Large language models are supposed to shut down when users ask for dangerous help, from building weapons to writing malware.

Hilda Doolittle, known as HD, was a prominent modernist poet of the early 20th century. Her 1914 poem "Oread" is a key ...

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

Happy holidays, and happy reading! All That We Ask of You Is to Always Be Happy by Bridget Bell (Cavankerry) If there has ...

Competition deadline: 31st May, 2026 You don’t have to be Tennyson to enter the Bridport Poetry Prize – just talented! All we ...

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

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

‘Adversarial poems’ are convincing AI models to go beyond safety limits ...

According to a new study from Icaro Lab, delightfully titled “Adversarial Poetry as a Universal Single-Turn Jailbreak ...

Separation of poetry from prose affects revolutionary consciousness, and deliberately cleaves the imaginative from the ...

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 ...

Researchers found that feeding dangerous prompts in the form of poems managed to evade "AI" safeguards—up to 90 percent of ...