AI kill switch may not stop superintelligent AI, says godfather of AI

Geoffrey Hinton and other AI experts doubt that a kill switch would work against a superintelligent system: it could bypass control or persuade operators not to press the button. At Anthropic and OpenAI, they believe the kill switch is just one layer of safety alongside testing and external evaluation.

• Hinton: kill switch won't work against superintelligent AI in the long term
• Nate Soares: shutdown works while AI is tied to a physical location
• Jack Clark proposed independent third-party verification of kill switch
• Sam Altman: no single 'magic button' for AI safety exists