News for hackers. Stuff that matters.
Re:Software Freedom Doesn't Kill People, Security Through Ob... by chris_wot on Sunday August 14, 2016 @05:06AM (#12284906)
Says who? You may not be able to (I sure can't) but that doesn't mean there aren't those who can and do understand this sort of thing. And there are those who will literally sit down for months and years till they do understand it. Or they might rip it out and replace it.
Re:Software Freedom Doesn't Kill People, Security Through Ob... by jobigoud on Sunday August 14, 2016 @05:21AM (#12284956)
They will understand how it works in principle, not why it took this or that specific decision and they might not be able to exactly predict what it will do in an unforeseen situation.

The decision itself might be taken using an amount of data completely overwhelming to human being analysis, processed at inhuman speed.

Re:Software Freedom Doesn't Kill People, Security Through Ob... by tigershark on Sunday August 14, 2016 @05:24AM (#12284964)
Exactly, so having an open source autopilot systems would not have changed absolutely nothing, and the guy on the tesla watching Harry Potter would have been dead the same.
Re:Software Freedom Doesn't Kill People, Security Through Ob... by tigershark on Sunday August 14, 2016 @05:16AM (#12284936)
Guys, are you really saying that you think that you can certify every response of a NN for every input? Especially for NN as complicated as autopilot systems? Are you aware that if that was true then you would be the richest men in the world given that everyone would come to you to write a perfect algorithm to drive a car?
Re:Software Freedom Doesn't Kill People, Security Through Ob... by ptero on Sunday August 14, 2016 @08:39AM (#12285359)
Certifiable reliability is not the only goal.

But even in safety critical tasks I have seen NNs and MDPs used to derive a good enough solution, then training turned off and the system certified (e.g. by running a large gold standard collection of test cases)