Google tackles challenge of building an honest robot
Researchers' thinking is that the robots' goals must be aligned with those of their human owners
Add BT as a preferred source
DeeperDive is a beta AI feature. Refer to full articles for the facts.
San Francisco
GOOGLE can see a future where robots help us unload the dishwasher and sweep the floor. The challenge is making sure they don't inadvertently knock over a vase -- or worse - while doing so.
Researchers at Alphabet Inc unit Google, along with collaborators at Stanford University, the University of California at Berkeley, and OpenAI - an artificial intelligence development company backed by Elon Musk - have some ideas about how to design robot minds that won't lead to undesirable consequences for the people they serve. They published a technical paper on Tuesday outlining their thinking.
Share with us your feedback on BT's products and services
TRENDING NOW
Ministry of Home Affairs Permanent Secretary Pang Kin Keong to retire
Shelving S$5 billion office redevelopment plan proved ‘wise’ as geopolitical risks mount: OCBC chairman
Richard Eu on how core values, customers keep Singapore’s TCM chain Eu Yan Sang relevant
China pips the US if Asean is forced to choose, but analysts warn against reading it like a sports result
