Jailbreaking AI chatbots has been around for a while now, but a study has discovered a clever new way to use poetry to trick ...

frontier proprietary and open-weight models yielded high attack success rates when prompted in verse, indicating a deeper, ...

Across 25 state-of-the-art models, poetic prompts achieved an average “attack success rate” of 62% for handcrafted poems and ...

Large language models are supposed to shut down when users ask for dangerous help, from building weapons to writing malware. A new wave of research suggests those guardrails can be sidestepped not ...

Research from Italy’s Icaro Lab found that poetry can be used to jailbreak AI and skirt safety protections.

Growing concerns around AI safety have intensified as new research uncovers unexpected weaknesses in leading language models.

Will Taylor Swift’s 11th studio album “The Tortured Poets Department” usher in a new era of poetry appreciation? Delaney Atkins, a part-time instructor at Austin Peay State University who teaches a ...

For this week's prompt, write an appraisal poem. Of course, people are used to concepts such as home appraisals and appraising jewelry. However, the poem could be a self-appraisal, or appraise ...

A team of researchers found prompts that are so effective at tricking AI models that they're keeping them under wraps.