Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
Stuart_Armstrong
(Stuart Armstrong)
Karma:
15,386
All
Posts
Comments
New
Top
Old
Page
1
Connecting the good regulator theorem with semantics and symbol grounding
Stuart_Armstrong
4 Mar 2021 14:35 UTC
9
points
0
comments
2
min read
LW
link
Cartesian frames as generalised models
Stuart_Armstrong
16 Feb 2021 16:09 UTC
19
points
0
comments
5
min read
LW
link
Generalised models as a category
Stuart_Armstrong
16 Feb 2021 16:08 UTC
12
points
5
comments
4
min read
LW
link
Counterfactual control incentives
Stuart_Armstrong
21 Jan 2021 16:54 UTC
20
points
8
comments
9
min read
LW
link
Short summary of mAIry’s room
Stuart_Armstrong
18 Jan 2021 18:11 UTC
26
points
2
comments
4
min read
LW
link
Syntax, semantics, and symbol grounding, simplified
Stuart_Armstrong
23 Nov 2020 16:12 UTC
25
points
4
comments
9
min read
LW
link
The ethics of AI for the Routledge Encyclopedia of Philosophy
Stuart_Armstrong
18 Nov 2020 17:55 UTC
45
points
8
comments
1
min read
LW
link
Extortion beats brinksmanship, but the audience matters
Stuart_Armstrong
16 Nov 2020 21:13 UTC
27
points
15
comments
4
min read
LW
link
Humans are stunningly rational and stunningly irrational
Stuart_Armstrong
23 Oct 2020 14:13 UTC
21
points
4
comments
2
min read
LW
link
Knowledge, manipulation, and free will
Stuart_Armstrong
13 Oct 2020 17:47 UTC
32
points
15
comments
3
min read
LW
link
Dehumanisation *errors*
Stuart_Armstrong
23 Sep 2020 9:51 UTC
13
points
0
comments
1
min read
LW
link
Anthropomorphisation vs value learning: type 1 vs type 2 errors
Stuart_Armstrong
22 Sep 2020 10:46 UTC
16
points
10
comments
1
min read
LW
link
Technical model refinement formalism
Stuart_Armstrong
27 Aug 2020 11:54 UTC
9
points
0
comments
6
min read
LW
link
Model splintering: moving from one imperfect model to another
Stuart_Armstrong
27 Aug 2020 11:53 UTC
41
points
9
comments
33
min read
LW
link
Learning human preferences: black-box, white-box, and structured white-box access
Stuart_Armstrong
24 Aug 2020 11:42 UTC
23
points
9
comments
6
min read
LW
link
AI safety as featherless bipeds *with broad flat nails*
Stuart_Armstrong
19 Aug 2020 10:22 UTC
35
points
1
comment
1
min read
LW
link
Learning human preferences: optimistic and pessimistic scenarios
Stuart_Armstrong
18 Aug 2020 13:05 UTC
26
points
6
comments
6
min read
LW
link
Strong implication of preference uncertainty
Stuart_Armstrong
12 Aug 2020 19:02 UTC
20
points
3
comments
2
min read
LW
link
“Go west, young man!”—Preferences in (imperfect) maps
Stuart_Armstrong
31 Jul 2020 7:50 UTC
21
points
10
comments
3
min read
LW
link
Learning Values in Practice
Stuart_Armstrong
20 Jul 2020 18:38 UTC
23
points
0
comments
5
min read
LW
link
Back to top
Next