RSS

abramdemski(Abram Demski)

Karma: 11,418

The Parable of Pre­dict-O-Matic

abramdemski15 Oct 2019 0:49 UTC
245 points
41 comments14 min readLW link5 nominations4 reviews

Align­ment Re­search Field Guide

abramdemski8 Mar 2019 19:57 UTC
199 points
9 comments17 min readLW link2 nominations2 reviews

The Zet­telkas­ten Method

abramdemski20 Sep 2019 13:15 UTC
193 points
77 comments42 min readLW link2 nominations3 reviews

Embed­ded Agents

29 Oct 2018 19:53 UTC
185 points
41 comments1 min readLW link

Mis­takes with Con­ser­va­tion of Ex­pected Evidence

abramdemski8 Jun 2019 23:07 UTC
159 points
21 comments12 min readLW link2 nominations1 review

An Un­trol­lable Math­e­mat­i­cian Illustrated

abramdemski20 Mar 2018 0:00 UTC
150 points
38 comments1 min readLW link

Rad­i­cal Probabilism

abramdemski18 Aug 2020 21:14 UTC
146 points
46 comments35 min readLW link

Most Pri­soner’s Dilem­mas are Stag Hunts; Most Stag Hunts are Schel­ling Problems

abramdemski14 Sep 2020 22:13 UTC
123 points
31 comments10 min readLW link

Selec­tion vs Control

abramdemski2 Jun 2019 7:01 UTC
122 points
25 comments11 min readLW link2 nominations2 reviews

The Bayesian Tyrant

abramdemski20 Aug 2020 0:08 UTC
116 points
14 comments6 min readLW link

An Ortho­dox Case Against Utility Functions

abramdemski7 Apr 2020 19:18 UTC
113 points
49 comments8 min readLW link

Ro­bust Delegation

4 Nov 2018 16:38 UTC
108 points
10 comments1 min readLW link

De­ci­sion Theory

31 Oct 2018 18:41 UTC
105 points
38 comments1 min readLW link

“Zero Sum” is a mis­nomer.

abramdemski30 Sep 2020 18:25 UTC
105 points
35 comments6 min readLW link

Sub­sys­tem Alignment

6 Nov 2018 16:16 UTC
99 points
12 comments1 min readLW link

[Question] What makes peo­ple in­tel­lec­tu­ally ac­tive?

abramdemski29 Dec 2018 22:29 UTC
93 points
63 comments1 min readLW link

Prob­a­bil­ity vs Likelihood

abramdemski10 Nov 2020 21:28 UTC
92 points
10 comments12 min readLW link

Be­com­ing Unusu­ally Truth-Oriented

abramdemski3 Jan 2020 1:27 UTC
88 points
20 comments10 min readLW link

Ma­chine Learn­ing Anal­ogy for Med­i­ta­tion (illus­trated)

abramdemski28 Jun 2018 22:51 UTC
85 points
48 comments1 min readLW link

Embed­ded World-Models

2 Nov 2018 16:07 UTC
85 points
16 comments1 min readLW link