Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
Jérémy Andréoletti
Karma:
183
All
Posts
Comments
New
Top
Old
Claude Mythos Preview: Analysis of Anthropic’s Public Announcement
Antoine Maier
,
Tom DAVID
,
lcarbonell
,
Jérémy Andréoletti
,
TReltgen
and
Pierre Peigné
14 Apr 2026 21:25 UTC
24
points
3
comments
12
min read
LW
link
(gpaipolicylab.org)
Mapping AI Capabilities to Human Expertise on the Rosetta Stone (Epoch Capabilities Index)
Laura Domenech
and
Jérémy Andréoletti
9 Mar 2026 17:09 UTC
18
points
2
comments
6
min read
LW
link
Jailbreaking is Empirical Evidence for Inner Misalignment and Against Alignment by Default
Jérémy Andréoletti
16 Feb 2026 17:49 UTC
54
points
16
comments
2
min read
LW
link
Basics of How Not to Die
Camille B.
,
Jérémy Andréoletti
,
elisareine
,
Charbel-Raphaël
,
Lucie Philippon
,
Maxime Fournes
and
T-bo🔸
31 Jan 2026 19:04 UTC
112
points
21
comments
4
min read
LW
link
Back to top