@abramdemski to try and work one out, or else show why it’s impossible.
-
-
Replying to @Meaningness
@Meaningness I keep meaning to come back to this, and now realize it's been the larger part of a year :p1 reply 0 retweets 0 likes -
Replying to @abramdemski
@Meaningness I'm a coathor on this preprint: http://arxiv.org/abs/1510.03370 but there's a revised version now, which I could email you1 reply 0 retweets 2 likes -
Replying to @abramdemski
@abramdemski Thanks! To be honest, it’s probably more technical than I would want to read at the moment. Glad you are working on it though!3 replies 0 retweets 0 likes -
Replying to @Meaningness
Alright, you *have* to look at this one, I insist! Big result, good non-technical summary included.https://intelligence.org/2016/09/12/new-paper-logical-induction/ …
1 reply 0 retweets 1 like -
Replying to @abramdemski
Unconvinced there’s a big result. “The logical induction algorithm that we provide is theoretical rather than practical.”
2 replies 0 retweets 1 like -
Replying to @Meaningness @abramdemski
I prodded some of the authors until one linked empirical stuff they've done. https://github.com/GallagherCommaJack/markets …
2 replies 0 retweets 2 likes -
Replying to @othercriteria @abramdemski
Can you summarize? (I’m not motivated to do work on this unless/until someone convinces me it’s exciting)
2 replies 0 retweets 0 likes -
Replying to @Meaningness @abramdemski1 reply 0 retweets 2 likes
-
Replying to @othercriteria @abramdemski
Thanks, have read now! Better explanation than authors’.
1 reply 0 retweets 0 likes
Mildly increased my subjective probability estimate that it’s interesting as logic;
-
-
significantly strengthened belief that it’s irrelevant to AI
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.