RSS

sbenthall

Karma: 365

Re­ward Hack­ing from a Causal Perspective

21 Jul 2023 18:27 UTC
29 points
4 comments7 min readLW link

In­cen­tives from a causal perspective

10 Jul 2023 17:16 UTC
27 points
0 comments6 min readLW link

Causal­ity: A Brief Introduction

20 Jun 2023 15:01 UTC
48 points
18 comments6 min readLW link

In­tro­duc­tion to Towards Causal Foun­da­tions of Safe AGI

12 Jun 2023 17:55 UTC
67 points
6 comments4 min readLW link

Don’t Fear the Reaper: Re­fut­ing Bostrom’s Su­per­in­tel­li­gence Argument

sbenthall1 Mar 2017 14:28 UTC
9 points
20 comments1 min readLW link

Au­ton­omy, util­ity, and de­sire; against con­se­quen­tial­ism in AI design

sbenthall3 Dec 2014 17:34 UTC
7 points
5 comments3 min readLW link

more on pre­dict­ing agents

sbenthall8 Nov 2014 6:43 UTC
1 point
11 comments2 min readLW link

pre­dic­tion and ca­pac­ity to represent

sbenthall4 Nov 2014 6:09 UTC
−9 points
20 comments1 min readLW link

AI Tao

sbenthall21 Oct 2014 1:15 UTC
−17 points
3 comments1 min readLW link

What is op­ti­miza­tion power, for­mally?

sbenthall18 Oct 2014 18:37 UTC
17 points
16 comments2 min readLW link

Depth-based su­per­con­trol­ler ob­jec­tives, take 2

sbenthall24 Sep 2014 1:25 UTC
1 point
24 comments7 min readLW link

Every­body’s talk­ing about ma­chine ethics

sbenthall17 Sep 2014 17:20 UTC
24 points
16 comments1 min readLW link

Pro­posal: Use log­i­cal depth rel­a­tive to hu­man his­tory as ob­jec­tive func­tion for superintelligence

sbenthall14 Sep 2014 20:00 UTC
10 points
23 comments3 min readLW link

In­tel­li­gence ex­plo­sion in or­ga­ni­za­tions, or why I’m not wor­ried about the singularity

sbenthall27 Dec 2012 4:32 UTC
13 points
187 comments3 min readLW link