Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
Marcel Windys
Karma:
61
All
Posts
Comments
New
Top
Old
Unlearning Needs to be More Selective [Progress Report]
Filip Sondej
,
Yushi Yang
and
Marcel Windys
27 Jun 2025 16:38 UTC
24
points
6
comments
3
min read
LW
link
AI Safety Polska community meet-up in Kraków — Representation Engineering
Marcel Windys
6 Dec 2024 3:28 UTC
14
points
0
comments
1
min read
LW
link
GPTs’ ability to keep a secret is weirdly prompt-dependent
Mateusz Bagiński
,
Filip Sondej
and
Marcel Windys
22 Jul 2023 12:21 UTC
31
points
0
comments
9
min read
LW
link
Back to top