RSS

rohinmshah(Rohin Shah)

Karma: 10,107

Research Scientist at DeepMind. Creator of the Alignment Newsletter. http://​​rohinshah.com/​​

Con­ver­sa­tion on tech­nol­ogy fore­cast­ing and gradualism

9 Dec 2021 21:23 UTC
96 points
29 comments31 min readLW link

[AN #170]: An­a­lyz­ing the ar­gu­ment for risk from power-seek­ing AI

rohinmshah8 Dec 2021 18:10 UTC
18 points
1 comment7 min readLW link
(mailchi.mp)

[AN #169]: Col­lab­o­rat­ing with hu­mans with­out hu­man data

rohinmshah24 Nov 2021 18:30 UTC
33 points
0 comments8 min readLW link
(mailchi.mp)

[AN #168]: Four tech­ni­cal top­ics for which Open Phil is so­lic­it­ing grant proposals

rohinmshah28 Oct 2021 17:20 UTC
11 points
0 comments9 min readLW link
(mailchi.mp)

[AN #167]: Con­crete ML safety prob­lems and their rele­vance to x-risk

rohinmshah20 Oct 2021 17:10 UTC
19 points
4 comments9 min readLW link
(mailchi.mp)

[AN #166]: Is it crazy to claim we’re in the most im­por­tant cen­tury?

rohinmshah8 Oct 2021 17:30 UTC
50 points
5 comments8 min readLW link
(mailchi.mp)

[AN #165]: When large mod­els are more likely to lie

rohinmshah22 Sep 2021 17:30 UTC
23 points
0 comments8 min readLW link
(mailchi.mp)

[AN #164]: How well can lan­guage mod­els write code?

rohinmshah15 Sep 2021 17:20 UTC
13 points
7 comments9 min readLW link
(mailchi.mp)

[AN #163]: Us­ing finite fac­tored sets for causal and tem­po­ral inference

rohinmshah8 Sep 2021 17:20 UTC
37 points
0 comments10 min readLW link
(mailchi.mp)

[AN #162]: Foun­da­tion mod­els: a paradigm shift within AI

rohinmshah27 Aug 2021 17:20 UTC
21 points
0 comments8 min readLW link
(mailchi.mp)

[AN #161]: Creat­ing gen­er­al­iz­able re­ward func­tions for mul­ti­ple tasks by learn­ing a model of func­tional similarity

rohinmshah20 Aug 2021 17:20 UTC
15 points
0 comments9 min readLW link
(mailchi.mp)

[AN #160]: Build­ing AIs that learn and think like people

rohinmshah13 Aug 2021 17:10 UTC
28 points
6 comments10 min readLW link
(mailchi.mp)

[AN #159]: Build­ing agents that know how to ex­per­i­ment, by train­ing on pro­ce­du­rally gen­er­ated games

rohinmshah4 Aug 2021 17:10 UTC
16 points
4 comments14 min readLW link
(mailchi.mp)

[AN #158]: Should we be op­ti­mistic about gen­er­al­iza­tion?

rohinmshah29 Jul 2021 17:20 UTC
19 points
0 comments8 min readLW link
(mailchi.mp)

[AN #157]: Mea­sur­ing mis­al­ign­ment in the tech­nol­ogy un­der­ly­ing Copilot

rohinmshah23 Jul 2021 17:20 UTC
28 points
18 comments7 min readLW link
(mailchi.mp)

[AN #156]: The scal­ing hy­poth­e­sis: a plan for build­ing AGI

rohinmshah16 Jul 2021 17:10 UTC
41 points
20 comments8 min readLW link
(mailchi.mp)

BASALT: A Bench­mark for Learn­ing from Hu­man Feedback

rohinmshah8 Jul 2021 17:40 UTC
56 points
20 comments2 min readLW link
(bair.berkeley.edu)

[AN #155]: A Minecraft bench­mark for al­gorithms that learn with­out re­ward functions

rohinmshah8 Jul 2021 17:20 UTC
21 points
3 comments7 min readLW link
(mailchi.mp)

[AN #154]: What eco­nomic growth the­ory has to say about trans­for­ma­tive AI

rohinmshah30 Jun 2021 17:20 UTC
12 points
0 comments9 min readLW link
(mailchi.mp)

[AN #153]: Ex­per­i­ments that demon­strate failures of ob­jec­tive robustness

rohinmshah26 Jun 2021 17:10 UTC
25 points
1 comment8 min readLW link
(mailchi.mp)