According to the researchers, chatbots including ChatGPT, Claude and others were far more likely to respond to prohibited ...

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, underlying problems in their ability to process ambiguity veiled in poetry.

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

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

Growing concerns around AI safety have intensified as new research uncovers unexpected weaknesses in leading language models. A recent study has revealed that p ...

Wow! It feels so long since our last Wednesday Poetry Prompt (almost like another time and place), but it's only been a little over a month. So weird how time works at times. For this week's prompt, ...

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 ...

The Red & Black is a 501c3 nonprofit. Please consider a one-time gift or become a monthly supporter. Cancel anytime. Every April since its inception in 1996 by the Academy of American Poets, National ...