The intuition that machines cannot be as ethical as humans is likely incorrect. Ethics is the systematic resolution of conflicts of interest under conditions of shared purpose. Ethics is not irrational. There is no reason to assume that machines cannot be more ethical than us.
-
-
Replying to @Plinz
The arguments made e.g. by Nick Bostrom is rather that they could lack deeper understanding of their actions, consequences and have different priories (produce paperclips at all costs), what possibly leads to rational but unethical actions.
1 reply 0 retweets 1 like -
Replying to @tymwol
Interesting question. Do you think that "autistic AI", i.e. an AI that only optimizes for a low level reward function, will outperform "sustainable AI", i.e. one that maximizes its expectation horizon?
2 replies 1 retweet 1 like -
Replying to @Plinz
I don't fully agree with Bostrom's arguments, but clearly, it would be much easier to build AI capable of unethical actions, then one capable of ethical reasoning. Same as it is easier to build self-driving car, then safe-driving car.
1 reply 0 retweets 1 like -
Replying to @tymwol
Do you think that the market for self-driving cars is larger than the market for safe-driving cars?
1 reply 0 retweets 0 likes -
Replying to @Plinz
I'm just saying that building ethically un-aware AI could be easier and so, more tempting. Moreover, the question is if AI will ever be intelligent enough for ethical reasoning?
1 reply 0 retweets 0 likes
That may be true for individual developers, but not for a world with tens of thousands of developers, with funding dependent largely on expected reward for organizations.
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.