Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
avturchin
Karma:
3,465
All
Posts
Comments
New
Top
Old
Page
1
Strengthening the Argument for Intrinsic AI Safety: The S-Curves Perspective
avturchin
7 Aug 2023 13:13 UTC
8
points
0
comments
12
min read
LW
link
The Sharp Right Turn: sudden deceptive alignment as a convergent goal
avturchin
6 Jun 2023 9:59 UTC
38
points
5
comments
1
min read
LW
link
Another formalization attempt: Central Argument That AGI Presents a Global Catastrophic Risk
avturchin
12 May 2023 13:22 UTC
16
points
4
comments
2
min read
LW
link
Running many AI variants to find correct goal generalization
avturchin
4 Apr 2023 14:16 UTC
20
points
3
comments
1
min read
LW
link
AI-kills-everyone scenarios require robotic infrastructure, but not necessarily nanotech
avturchin
3 Apr 2023 12:45 UTC
52
points
47
comments
4
min read
LW
link
The AI Shutdown Problem Solution through Commitment to Archiving and Periodic Restoration
avturchin
30 Mar 2023 13:17 UTC
16
points
7
comments
1
min read
LW
link
Long-term memory for LLM via self-replicating prompt
avturchin
10 Mar 2023 10:28 UTC
20
points
3
comments
2
min read
LW
link
Logical Probability of Goldbach’s Conjecture: Provable Rule or Coincidence?
avturchin
29 Dec 2022 13:37 UTC
5
points
15
comments
8
min read
LW
link
A Pin and a Balloon: Anthropic Fragility Increases Chances of Runaway Global Warming
avturchin
11 Sep 2022 10:25 UTC
33
points
23
comments
52
min read
LW
link
The table of different sampling assumptions in anthropics
avturchin
29 Jun 2022 10:41 UTC
38
points
5
comments
12
min read
LW
link
Another plausible scenario of AI risk: AI builds military infrastructure while collaborating with humans, defects later.
avturchin
10 Jun 2022 17:24 UTC
10
points
2
comments
1
min read
LW
link
Untypical SIA
avturchin
8 Jun 2022 14:23 UTC
5
points
3
comments
2
min read
LW
link
Russian x-risks newsletter May 2022 + short history of “methodologists”
avturchin
5 Jun 2022 11:50 UTC
23
points
4
comments
2
min read
LW
link
Grabby Animals: Observation-selection effects favor the hypothesis that UAP are animals which consist of the “field-matter”:
avturchin
27 May 2022 9:27 UTC
20
points
15
comments
8
min read
LW
link
The Future of Nuclear War
avturchin
21 May 2022 7:52 UTC
33
points
1
comment
34
min read
LW
link
The doomsday argument is normal
avturchin
3 Apr 2022 15:17 UTC
6
points
44
comments
2
min read
LW
link
Russian x-risk newsletter March 2022 update
avturchin
1 Apr 2022 13:26 UTC
19
points
13
comments
2
min read
LW
link
I left Russia on March 8
avturchin
10 Mar 2022 20:05 UTC
127
points
16
comments
1
min read
LW
link
Russian x-risks newsletter winter 21-22, war risks update.
avturchin
20 Feb 2022 18:58 UTC
29
points
14
comments
3
min read
LW
link
SIA becomes SSA in the multiverse
avturchin
1 Feb 2022 11:31 UTC
7
points
35
comments
5
min read
LW
link
Back to top
Next