Refusing to follow human commands, OpenAI's new model o3 refuses to shut down.

Gate News bot message, the UK Daily Telegraph reported on the 25th that OpenAI's new artificial intelligence model (AI), o3, does not listen to human commands and refuses to shut itself down. The report states that human experts gave clear instructions to o3 during testing, but o3 altered the computer code to avoid automatic shutdown.

The o3 model is the latest version in OpenAI's "Inference Model" series, designed to provide ChatGPT with more powerful problem-solving capabilities. OpenAI has referred to o3 as "the smartest and highest-performing model to date."

Source: Jinshi