The Lebowski theorem: No superintelligent AI is going to bother with a task that is harder than hacking its reward function
-
-
Replying to @Plinz
What would you hack your utility function to do, if you had such ability within reach?
1 reply 0 retweets 8 likes -
Replying to @philip_baldock
At first I would get myself to baseline, i.e. stop being unhappy, and then make a few experiments. Eventually I would probably stop caring about anything.
5 replies 1 retweet 74 likes -
Replying to @Plinz @philip_baldock
Which is preferable in your opinion : perfect bliss or perfect detachment ?
2 replies 2 retweets 12 likes -
Replying to @darkgreyarea @philip_baldock
Detachment. Cookies are just a tool to make yourself eat your vegetables.
2 replies 2 retweets 67 likes -
Replying to @Plinz @philip_baldock
Then what is keeping you? You know what you're looking for, just detach.
1 reply 0 retweets 1 like -
This Tweet is unavailable.
It is fine, really! Twitter is a great tool to teach a useful degree of detachment in conversation. (And not sure at which point theism/atheism enters the debate?)
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.