What does getting this wrong entail? Derailing AI research or failing in many other disciplines?
-
-
Replying to @niftierideology
Getting clear about this is an enabling technology for “meta-rationality” or “stage 5”: understanding how >
1 reply 0 retweets 0 likes -
Replying to @Meaningness @niftierideology
all systems are qualitatively inaccurate, not just quantitatively.
1 reply 0 retweets 5 likes -
Replying to @Meaningness
So, does this imply that one needs to be able to choose the right kind of map (representation) for any given problem domain?
1 reply 0 retweets 0 likes -
Replying to @niftierideology
Yes, but it also implies that no representation is actually qualitatively accurate for its domain, either.
1 reply 0 retweets 0 likes -
Replying to @Meaningness
Doesn't that depend on the complexity of the domain? E.g. tic-tac-toe board probably has accurate reps. Sorry if pedantic
1 reply 0 retweets 0 likes -
Replying to @niftierideology
yes, that’s right. Ttt is basically math, and math is the exception here
1 reply 0 retweets 0 likes -
Replying to @Meaningness
Would you agree that a quark-by-quark representation of the universe could be true, even if it was useless for cognition?
1 reply 0 retweets 1 like -
-
Replying to @Meaningness
It's obviously not possible to actually have this. I'm just trying to see if we have similar ontologies, I guess.
1 reply 0 retweets 0 likes
Not sure! I’m skeptical of impossible things (like full representation of quantum universe) as ideals.
-
-
Replying to @Meaningness
Yeah, like some things are unknowable by definition (e.g. Both momentum and position of a particle)—"holes" in the territory.
0 replies 0 retweets 1 likeThanks. 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.