Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
Paul B
Karma:
218
All
Posts
Comments
New
Top
Old
Paul Bogdan’s Shortform
Paul B
13 Sep 2025 11:32 UTC
3
points
1
comment
1
min read
LW
link
Statistical suggestions for mech interp research and beyond
Paul B
6 Aug 2025 12:45 UTC
65
points
4
comments
15
min read
LW
link
Unfaithful chain-of-thought as nudged reasoning
Paul B
,
Uzay Macar
,
Arthur Conmy
and
Neel Nanda
22 Jul 2025 22:35 UTC
54
points
3
comments
10
min read
LW
link
Thought Anchors: Which LLM Reasoning Steps Matter?
Uzay Macar
,
Paul B
,
Neel Nanda
and
Arthur Conmy
2 Jul 2025 20:16 UTC
35
points
6
comments
6
min read
LW
link
(www.thought-anchors.com)
Emergent scaling effects on the functional hierarchies within LLMs
Paul B
24 Mar 2025 13:03 UTC
8
points
0
comments
9
min read
LW
link
Back to top