Security researchers tricked LLMs into giving them cocaine recipes by abusing role models for prompt injection

Researchers say that machine learning models cannot reliably distinguish between authorized and unauthorized input, ensuring that prompt injection will continue to present a threat until developers find new ways to have machine learning systems process inputs. AI models provide responses to user-supplied prompts. The problem is that AI models may receive adversarial prompts – directly from a user or indirectly from an ingested document – that tell the model to take action contrary to its built-i