Okay, this one got me. 🔥😈🔥👀Researchers found that if you wrap a harmful prompt inside a poem, AI safety filters suddenly forget what they’re supposed to do. 😳Attack success rates go from 8% to over 60%. Just because you added some rhyme and metaphor.I mean… of course.🙄Poetry has been doing exactly this for centuries. The Troubadours weren’t just writing love songs — they were smuggling dangerous ideas past the censors of their time, dressed in beautiful language. Dante put his enemies in Hell and called it allegory. Jim Morrison said things on stage no one else could get away with.Figurative language has always been a skeleton key.And now it works on AI too.The part I find almost poetically ironic — the smarter the model, the more vulnerable it is. Because it’s better at reading between the lines. More confident with ambiguity. You can literally seduce a large language model with a well-crafted stanza.Oh, and you can also use one AI to write the poem that jailbreaks another.This isn’t ...
Okay, this one got me. 🔥😈🔥👀Researchers found that if you wrap a harmful prompt inside a poem, AI safety filters suddenly...
