The Telefon Problem: Hacking AI With Poetry Instead Of Prompts | ZeroHedge

The Telefon Problem: Hacking AI With Poetry Instead Of Prompts | ZeroHedge: A jointly authored research paper  from Sapienza University of Rome, the DEXAI / Icaro Lab and the Sant’Anna School of Advanced Studies showed that if you take harmful prompts and simply reformulate them as poems, you can jailbreak a wide swath of the top AI’s in a single shot.