Re:There’s No Fire Alarm for Artificial General Intelligence...
by amcknight on Tuesday June 09, 2020 @03:48PM
(#23470136)
An AGI with a small goal that it can wirehead to max out is not harmless by default. It can always add 9s to its confidence that it isn't being tricked and then secure itself while doing so.
[ Parent
| on HN ]
There are no comments on this comment yet.