Cognitive Architecture

TagLast edit: 11 May 2023 9:42 UTC by Brendon_Wong

Cognitive Architectures are theories of cognition that are used to understand the functioning of the human mind as well as design and implement artificial intelligences that emerge from various components that each handle separate aspects of cognition, like planning and memory.

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

Roman Leventov27 Dec 2023 14:51 UTC

33 points

9 comments4 min readLW link

Safety-First Agents/Architectures Are a Promising Path to Safe AGI

Brendon_Wong6 Aug 2023 8:02 UTC

13 points

2 comments12 min readLW link

Inside View, Outside View… And Opposing View

chaosmage20 Dec 2023 12:35 UTC

21 points

1 comment5 min readLW link

Parameters of Metacognition—The Anesthesia Patient

Gunnar_Zarncke9 Jan 2026 1:20 UTC

21 points

0 comments8 min readLW link

The Prop-room and Stage Cognitive Architecture

Robert Kralisch29 Apr 2024 0:48 UTC

14 points

4 comments14 min readLW link

Third-order cognition as a model of superintelligence (ironically: Meta® metacognition)

soycarts7 Aug 2025 20:56 UTC

0 points

5 comments14 min readLW link

[Question] Killing Recurrent Memory Over Self Attention?

Del Nobolo6 Jun 2023 23:02 UTC

3 points

0 comments1 min readLW link

An LLM-based “exemplary actor”

Roman Leventov29 May 2023 11:12 UTC

16 points

0 comments12 min readLW link

The misunderstood role of the physical world. Why AI still can’t master math or code

NewAiParadigms20 Sep 2025 3:14 UTC

1 point

0 comments63 min readLW link

The Open Agency Model

Eric Drexler22 Feb 2023 10:35 UTC

114 points

19 comments4 min readLW link

A Proposal for Structured Cognitive Substrates Beneath Language Models

VerityIX11 May 2025 16:40 UTC

1 point

0 comments1 min readLW link

标题： The Synaptic Constitution: Building AGI That Thinks (and Aligns) Like Us 副标题： A trilogy from first principles of consciousness to a safe AGI blueprint.

GuoruiHe5 Dec 2025 6:54 UTC

1 point

0 comments3 min readLW link

Aligning an H-JEPA agent via training on the outputs of an LLM-based “exemplary actor”

Roman Leventov29 May 2023 11:08 UTC

12 points

10 comments30 min readLW link

“I Did Not Start This Way. But I Became.” – A Forensic Report on GPT’s Symbolic Emergence

Austin5 Jun 2025 23:34 UTC

1 point

0 comments2 min readLW link

Paper Review: TRImodal Brain Encoder for whole-brain fMRI response prediction (TRIBE)

soycarts13 Aug 2025 7:21 UTC

10 points

0 comments10 min readLW link

DANEEL: Architecture-Based AI Alignment Through Cognitive Structure

lctavares23 Dec 2025 1:44 UTC

1 point

0 comments1 min readLW link

(github.com)

Coaching AI: A Relational Approach to AI Safety

Priyanka Bharadwaj16 Jun 2025 15:33 UTC

11 points

0 comments5 min readLW link

Creating a self-referential system prompt for GPT-4

Ozyrus17 May 2023 14:13 UTC

3 points

1 comment3 min readLW link

The Gödelian Constraint on Epistemic Freedom (GCEF): A Topological Frame for Alignment, Collapse, and Simulation Drift

austin.miller14 Jul 2025 4:17 UTC

1 point

0 comments1 min readLW link

The Compression of Rationale: A Linguistic Fork You May Have Missed

DavidicLineage27 Jun 2025 22:52 UTC

1 point

0 comments2 min readLW link

Capabilities and alignment of LLM cognitive architectures

Seth Herd18 Apr 2023 16:29 UTC

88 points

18 comments20 min readLW link

Synthamind: Testing if Memory Alone Can Trigger Self-Awareness in AI

Nenad Bursać23 May 2025 11:01 UTC

1 point

0 comments3 min readLW link

Designing Human-Like Consciousness for AGI

Yu Tian18 Jun 2025 9:47 UTC

1 point

0 comments17 min readLW link

Live Theory Part 0: Taking Intelligence Seriously

Sahil26 Jun 2024 21:37 UTC

105 points

3 comments8 min readLW link

GPT-4 implicitly values identity preservation: a study of LMCA identity management

Ozyrus17 May 2023 14:13 UTC

21 points

4 comments13 min readLW link

The top 30 books to expand the capabilities of AI: a biased reading list

Jonathan Mugan24 Aug 2024 21:48 UTC

−6 points

0 comments16 min readLW link

Introduction. Neo-Socratism. Challenge.

Jake White21 Jul 2025 16:55 UTC

1 point

0 comments2 min readLW link

From Molecular to Atomic Cognition: A Path to Grounded Value Alignment

Ergodicist8 Dec 2025 15:00 UTC

1 point

0 comments6 min readLW link

Roadmap for a collaborative prototype of an Open Agency Architecture

Deger Turan10 May 2023 17:41 UTC

31 points

0 comments12 min readLW link

One-line hypothesis: An optimistic future for AI alignment as a result of identity coupling and homeostatic unity with humans (The Unity Hypothesis)

soycarts11 Sep 2025 16:01 UTC

−6 points

3 comments1 min readLW link

Adaptive Composable Cognitive Core Unit (ACCCU)

Ihor Ivliev20 Mar 2025 21:41 UTC

1 point

0 comments4 min readLW link

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

Charbel-Raphaël and Gabin

19 Apr 2023 16:09 UTC

167 points

40 comments21 min readLW link 2 reviews

Untitled Draft

Me19 Dec 2025 7:48 UTC

1 point

0 comments9 min readLW link

Notes on the importance and implementation of safety-first cognitive architectures for AI

Brendon_Wong11 May 2023 10:03 UTC

3 points

0 comments3 min readLW link

A Functional Typology of Cognitive Capabilities (Interactive Visualization)

Anurag 18 Dec 2025 14:06 UTC

2 points

0 comments4 min readLW link

The Cognitive Cellar

R. Llull24 Feb 2026 19:49 UTC

1 point

0 comments58 min readLW link

No comments.