This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
Tags
LW
Login
Anthropic (org)
Edit
History
Subscribe
Discussion
(0)
Help improve this page
Edit
History
Subscribe
Discussion
(0)
Help improve this page
Anthropic (org)
Random Tag
Contributors
2
Ruby
0
Multicore
Anthropic
is an AI organization.
Not to be confused with
anthropics
.
Posts tagged
Anthropic (org)
Most Relevant
11
172
Anthropic's Core Views on AI Safety
Ω
Zac Hatfield-Dodds
2y
Ω
39
8
166
My understanding of Anthropic strategy
Swimmer963 (Miranda Dixon-Luinenburg)
2y
31
6
121
Why I'm joining Anthropic
Ω
evhub
2y
Ω
4
6
69
Toy Models of Superposition
Ω
evhub
2y
Ω
4
5
100
Concrete Reasons for Hope about AI
Ω
Zac Hatfield-Dodds
2y
Ω
13
5
73
[Linkpost] Google invested $300M in Anthropic in late 2022
Akash
2y
14
4
144
Transformer Circuits
Ω
evhub
3y
Ω
4
4
21
Anthropic's SoLU (Softmax Linear Unit)
Joel Burget
2y
1
3
287
Towards Monosemanticity: Decomposing Language Models With Dictionary Learning
Ω
Zac Hatfield-Dodds
1y
Ω
21
3
188
OMMC Announces RIP
Adam Scholl
,
aysja
7mo
5
3
115
Anthropic's Certificate of Incorporation
Zach Stein-Perlman
5mo
4
3
82
Anthropic is further accelerating the Arms Race?
sapphire
2y
22
3
12
Mechanistic Interpretability for the MLP Layers (rough early thoughts)
MadHatter
3y
3
2
199
Maybe Anthropic's Long-Term Benefit Trust is powerless
Zach Stein-Perlman
6mo
21
2
182
Introducing Alignment Stress-Testing at Anthropic
Ω
evhub
10mo
Ω
23