Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
Raffaello Fornasiere
Karma:
49
All
Posts
Comments
New
Top
Old
Activation Oracles significantly underperform without a safe base model
Raffaello Fornasiere
,
Nikita Menon
,
therootof3
,
GabrielKS
and
StefanHex
28 Aug 2026 1:39 UTC
20
points
0
comments
9
min read
LW
link
The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology
GabrielKS
,
therootof3
,
Raffaello Fornasiere
,
Nikita Menon
and
StefanHex
23 Jul 2026 22:37 UTC
45
points
0
comments
6
min read
LW
link
(arxiv.org)
Back to top