[SEQ RERUN] GAZP vs. GLUT
Today’s post, GAZP vs. GLUT was originally published on 07 April 2008. A summary (taken from the LW wiki):
Fleshes out the generalized anti-zombie principle a bit more, and describes the game “follow-the-improbability”.
Discuss the post here (rather than in the comments to the original post).
This post is part of the Rerunning the Sequences series, where we’ll be going through Eliezer Yudkowsky’s old posts in order so that people who are interested can (re-)read and discuss them. The previous post was The Generalized Anti-Zombie Principle, and you can use the sequence_reruns tag or rss feed to follow the rest of the series.
Sequence reruns are a community-driven effort. You can participate by re-reading the sequence post, discussing it here, posting the next day’s sequence reruns post, or summarizing forthcoming articles on the wiki. Go here for more details, or to have meta discussions about the Rerunning the Sequences series.
“Follow the improbability” is tantalizingly close, but not quite the right answer to the GLUT puzzle, I think. The right game seems to be “follow the K-complexity”. The simplest algorithm that generates the GLUT is probably similar to a conscious human, so if you subscribe to the universal prior, then seeing a GLUT implies with high probability that there’s a human nearby.
Well spotted. “Follow the improbability” is enough of a clue to get the right answer (“a human made it”), though.
And he still doesn’t actually state the GAZP. Is there a statement of it anywhere? I see there isn’t one on the wiki either.
I think the GAZP is probably something along the lines of “Anything that says it’s Bob, for reasons that is similar to the reasons Bob would say that he is Bob, is in fact Bob.” Along this principle, we could upload you, and as long as the computer is running algorithms that are isomorphic to the “algorithms” run by your brain, that copy in the computer is you.