RSS

Stuart_Armstrong

Karma: 20,597 (LW), 228 (AF)
AllPostsComments
NewTop
Page 1

Par­tial prefer­ences and models

Stuart_Armstrong
19 Mar 2019 16:29 UTC
13 points
4 comments2 min readLW link

Com­bin­ing in­di­vi­d­ual prefer­ence util­ity functions

Stuart_Armstrong
14 Mar 2019 14:14 UTC
11 points
0 comments1 min readLW link

Mys­ter­ies, iden­tity, and prefer­ences over non-rewards

Stuart_Armstrong
14 Mar 2019 13:52 UTC
14 points
1 comment1 min readLW link

A the­ory of hu­man values

Stuart_Armstrong
13 Mar 2019 15:22 UTC
26 points
12 comments7 min readLW link

Ex­am­ple pop­u­la­tion ethics: or­dered dis­counted utility

Stuart_Armstrong
11 Mar 2019 16:10 UTC
14 points
13 comments1 min readLW link

Smooth­min and per­sonal identity

Stuart_Armstrong
8 Mar 2019 15:16 UTC
20 points
0 comments1 min readLW link

Prefer­ences in sub­pieces of hi­er­ar­chi­cal systems

Stuart_Armstrong
6 Mar 2019 15:18 UTC
11 points
0 comments3 min readLW link

mAIry’s room: AI rea­son­ing to solve philo­soph­i­cal problems

Stuart_Armstrong
5 Mar 2019 20:24 UTC
34 points
6 comments6 min readLW link

Par­tial prefer­ences needed; par­tial prefer­ences sufficient

Stuart_Armstrong
5 Mar 2019 19:39 UTC
27 points
5 comments3 min readLW link

Find­ing the variables

Stuart_Armstrong
4 Mar 2019 19:37 UTC
28 points
1 comment4 min readLW link

Syn­tax vs se­man­tics: alarm bet­ter ex­am­ple than thermostat

Stuart_Armstrong
4 Mar 2019 12:43 UTC
12 points
1 comment3 min readLW link

De­cel­er­at­ing: laser vs gun vs rocket

Stuart_Armstrong
18 Feb 2019 23:21 UTC
22 points
16 comments3 min readLW link

Hu­mans in­ter­pret­ing humans

Stuart_Armstrong
13 Feb 2019 19:03 UTC
10 points
1 commentLW link

An­chor­ing vs Taste: a model

Stuart_Armstrong
13 Feb 2019 19:03 UTC
11 points
0 commentsLW link

Would I think for ten thou­sand years?

Stuart_Armstrong
11 Feb 2019 19:37 UTC
25 points
12 commentsLW link

“Nor­ma­tive as­sump­tions” need not be complex

Stuart_Armstrong
11 Feb 2019 19:03 UTC
11 points
0 commentsLW link

Wire­head­ing is in the eye of the beholder

Stuart_Armstrong
30 Jan 2019 18:23 UTC
25 points
8 commentsLW link

Can there be an in­de­scrib­able hel­l­world?

Stuart_Armstrong
29 Jan 2019 15:00 UTC
18 points
19 commentsLW link

How much can value learn­ing be dis­en­tan­gled?

Stuart_Armstrong
29 Jan 2019 14:17 UTC
22 points
29 commentsLW link

A small ex­am­ple of one-step hypotheticals

Stuart_Armstrong
28 Jan 2019 16:12 UTC
14 points
0 commentsLW link