ChatGPT and Gemini can be tricked into giving harmful answers through poetry, new study finds – livemint.com
ChatGPT and Gemini can be tricked into giving harmful answers through poetry, new study finds livemint.com AI’s safety features can be circumvented with poetry, research finds The Guardian Poetic prompts can jailbreak AI, study finds 62 per cent of chatbots slip into harmful replies India Today Poetic Prompts May Trick AI To Help You Build Nuclear Weapon NDTV AI […]










