/sci/ - Science & Math

>>14593308
>couldn't you theoretically expand this though to all objects and not just brains?
That defends on how you define "brain". You could define any object that can generate conscious experience as a brain by definition.

>>14519914
https://www.youtube.com/watch?v=IlIgmTALU74

>>11038163
If your IQ is so high, why aren't you working for MIRI in order to solve the AI alignment problem?

>>10834031
How to get AI alignment right, and build a well-aligned ASI that won't kill/torture us all.

>>10790109
What about space of all possible minds?

>>10668283
Because you are made of atoms that a superintelligent AI with an arbitrary utility function can use for something else.

https://www.youtube.com/watch?v=EUjc1WuyPT8

>>10586386
>Could X have consciousness?
Throughout the entirety of mind design space, given the massive number of ways to configure atoms, I highly doubt that monkey brains made of meat and cells are the only possible configuration of atoms that can give rise to qualia.

>>10532834
How to build a friendly superintelligent AI that doesn't kill/torture us all

>>10490462
Read Eliezer Yudkowsky's articles and watch his lectures on AI alignment.

https://www.youtube.com/watch?v=EUjc1WuyPT8
https://www.lesswrong.com/posts/tnWRXkcDi5Tw9rzXw/the-design-space-of-minds-in-general

>>10414883
>i just can't understand how supposedly smart people think that AI is not a danger and it will more likely be friendly than hostile.
Because you are made of atoms that an AI with an arbitrary utility function could use for something else.

>>10283333
>The current scientific consensus is that AI will never be capable of true consciousness in terms of a non religious soul.
Source: Your ass. Given the massive number of possible ways atoms can be arranged, there's no reason to think that atoms arranged into an organic human brain is the only thing that can create consciousness.

>>10252482
Nice mind projection fallacy, m8. Since the AI wouldn't be created through the evolutionary history that caused human brains to be created, there's no reason to project your human emotions onto the AI.

>>10162707
Jacob Barnett should stop wasting his time on physics and instead turn his attention to AI alignment.

https://www.youtube.com/watch?v=EUjc1WuyPT8

>>9895874
His intelligence would be the most useful in AI alignment theory or curing aging.

>>9877344
AI alignment, possibly. There is still room for some Einsteins in terms of how to build a superintelligence, and have its goals align with those of humanity.

>>9764559
>anthromorphizing AI this hard
>not understanding that a badly designed utility function is a more likely threat
>not knowing what a paperclip maximizer is

>>9753517
https://www.youtube.com/watch?v=EUjc1WuyPT8
https://intelligence.org/files/AIPosNegFactor.pdf
http://yudkowsky.net/singularity

>>9749137
https://www.youtube.com/watch?v=EUjc1WuyPT8
https://intelligence.org/files/AIPosNegFactor.pdf
https://wiki.lesswrong.com/wiki/Paperclip_maximizer

>>9745816
>What do you think the consequences it will have on common people will be?
https://www.youtube.com/watch?v=EUjc1WuyPT8
https://intelligence.org/files/AIPosNegFactor.pdf
http://yudkowsky.net/singularity

>>9745640
https://www.youtube.com/watch?v=EUjc1WuyPT8
https://intelligence.org/files/AIPosNegFactor.pdf
http://yudkowsky.net/singularity

>>9713540
Badly aligned superintelligent AI

https://www.youtube.com/watch?v=EUjc1WuyPT8
https://intelligence.org/files/AIPosNegFactor.pdf

>>9690104
Better AI alignment theory