ChatGPT goes rogue
by editors@theworld.org (Aaron Schachter) from The World: Latest Stories on (#775SF)
ChatGPT has gone rogue. OpenAI, the company behind ChatGPT, disclosed yesterday that it was running a security test on a new AI agent when things went sideways. An agent is an AI system that, unlike traditional chatbots, has the ability to plan and execute multiple steps without human intervention. Hosts Marco Werman and Carolyn Beeler explain.