Davis’s review of Bostrom’s Superintelligence (dated 23 October 2014) says that a computer or robot with any tendency toward self-preservation should have an off switch it cannot block, and that this is easily done because we are building them.
One recorded claim. The claim panel gives its qualification, the source passages with their place in each source, and how it was checked.
What it connects
Ethical Guidelines for A Superintelligence → articulates → Advanced AI can be kept under control by design