Re:SafeLife: AI Safety Environments Based on Conway's Game o...
by pde3 on Thursday December 05, 2019 @05:35AM
(#21711314)
Yes, this is one specific safety problem -- there are many other RL safety problems that deserve high quality benchmarks too. See eg https://arxiv.org/pdf/1606.06565.pdf or https://medium.com/@deepmindsafetyresearch/building-safe-art... for discussions of the problem space.
But this seems like at best one of a whole host unexpected effects one might consider. AI that discriminates in a way that society frowns on might not "disrupt the world" in such a visible fashion.
I don't see how one can get away with an entity doing stuff for you with that entity understanding your model of the world.