This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
Wikitags
AF
Login
Cognitive Architecture
Settings
Applied to
Adaptive Composable Cognitive Core Unit (ACCCU)
by
Thinker
9d
ago
Applied to
The top 30 books to expand the capabilities of AI: a biased reading list
7mo
ago
Applied to
Live Theory Part 0: Taking Intelligence Seriously
by
particlemania
9mo
ago
Applied to
The Prop-room and Stage Cognitive Architecture
by
Robert Kralisch
1y
ago
Applied to
AGI will be made of heterogeneous components, Transformer and Selective SSM blocks will be among them
by
Roman Leventov
1y
ago
Applied to
Inside View, Outside View... And Opposing View
by
Daniel Böttger
1y
ago
Applied to
Safety-First Agents/Architectures Are a Promising Path to Safe AGI
by
Brendon_Wong
2y
ago
Applied to
Killing Recurrent Memory Over Self Attention?
by
Del Nobolo
2y
ago
Applied to
Aligning an H-JEPA agent via training on the outputs of an LLM-based "exemplary actor"
by
Roman Leventov
2y
ago
Applied to
An LLM-based “exemplary actor”
by
Roman Leventov
2y
ago
Applied to
Roadmap for a collaborative prototype of an Open Agency Architecture
by
Brendon_Wong
2y
ago
Applied to
Creating a self-referential system prompt for GPT-4
by
Ozyrus
2y
ago
Applied to
GPT-4 implicitly values identity preservation: a study of LMCA identity management
by
Ozyrus
2y
ago
Applied to
The Open Agency Model
by
Brendon_Wong
2y
ago
Applied to
Capabilities and alignment of LLM cognitive architectures
by
Brendon_Wong
2y
ago
Applied to
Davidad's Bold Plan for Alignment: An In-Depth Explanation
by
Brendon_Wong
2y
ago
Applied to
Notes on the importance and implementation of safety-first cognitive architectures for AI
by
Brendon_Wong
2y
ago
Brendon_Wong
v1.0.0
May 11th 2023 GMT
(+278)
LW
1
Created by
Brendon_Wong
at
2y