LESSWRONGTags
LW

Open Agency Architecture

EditHistorySubscribe

Help improve this page (3 flags)

EditHistorySubscribe

Help improve this page (3 flags)

Open Agency Architecture

Contributors

4Roman Leventov

You are viewing revision 1.8.0, last edited by Chipmonk

The Open Agency Architecture ("OAA") is an AI alignment proposal by (among others) @davidad and @Eric Drexler.

A short and simple introduction to the OAA is not available on LW, but instead available here. (2023 Dec)

Related:...

Posts tagged Open Agency Architecture

6

154Davidad's Bold Plan for Alignment: An In-Depth Explanation

Charbel-Raphaël, Gabin

1y

33

5

162A list of core AI safety problems and how I hope to solve them

9mo

26

5

79An Open Agency Architecture for Safe Transformative AI

1y

22

3

113The Open Agency Model

1y

18

3

19Gaia Network: a practical, incremental pathway to Open Agency Architecture

Roman Leventov, Rafael Kaufmann Nedal

5mo

8

2

33AGI will be made of heterogeneous components, Transformer and Selective SSM blocks will be among them

5mo

9

2

17SociaLLM: proposal for a language model design for personalised apps, social science, and AI safety research

5mo

5

1

69Davidad's Provably Safe AI Architecture - ARIA's Programme Thesis

4mo

17

1

63Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems

15d

9

1

53«Boundaries/Membranes» and AI safety compilation

1y

17

1

48Apply to the Conceptual Boundaries Workshop for AI Safety

6mo

0

1

47Safety First: safety before full alignment. The deontic sufficiency hypothesis.

5mo

3

1

44Announcing Atlas Computing

2mo

4

1

41What does davidad want from «boundaries»?

Chipmonk, davidad

4mo

1

1

30Roadmap for a collaborative prototype of an Open Agency Architecture

1y

0