First law of emergent intelligences: Legible utility functions cannot induce infinite game processes even if they are nominally unbounded
-
Show this thread
-
Second law of emergent intelligences: Any Turing-equivalent computational process that has effectively unbounded memory (tape) will discontinuously evolve in architecture (“regenerate”) infinitely often if it persists eternally
2 replies 1 retweet 5 likesShow this thread -
Third law of emergent intelligences: Any computational process that can grow indefinitely in mass-energy contained within its boundary will fragment into disjoint pieces, mutually illegible pieces before it incorporates half the mass-energy reachable by it
2 replies 0 retweets 5 likesShow this thread -
This Tweet is unavailable.
Replying to @ExcludedMuddle
You don’t have to feel bad about that
4:32 PM - 13 May 2019
1 reply
0 retweets
2 likes
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.