x
This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
Claude 3 Opus — LessWrong
Claude 3 Opus
This page is a stub.
Subscribe
Discussion
Subscribe
Discussion
Posts tagged
Claude 3 Opus
Most Relevant
1
494
Alignment Faking in Large Language Models
Ω
ryan_greenblatt
,
evhub
,
Carson Denison
,
Benjamin Wright
,
Fabien Roger
,
Monte M
,
Sam Marks
,
Johannes Treutlein
,
Sam Bowman
,
Buck
2y
Ω
87
1
392
Did Claude 3 Opus align itself via gradient hacking?
Ω
Fiora Starlight
6mo
Ω
49
1
209
Will alignment-faking Claude accept a deal to reveal its misalignment?
Ω
ryan_greenblatt
,
Kyle Fish
2y
Ω
28
1
160
Why Do Some Language Models Fake Alignment While Others Don't?
Ω
abhayesian
,
John Hughes
,
Alex Mallen
,
Jozdien
,
janus
,
Fabien Roger
1y
Ω
14
1
127
what makes Claude 3 Opus misaligned
janus
1y
14
1
115
Anthropic release Claude 3, claims >GPT-4 Performance
Ω
LawrenceC
2y
Ω
41
1
82
Character Training Induces Motivation Clarification: A Clue to Claude 3 Opus
Oliver Daniels
6mo
5
1
42
Economics of Claude 3 Opus Inference
Antra Tessera
,
janus
1y
0