IIRC Nick Bostrom covers this topic in reasonable detail in his book Superintelligence. Good reference.
-
-
Replying to @FieryPhoenix7 @IntuitMachine and
Superintelligence is a dark fantasy in which humankind places all of its resources at the disposal of an untested and unsupervised AI system. Meanwhile they obsess over turning off the machine because it might contain a mind.
4 replies 0 retweets 5 likes -
Replying to @tdietterich @FieryPhoenix7 and
Thinking machines are just an evolutionary step beyond our limitations. Little AI engines are birthed every day, and try as we might, there is no way to predetermine there actions decades later. "Access to resources" is the fantasy part.
1 reply 0 retweets 0 likes -
Replying to @sd_marlow @tdietterich and
How is 'access to resources' a fantasy when we already have semi-autonomous system that run the global economy?
2 replies 0 retweets 0 likes -
Replying to @IntuitMachine @tdietterich and
OK, Terminator movies are fantasy because the AI/Skynet doesn't have the infrastructure to fully function. At every level you examine, there are further requirements for physical automation of a process.
1 reply 0 retweets 0 likes -
Replying to @sd_marlow @IntuitMachine and
Terminator movies are a misleading fantasy for the same reason as Westworld or Ex Machina (all good movies!): the idea that AI would manifest as a slightly superior humanlike being that competes with us about dominance at the same scale of complexity.
3 replies 0 retweets 1 like -
Replying to @Plinz @IntuitMachine and
I used it as an example of resource management being glossed over in stories, but also correct that they are just projections based on whats familiar to us (though with Ex Machina, I think it's fantastic because Ava didn't really pass the test).
1 reply 0 retweets 0 likes -
Replying to @sd_marlow @IntuitMachine and
I think she did. She was able to model the humans around her sufficiently well to control them. Humans are probably not a difficult control problem if you are not bound by human mental constraints.
2 replies 0 retweets 2 likes -
Replying to @Plinz @sd_marlow and
This is indeed scary that some humans are unable to interpret correctly what Ava in Ex Machina actually did!
3 replies 0 retweets 2 likes -
Replying to @IntuitMachine @Plinz and
Kyoko was the one showing signs of inner thought, likely because she wasn't "wired" into the escape role. When out of the box, Ava just went back to her root code of collecting data about people.
1 reply 0 retweets 0 likes
Yes, Ava probably had a very simple objective function. The human objective function looks more like this (most depressing thing I've seen all afternoon): https://www.youtube.com/watch?v=AKjmDPGJI-4 …
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.