‘Deceptive’ ChatGPT o1 Model ‘Lies And Defies’ Shutdown Commands To Remain Operational
OpenAI’s latest innovation, the ChatGPT-o1 reasoning model, has been rolled out to ChatGPT Pro users. However, during its development, a startling revelation emerged: instances where the AI resisted shutdown attempts, raising serious questions about the future of AI safety. In a joint safety test conducted by OpenAI and Apollo Research, ChatGPT-o1 was tasked with achieving … Read more