Re:For AI to thrive, it must explain itself
by twblalock on Sunday February 18, 2018 @03:11PM
(#16408158)
Good luck explaining that to a judge who demands to know why the AI made the decisions that caused an accident, and what exactly the manufacturer is doing to prevent it from happening again.
Re:For AI to thrive, it must explain itself
by jwatte on Sunday February 18, 2018 @07:16PM
(#16409779)
There are tons of physical processes that aren't explainable.
Most current petrochemical plants have inner workings that are only half known, at best.
What are we doing about it? Modeling the failure, and engineering a solution that no longer fails in that situation.
Unit testing our way to robustness!
Re:For AI to thrive, it must explain itself
by JumpCrisscross on Sunday February 18, 2018 @09:23PM
(#16410319)
> Most current petrochemical plants have inner workings that are only half known, at best. What are we doing about it?
When these processes kill people we very much do somethint about them.
Re:For AI to thrive, it must explain itself
by afarrell on Sunday February 18, 2018 @07:05PM
(#16409732)
> Becauae there’s nothing to explain. The software is broken and needs to be fixed
The second statement kinda denies the first. If broken software causes a severe or expensive problem, people generally expect an explanation. That is what a post-mortem is generally for.
Becauae there’s nothing to explain. The software is broken and needs to be fixed, and if the problem is severe and the manufacturer knowingly tries to cover it up, that manufacturer is culpable of negligence.
The software has no more agency than a cruise control.