AI ALIGNMENT FORUMTags
AF

Anthropic (org)

EditHistorySubscribe

Help improve this page

EditHistorySubscribe

Help improve this page

Anthropic (org)

Contributors

Anthropic is an AI organization.

Not to be confused with anthropics.

Posts tagged Anthropic (org)

4

63Anthropic's Core Views on AI Safety

Zac Hatfield-Dodds

2y

13

1

50Why I'm joining Anthropic

2y

2

3

33Toy Models of Superposition

2y

2

1

33Concrete Reasons for Hope about AI

Zac Hatfield-Dodds

2y

0

2

67Transformer Circuits

3y

3

1

110Towards Monosemanticity: Decomposing Language Models With Dictionary Learning

Zac Hatfield-Dodds

1y

11

1

95Introducing Alignment Stress-Testing at Anthropic

10mo

19

1

69EIS XIII: Reflections on Anthropic’s SAE Research Circa May 2024

6mo

7

2

42Anthropic: Three Sketches of ASL-4 Safety Case Components

Zach Stein-Perlman

16d

18

1

46Dario Amodei’s prepared remarks from the UK AI Safety Summit, on Anthropic’s Responsible Scaling Policy

Zac Hatfield-Dodds

1y

0

1

44Anthropic's Responsible Scaling Policy & Long-Term Benefit Trust

Zac Hatfield-Dodds

1y

5

1

30Paper: The Capacity for Moral Self-Correction in Large Language Models (Anthropic)

2y

0

1

25Anthropic's updated Responsible Scaling Policy

Zac Hatfield-Dodds

1mo

0

1

18How do new models from OpenAI, DeepMind and Anthropic perform on TruthfulQA?

3y

1

1

15Frontier Model Security

Matthew "Vaniver" Gray

1y

1