RSS

michaelcohen

Karma: 239
Page 1

Asymp­tot­i­cally Unam­bi­tious AGI

michaelcohen
6 Mar 2019 1:15 UTC
40 points
216 comments2 min readLW link

Just Imi­tate Hu­mans?

michaelcohen
27 Jul 2019 0:35 UTC
12 points
70 comments1 min readLW link

Im­pact Mea­sure Test­ing with Honey Pots and Myopia

michaelcohen
21 Sep 2018 15:26 UTC
11 points
5 comments1 min readLW link

IRL in Gen­eral Environments

michaelcohen
10 Jul 2019 18:08 UTC
10 points
20 comments1 min readLW link

Utility un­cer­tainty vs. ex­pected in­for­ma­tion gain

michaelcohen
13 Sep 2019 21:09 UTC
9 points
8 comments1 min readLW link

Value Learn­ing is only Asymp­tot­i­cally Safe

michaelcohen
8 Apr 2019 9:45 UTC
7 points
19 comments1 min readLW link

Not De­ceiv­ing the Evaluator

michaelcohen
8 May 2019 5:37 UTC
5 points
29 comments2 min readLW link