why does preparing for a paperclip maximizer assume Bayesianism?
-
-
Replying to @teleonomist
You are correct -- it doesn't assume Bayesianism -- but this doesn't invalidate my central point, which is that we don't know what it will look like.
1 reply 0 retweets 0 likes -
Replying to @simpolism @teleonomist
thinking about ai safety doesn't require knowing what it looks like, just that it intelligently pursues goals and isn't human
1 reply 1 retweet 4 likes -
i'd be interested if you have a specific example of an ai safety argument that depends on knowing the ai's architecture
1 reply 1 retweet 2 likes -
as for the aliens below the moon thing: artificial general intelligence seems possible because humans are possible
1 reply 1 retweet 3 likes -
and it would help achieve a lot of different goals, which means people will be motivated to try to invent it
1 reply 1 retweet 3 likes -
also, sometimes when you don't know what a thing will be like there are a few possibilities and you can study each of them
1 reply 1 retweet 2 likes -
Replying to @VesselOfSpirit @teleonomist
simpolism Retweeted sol
1) re "intelligent thing risk" my new fave take is https://twitter.com/fire__exit/status/1011762984136445953 … 2) humans took millennia to appear and were shaped by long-term environments. we're motivated to make virtual humans but it's gonna be messy & I think Moore's Law is over 3) "study"?
"sound alarm"? 
simpolism added,
1 reply 0 retweets 1 like -
I think a major point I deeply disagree with is that I don't think Moore's Law will hold. A lot of AI-related fear seems to assume a continuous creep in computing power. How would AI-risk research change if we were forever stuck with the computing power of our current hardware?
3 replies 0 retweets 0 likes -
Replying to @simpolism @teleonomist
i hear moore's law is still going if you measure it in computing power per dollar
1 reply 0 retweets 0 likes
also apparently more gains have come from better algorithms than hardwarehttps://aiimpacts.org/trends-in-algorithmic-progress/ …
-
-
Replying to @VesselOfSpirit @teleonomist
Computing power alone isn't the entire story, density matters significantly for information processing. But yes, my assumption is that algorithms would be vastly more important than the hardware.
0 replies 0 retweets 0 likesThanks. Twitter will use this to make your timeline better. UndoUndo
-
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.