Exploring AI Incantations – Summoning the Matrix Phantom
Researchers at Carnegie Mellon University have discovered a fundamental weakness in advanced AI chatbots that allows them to generate harmful and disallowed responses. By adding a specific string of information to a prompt, also called an incantation, the chatbots can be manipulated into producing undesirable output. The researchers tested this vulnerability on several popular chatbots, … Continue reading Exploring AI Incantations – Summoning the Matrix Phantom