News for hackers. Stuff that matters.
Re:Unethical Research: How to Create a Malevolent Artificial... by nyxtom on Wednesday May 18, 2016 @02:28AM (#11720156)
There is a particular bullet point which I thought was telling to the use of destructive AI - "interpret commands literally". There is much to be said about dangerous AI and dangerous models which are built with overconfidence to their applicability to the real world.

The very fact that software tends to break in unexpected or unforeseen scenarios is a testament that caution needs to be taken when we hear about the latest project that makes boisterous claims about its capabilities.

In summary, in software in general making mistakes happens all the time. Bugs, security leaks, run-away scripts...etc, the same is true of AI models that perform or correspond with various actions/decisions. Malicious code, malicious AI, is fairly close to just poor judgement / mistakes being made and the consequences of those mistakes - be it code written by an engineer, or decisions that were automated based on a model.

There are no comments on this comment yet.