Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
JustisMills
Karma:
445
All
Posts
Comments
New
Top
Old
LLMs seem (relatively) safe
JustisMills
25 Apr 2024 22:13 UTC
48
points
23
comments
7
min read
LW
link
(justismills.substack.com)
AI Safety Concepts Writeup: WebGPT
JustisMills
11 Aug 2023 1:35 UTC
9
points
1
comment
7
min read
LW
link
Consider Multiclassing
JustisMills
7 Jul 2022 14:54 UTC
17
points
1
comment
3
min read
LW
link
Alignment Risk Doesn’t Require Superintelligence
JustisMills
15 Jun 2022 3:12 UTC
35
points
4
comments
2
min read
LW
link
Editing Advice for LessWrong Users
JustisMills
11 Apr 2022 16:32 UTC
231
points
14
comments
6
min read
LW
link
1
review
Back to top