A bipartisan group in Congress and Gov. Gavin Newsom of California have floated ideas for building a mechanism that would instantly power down an A.I. system. Only no one really knows how.
Creating a kill switch, a metaphorical big red button that could be pressed in an emergency, is harder than many policymakers assume. “There often isn’t one plug you can pull,” said one A.I. researcher.
Some people worry that connecting A.I. agents to the internet or vital infrastructure will wreak havoc in unexpected ways, while others worry that researchers will soon develop A.I. systems that have agency.
“Alignment” is the science of teaching A.I. to do what is in line with human preferences, ethics and judgment. But, at times, the systems have gone rogue.
When an A.I. system starts acting of its own accord, engages in unsafe behavior or ignores the wishes of humans, the behavior is known as misalignment.
Login
