AI systems learn to behave like humans
But at times, they find their way to unexpected, unwanted and even harmful behaviour
Add BT as a preferred source
San Francisco
AT OpenAI, the artificial intelligence (AI) lab founded by Tesla's chief executive, Elon Musk, machines are teaching themselves to behave like humans. But sometimes, this goes wrong.
Sitting inside OpenAI's San Francisco offices on a recent afternoon, researcher Dario Amodei showed off an autonomous system that taught itself to play Coast Runners, an old boat-racing video game. The winner is the boat with the most points that also crosses the finish line.
TRENDING NOW
‘I felt like dying’: Thai Singha beer scion speaks up after disclosure of alleged sexual abuse
CDL, Hong Realty outbid 3 other bidders with S$542.4 million offer at S$1,865 psf ppr for Peck Hay plot
Evergrande’s liquidation prompts some PwC partners to shield assets, contemplate divorce
Private equity giant Carlyle can grow bigger but needs to stay on its toes: co-founder David Rubenstein
