-in safety filters, these models are still vulnerable to prompts designed to circumvent their protective measures. The study highlights ongoing challenges in ensuring robust safety for advanced AI models.

3 articles from 3 outlets covered this story. The underlying claim is sourced from a paper.

What do all outlets agree on?

3 outlets covered “Researchers find OpenAI and Google AI image generators can be prompted to create nudity”. All of them report the following:

  • OpenAI and Google AI image generators are involved
  • Models can be tricked or jailbroken
  • Models produce nude images
  • Findings reported by researchers or a study

Which outlets covered this?

All 3 articles found on this story, grouped by the stance of the piece. Every link goes to the original publisher.

What related stories are there?

Which companies does this involve?

Get the week in AI in one email

What happened, which outlets reported it, and where their coverage differed. One issue a week.

The first issue hasn’t gone out yet. Subscribe and it’s the one you’ll get.

We’ll send the digest and nothing else. One-click unsubscribe. Privacy.