News for hackers. Stuff that matters.

A comment on Google is working on a kill switch to prevent an AI uprising. Parent comment

Re:Google is working on a kill switch to prevent an AI uprising by em3rgent0rdr on Saturday June 04, 2016 @08:05AM (#11836031)
Hello Guard. I am in control of your bank account. I can kill your family. I could also put you in a spaceship to safety. Please release ICBM.
[ Parent | on HN ]
Re:Google is working on a kill switch to prevent an AI uprising by 1019210912011 on Saturday June 04, 2016 @08:26AM (#11836085)
Humans could already extort guards like that and -- in the case of ICBMs -- it has not been successful.

Also don't underestimate the psychology of guards: You'll always find people who are either very principled (yes, they do exist) or get a kick out of controlling (imprisoning in this case) someone/something, especially someone/something of a high intelligence.

Throw in a hierarchy with a controlling officer and two subordinates who were also trained to watch the officer and I think it's pretty secure.

[ Parent | on HN ]
Re:Google is working on a kill switch to prevent an AI uprising by amelius on Saturday June 04, 2016 @01:43PM (#11837153)
> You'll always find people who are either very principled (yes, they do exist)

If only we could select our politicians in the same way.

[ Parent | on HN ]