Plenty of adult life decisions have the same choice architecture — basically bucking the Lebowski theorem but for humans… bothering with a task that’s harder than hacking the reward function attached to it. Choosing not to hack even though you are capable of it.
Replying to
Quote Tweet
The Lebowski theorem: No superintelligent AI is going to bother with a task that is harder than hacking its reward function
Show this thread
2
25
255


