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:
17,677
All
Posts
Comments
New
Top
Old
Page
1
Using GPT-Eliezer against ChatGPT Jailbreaking
Stuart_Armstrong
and
rgorman
6 Dec 2022 19:54 UTC
170
points
85
comments
9
min read
LW
link
The AI in a box boxes you
Stuart_Armstrong
2 Feb 2010 10:10 UTC
168
points
389
comments
1
min read
LW
link
Assessing Kurzweil predictions about 2019: the results
Stuart_Armstrong
6 May 2020 13:36 UTC
145
points
21
comments
4
min read
LW
link
Just another day in utopia
Stuart_Armstrong
25 Dec 2011 9:37 UTC
142
points
118
comments
13
min read
LW
link
Assessing Kurzweil: the results
Stuart_Armstrong
16 Jan 2013 16:51 UTC
97
points
64
comments
2
min read
LW
link
The Adventure: a new Utopia story
Stuart_Armstrong
5 Feb 2020 16:50 UTC
97
points
37
comments
51
min read
LW
link
mAIry’s room: AI reasoning to solve philosophical problems
Stuart_Armstrong
5 Mar 2019 20:24 UTC
87
points
41
comments
6
min read
LW
link
2
reviews
Anthropic signature: strange anti-correlations
Stuart_Armstrong
21 Oct 2014 16:59 UTC
83
points
25
comments
1
min read
LW
link
Benchmark for successful concept extrapolation/avoiding goal misgeneralization
Stuart_Armstrong
4 Jul 2022 20:48 UTC
82
points
12
comments
4
min read
LW
link
The Goldbach conjecture is probably correct; so was Fermat’s last theorem
Stuart_Armstrong
14 Jul 2020 19:30 UTC
80
points
27
comments
4
min read
LW
link
Model splintering: moving from one imperfect model to another
Stuart_Armstrong
27 Aug 2020 11:53 UTC
79
points
10
comments
33
min read
LW
link
Completeness, incompleteness, and what it all means: first versus second order logic
Stuart_Armstrong
16 Jan 2012 17:38 UTC
79
points
39
comments
11
min read
LW
link
AI timeline predictions: are we getting better?
Stuart_Armstrong
17 Aug 2012 7:07 UTC
79
points
81
comments
4
min read
LW
link
Siren worlds and the perils of over-optimised search
Stuart_Armstrong
7 Apr 2014 11:00 UTC
77
points
418
comments
7
min read
LW
link
The Octopus, the Dolphin and Us: a Great Filter tale
Stuart_Armstrong
3 Sep 2014 21:37 UTC
76
points
236
comments
3
min read
LW
link
“But that’s your job”: why organisations can work
Stuart_Armstrong
5 Feb 2020 12:25 UTC
76
points
12
comments
4
min read
LW
link
And the AI would have got away with it too, if...
Stuart_Armstrong
22 May 2019 21:35 UTC
75
points
7
comments
1
min read
LW
link
Let’s split the cake, lengthwise, upwise and slantwise
Stuart_Armstrong
25 Oct 2010 13:15 UTC
74
points
29
comments
4
min read
LW
link
To reduce astronomical waste: take your time, then go very fast
Stuart_Armstrong
13 Jul 2013 16:41 UTC
70
points
50
comments
3
min read
LW
link
Research Agenda v0.9: Synthesising a human’s preferences into a utility function
Stuart_Armstrong
17 Jun 2019 17:46 UTC
70
points
26
comments
33
min read
LW
link
Back to top
Next