Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
Raymond D
Karma:
675
All
Posts
Comments
New
Top
Old
ChatGPT can learn indirect control
Raymond D
21 Mar 2024 21:11 UTC
212
points
23
comments
1
min read
LW
link
Predictive model agents are sort of corrigible
Raymond D
5 Jan 2024 14:05 UTC
35
points
6
comments
3
min read
LW
link
Picking Mentors For Research Programmes
Raymond D
10 Nov 2023 13:01 UTC
105
points
8
comments
4
min read
LW
link
Goal-Direction for Simulated Agents
Raymond D
12 Jul 2023 17:06 UTC
33
points
2
comments
6
min read
LW
link
Language Models can be Utility-Maximising Agents
Raymond D
1 Feb 2023 18:13 UTC
22
points
1
comment
2
min read
LW
link
Taking Clones Seriously
Raymond D
1 Dec 2021 17:29 UTC
58
points
45
comments
2
min read
LW
link
Why Save The Drowning Child: Ethics Vs Theory
Raymond D
16 Nov 2021 19:07 UTC
17
points
12
comments
4
min read
LW
link
The Opt-Out Clause
Raymond D
3 Nov 2021 22:02 UTC
38
points
49
comments
1
min read
LW
link
30-ish focusing tips
Raymond D
22 Oct 2021 19:38 UTC
21
points
4
comments
6
min read
LW
link
Back to top