Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
Logan Zoellner
Karma:
1,113
All
Posts
Comments
New
Top
Old
Page
1
Anti MMAcevedo Protocol
Logan Zoellner
16 Apr 2024 22:32 UTC
1
point
1
comment
8
min read
LW
link
[Question]
Is there a “critical threshold” for LLM scaling laws?
Logan Zoellner
30 Mar 2024 12:23 UTC
7
points
1
comment
1
min read
LW
link
Are AIs conscious? It might depend
Logan Zoellner
15 Mar 2024 23:09 UTC
7
points
6
comments
3
min read
LW
link
[Question]
Theoretically, could we balance the budget painlessly?
Logan Zoellner
3 Jan 2024 14:46 UTC
4
points
12
comments
1
min read
LW
link
Various AI doom pathways (and how likely they are)
Logan Zoellner
14 Dec 2023 0:54 UTC
1
point
1
comment
4
min read
LW
link
(midwitalignment.substack.com)
Normative Ethics vs Utilitarianism
Logan Zoellner
30 Nov 2023 15:36 UTC
6
points
0
comments
2
min read
LW
link
(midwitalignment.substack.com)
AI Alignment [progress] this Week (11/19/2023)
Logan Zoellner
21 Nov 2023 16:09 UTC
17
points
3
comments
5
min read
LW
link
(midwitalignment.substack.com)
AI Alignment [progress] this Week (11/12/2023)
Logan Zoellner
14 Nov 2023 22:21 UTC
6
points
0
comments
2
min read
LW
link
(midwitalignment.substack.com)
AI Alignment [Progress] this Week (11/05/2023)
Logan Zoellner
7 Nov 2023 13:26 UTC
24
points
0
comments
4
min read
LW
link
(midwitalignment.substack.com)
AI Alignment [progress] this Week (10/29/2023)
Logan Zoellner
30 Oct 2023 15:02 UTC
15
points
4
comments
6
min read
LW
link
(midwitalignment.substack.com)
[Question]
ELI5 Why isn’t alignment *easier* as models get stronger?
Logan Zoellner
28 Oct 2023 14:34 UTC
3
points
9
comments
1
min read
LW
link
AI Alignment [Incremental Progress Units] this Week (10/22/23)
Logan Zoellner
23 Oct 2023 20:32 UTC
22
points
0
comments
6
min read
LW
link
(midwitalignment.substack.com)
A NotKillEveryoneIsm Argument for Accelerating Deep Learning Research
Logan Zoellner
19 Oct 2023 16:28 UTC
−7
points
6
comments
5
min read
LW
link
(midwitalignment.substack.com)
AI Alignment [Incremental Progress Units] this week (10/08/23)
Logan Zoellner
16 Oct 2023 1:46 UTC
14
points
5
comments
4
min read
LW
link
(midwitalignment.substack.com)
AI Alignment Breakthroughs this week (10/08/23)
Logan Zoellner
8 Oct 2023 23:30 UTC
30
points
14
comments
6
min read
LW
link
AI Alignment Breakthroughs this Week [new substack]
Logan Zoellner
1 Oct 2023 22:13 UTC
0
points
8
comments
2
min read
LW
link
Instrumental Convergence Bounty
Logan Zoellner
14 Sep 2023 14:02 UTC
62
points
24
comments
1
min read
LW
link
An embedding decoder model, trained with a different objective on a different dataset, can decode another model’s embeddings surprisingly accurately
Logan Zoellner
3 Sep 2023 11:34 UTC
20
points
1
comment
1
min read
LW
link
Towards Non-Panopticon AI Alignment
Logan Zoellner
6 Jul 2023 15:29 UTC
7
points
0
comments
3
min read
LW
link
Re: The Crux List
Logan Zoellner
1 Jun 2023 4:48 UTC
11
points
0
comments
2
min read
LW
link
Back to top
Next