Rashan Brown's New York-based side hustle Poetry me, please — a series of poetry showcase events — brings in six figures per ...

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

When prompts were presented in poetic rather than prose form, attack success rates increased from 8% to 43%, on average — a ...

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

Riddle-like poems tricked chatbots into spewing hate speech and helping design nuclear weapons and nerve agents. It turns out ...

Poetry -based prompts can bypass safety features in AI models like ChatGPT to obtain instructions for creating malware or ...

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

Natalie Lim is a Chinese-Canadian poet based in Vancouver. Her work has been featured in Arc Poetry Magazine and Best ...

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 ...

You can get ChatGPT to help you build a nuclear bomb if you simply design the prompt in the form of a poem, according to a new study from researchers in Europe. The study, "Adversarial Poetry as a ...

A month before COVID struck, I took a course in writing poetry. I chose poetry for the same reason I might have chosen opera ...

Researchers from Italy discovered that phrasing prompts in poetry can be a reliable jailbreaking method for LLMs.