Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
OscarGilg
Karma:
134
MATS 9.0 with Patrick Butlin
Prev quant trader
@gilg_oscar
All
Posts
Comments
New
Top
Old
Ablating Split Personality Training
OscarGilg
23 Mar 2026 17:45 UTC
54
points
1
comment
5
min read
LW
link
Models have linear representations of what tasks they like
OscarGilg
5 Mar 2026 18:44 UTC
54
points
16
comments
11
min read
LW
link
Building Conscious* AI: An Illusionist Case
OscarGilg
11 Sep 2025 16:41 UTC
2
points
9
comments
14
min read
LW
link
Back to top