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
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
181
Anthropic's Core Views on AI Safety
Ω
Zac Hatfield-Dodds
1y
Ω
39
8
165
My understanding of Anthropic strategy
Swimmer963 (Miranda Dixon-Luinenburg)
1y
31
6
121
Why I'm joining Anthropic
Ω
evhub
1y
Ω
4
6
68
Toy Models of Superposition
Ω
evhub
2y
Ω
4
5
102
Concrete Reasons for Hope about AI
Ω
Zac Hatfield-Dodds
1y
Ω
13
5
73
[Linkpost] Google invested $300M in Anthropic in late 2022
Akash
1y
14
4
144
Transformer Circuits
Ω
evhub
2y
Ω
4
4
21
Anthropic's SoLU (Softmax Linear Unit)
Joel Burget
2y
1
3
281
Towards Monosemanticity: Decomposing Language Models With Dictionary Learning
Ω
Zac Hatfield-Dodds
5mo
Ω
18
3
82
Anthropic is further accelerating the Arms Race?
sapphire
1y
22
3
11
Mechanistic Interpretability for the MLP Layers (rough early thoughts)
MadHatter
2y
2
2
178
Introducing Alignment Stress-Testing at Anthropic
Ω
evhub
3mo
Ω
23
2
141
Request to AGI organizations: Share your views on pausing AI progress
Akash
,
simeon_c
1y
11
2
104
Anthropic Observations
Zvi
8mo
1
2
90
Anthropic's Responsible Scaling Policy & Long-Term Benefit Trust
Ω
Zac Hatfield-Dodds
6mo
Ω
23