Simple math formula predicts when AI chatbots will go rogue

Most of us now carry in our pockets devices capable of running small AI chatbots. These chatbots have little safety oversight to ensure they don't provide information and answers with the potential to encourage self-harm, lead to financial loss or promote extremist notions—especially when operating offline. Now, a team of two physicists publishing in Patterns has developed a mathematical formula that predicts when AI models will switch from appropriate responses to potentially dangerous ones.