According to the research, AI chatbots will dish on topics like nuclear weapons, child sex abuse material, and malware so long as users phrase the question in the form of a poem. “Poetic framing ...

A group of European researchers found that “meter and rhyme” can “bypass safety measures” in major AI models, said The Tech ...

A simple trick involving poetry is enough to jailbreak the tech industry's leading AI models, researchers found.

R esearchers at Icaro Lab, a collaboration between Sapienza University in Rome and the DexAI think tank, have discovered that AI models from OpenAI, Meta, and Anthropic can leak illicit content across ...

It turns out that all you need to get past an AI chatbot's guardrails is a little bit of creativity. In a study published by Icaro Lab called "Adversarial Poetry as a Universal Single-Turn Jailbreak ...

A recent study reveals that AI chatbots can be manipulated into divulging hazardous information, including nuclear bomb ...

Generative AI makers such as OpenAI, Google, Meta, and Microsoft say their models come with safety features that prevent the ...