AI ALIGNMENT FORUM
AF

Wikitags

Open Agency Architecture

Edited by Chris Lakin, Roman Leventov, niplav last updated 10th Apr 2024

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

See Davidad's Provably Safe AI Architecture - ARIA's Programme Thesis for the most up-to-date (2024 Feb 1) and quite readable explanation.

A shorter but older explanation is also available here.

New better link: https://www.aria.org.uk/programme-safeguarded-ai/ 

Related:

  • Atlas Computing is the org intended to house OAA.
  • Gaia Network is a variant of an open agency architecture. Gaia Network is related to (the) OAA, but not directly descending from it.
Subscribe
Subscribe
Discussion0
Discussion0
Posts tagged Open Agency Architecture
52Davidad's Bold Plan for Alignment: An In-Depth Explanation
Charbel-Raphaël, Gabin
2y
5
56A list of core AI safety problems and how I hope to solve them
davidad
2y
12
34An Open Agency Architecture for Safe Transformative AI
davidad
3y
18
39The Open Agency Model
Eric Drexler
3y
2
8AGI will be made of heterogeneous components, Transformer and Selective SSM blocks will be among them
Roman Leventov
2y
0
25Davidad's Provably Safe AI Architecture - ARIA's Programme Thesis
simeon_c
2y
0
30Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems
Joar Skalse
1y
8
18Safety First: safety before full alignment. The deontic sufficiency hypothesis.
Chris Lakin
2y
1
23What does davidad want from «boundaries»?
Chris Lakin, davidad
2y
0
Add Posts