Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
So8res
(Nate Soares)
Karma:
15,569
All
Posts
Comments
New
Top
Old
Page
1
Focus on the places where you feel shocked everyone’s dropping the ball
So8res
2 Feb 2023 0:27 UTC
413
points
61
comments
4
min read
LW
link
On how various plans miss the hard bits of the alignment challenge
So8res
12 Jul 2022 2:49 UTC
302
points
88
comments
29
min read
LW
link
3
reviews
Hooray for stepping out of the limelight
So8res
1 Apr 2023 2:45 UTC
281
points
24
comments
1
min read
LW
link
A central AI alignment problem: capabilities generalization, and the sharp left turn
So8res
15 Jun 2022 13:10 UTC
279
points
53
comments
10
min read
LW
link
1
review
Dark Arts of Rationality
So8res
19 Jan 2014 2:47 UTC
254
points
193
comments
18
min read
LW
link
Visible Thoughts Project and Bounty Announcement
So8res
30 Nov 2021 0:19 UTC
249
points
103
comments
13
min read
LW
link
1
review
Deep Deceptiveness
So8res
21 Mar 2023 2:51 UTC
231
points
58
comments
14
min read
LW
link
On saving the world
So8res
30 Jan 2014 20:00 UTC
227
points
171
comments
16
min read
LW
link
On Caring
So8res
15 Oct 2014 1:59 UTC
225
points
276
comments
10
min read
LW
link
Enemies vs Malefactors
So8res
28 Feb 2023 23:38 UTC
203
points
60
comments
1
min read
LW
link
On learning difficult things
So8res
11 Nov 2013 23:35 UTC
202
points
47
comments
6
min read
LW
link
Ability to solve long-horizon tasks correlates with wanting things in the behaviorist sense
So8res
24 Nov 2023 17:37 UTC
202
points
82
comments
5
min read
LW
link
The mechanics of my recent productivity
So8res
9 Jan 2014 2:30 UTC
199
points
47
comments
9
min read
LW
link
If interpretability research goes well, it may get dangerous
So8res
3 Apr 2023 21:48 UTC
197
points
10
comments
2
min read
LW
link
A note about differential technological development
So8res
15 Jul 2022 4:46 UTC
192
points
32
comments
6
min read
LW
link
AI alignment researchers don’t (seem to) stack
So8res
21 Feb 2023 0:48 UTC
189
points
40
comments
3
min read
LW
link
A rough and incomplete review of some of John Wentworth’s research
So8res
28 Mar 2023 18:52 UTC
175
points
17
comments
18
min read
LW
link
AI as a science, and three obstacles to alignment strategies
So8res
25 Oct 2023 21:00 UTC
175
points
79
comments
11
min read
LW
link
AGI ruin scenarios are likely (and disjunctive)
So8res
27 Jul 2022 3:21 UTC
170
points
38
comments
6
min read
LW
link
Thoughts on the AI Safety Summit company policy requests and responses
So8res
31 Oct 2023 23:54 UTC
169
points
14
comments
10
min read
LW
link
Back to top
Next