’You could say ‘guarantee no harm’. But a self-driving car that followed Asimov’s first…

’You could say ‘guarantee no harm’. But a self-driving car that followed Asimov’s first law would never leave the garage.’

@UCBerkeley’s Stuart Russell tells #RadioDavos how to achieve ‘human-compatible’ AI, with @KayFButterfield @RobinPomeroyEd

https://t.co/MN2f80r0O3 https://t.co/I1BKCcVqY5