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
178
Anthropic's Core Views on AI Safety
Ω
Zac Hatfield-Dodds
15d
Ω
38
6
121
Why I'm joining Anthropic
Ω
evhub
3mo
Ω
4
6
64
Toy Models of Superposition
Ω
evhub
6mo
Ω
2
5
107
Concrete Reasons for Hope about AI
Ω
Zac Hatfield-Dodds
2mo
Ω
13
5
73
[Linkpost] Google invested $300M in Anthropic in late 2022
Akash
2mo
14
4
161
My understanding of Anthropic strategy
Swimmer963 (Miranda Dixon-Luinenburg)
1mo
28
4
143
Transformer Circuits
Ω
evhub
1y
Ω
4
4
15
Anthropic's SoLU (Softmax Linear Unit)
Joel Burget
9mo
1
3
11
Mechanistic Interpretability for the MLP Layers (rough early thoughts)
MadHatter
1y
2
2
82
A Summary Of Anthropic's First Paper
Sam Ringer
1y
1
2
65
Paper: The Capacity for Moral Self-Correction in Large Language Models (Anthropic)
Ω
LawrenceC
1mo
Ω
9
2
46
Podcast Transcript: Daniela and Dario Amodei on Anthropic
remember
17d
2
2
42
How do new models from OpenAI, DeepMind and Anthropic perform on TruthfulQA?
Ω
Owain_Evans
1y
Ω
3
2
17
Anthropic: Core Views on AI Safety: When, Why, What, and How
jonmenaster
15d
1
1
294
A challenge for AGI organizations, and a challenge for readers
Ω
Rob Bensinger
,
Eliezer Yudkowsky
4mo
Ω
32