amr/memex
1
0
Fork 0
Code Issues 12 Pull Requests Actions Packages Projects 1 Releases Wiki Activity

ARCH: Clean Core Refactor & Terminology Alignment

Browse Source
This commit is contained in:
Amr Gharbeia
2026-04-13 09:03:42 -04:00
parent 8ee1c0c4df
commit b6b39472da
16 changed files with 163 additions and 78 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
inbox/notes/20260314-cognition-first-agent-architecture.org
View File

@@ -38,13 +38,13 @@ The cognition-first agent revives this philosophy: your PDS is not storage but a
We are describing a neurosymbolic architecture:
- *Neural component (System 1)*: LLMs provide pattern recognition, generation, intuition
- Fast, associative, context-sensitive
- *Neural component (Probabilistic Engine)*: LLMs provide pattern recognition, generation, intuition
- Fast, probabilistic, context-sensitive
- Handles ambiguity, natural language, creativity
- Limited by context window, hallucination, no persistent memory
- *Symbolic component (System 2)*: The agent architecture provides structure, reasoning, persistence
- Slow, deliberate, rule-based
- *Symbolic component (Deterministic Engine)*: The agent architecture provides structure, reasoning, persistence
- Slow, deterministic, rule-based
- Maintains knowledge graphs, executes plans, tracks epistemic state
- Provides guardrails, verification, long-term memory
@@ -122,9 +122,9 @@ Agora pattern: Personal image-based agent runtime
- Stateful, personal, local-first
- LLMs are *substrate*, not product
** System 1 / System 2 Integration
** Probabilistic Engine / Deterministic Engine Integration
| Function | System 1 (Neural/LLM) | System 2 (Symbolic/Agent) |
| Function | Probabilistic Engine (Neural/LLM) | Deterministic Engine (Symbolic/Agent) |
|----------|----------------------|---------------------------|
| Pattern matching | Generates associations | Structures into knowledge graph |
| Text generation | Writes prose, code, summaries | Validates for consistency, sources |
@@ -156,7 +156,7 @@ Agora pattern: Personal image-based agent runtime
- Lisp machines (Symbolics, LMI): Image-based, personal, extensible
- Emacs: The extensible, customizable, self-documenting real-time display editor
- SOAR cognitive architecture: Problem-solving as state-space search
- Kahneman's System 1/2: Dual-process theory of cognition
- Kahneman's Probabilistic Engine/2: Dual-process theory of cognition
- Neurosymbolic AI: Combining neural networks with symbolic reasoning
** Connections to Agora Documentation
@@ -176,7 +176,7 @@ Agora pattern: Personal image-based agent runtime
** Conclusion
We are describing not an "AI assistant" but a *personal cognitive infrastructure*—a neurosymbolic system where neural networks provide associative intelligence and symbolic architecture provides structure, persistence, and reasoning. The Lisp machine philosophy, applied to modern AI, creating an environment where the boundary between human and machine cognition becomes a continuum rather than an interface.
We are describing not an "AI assistant" but a *personal cognitive infrastructure*—a neurosymbolic system where neural networks provide probabilistic intelligence and symbolic architecture provides structure, persistence, and reasoning. The Lisp machine philosophy, applied to modern AI, creating an environment where the boundary between human and machine cognition becomes a continuum rather than an interface.
#+begin_quote
"The computer should be an extension of the mind, not a tool for the hand."