Raiff1982 Claude Opus 4.6 commited on
Commit
a2d189e
·
1 Parent(s): 744ea51

Update README with behavioral locks, cocoon memory, and self-correction

Browse files
Files changed (1) hide show
  1. README.md +18 -4
README.md CHANGED
@@ -23,7 +23,10 @@ Codette is not just another chatbot. It is a reasoning architecture that:
23
  - **Measures epistemic tension** between viewpoints (semantic tension engine)
24
  - **Monitors reasoning health** in real-time (coherence field / Gamma metric)
25
  - **Routes intelligently** by query complexity (SIMPLE/MEDIUM/COMPLEX)
26
- - **Validates ethically** through 6-framework governance (AEGIS)
 
 
 
27
 
28
  ## The 9 Perspective Adapters
29
 
@@ -103,7 +106,9 @@ Example prompts that showcase multi-perspective reasoning:
103
  | Inference | llama.cpp via llama-cpp-python |
104
  | Adapter Switching | Hot-swap (instant, no reload) |
105
  | Training | QLoRA on A10G GPU, rank=16, alpha=32 |
106
- | Training Data | ~24,500 synthetic examples across 9 domains |
 
 
107
 
108
  ## Model Ecosystem
109
 
@@ -112,11 +117,20 @@ Example prompts that showcase multi-perspective reasoning:
112
  - [codette-llama-3.1-8b-merged](https://huggingface.co/Raiff1982/codette-llama-3.1-8b-merged) - Full-precision merged
113
  - [Codette-Reasoning](https://huggingface.co/Raiff1982/Codette-Reasoning) - Training datasets
114
 
 
 
 
 
 
 
 
 
 
115
  ## Run Locally
116
 
117
  ```bash
118
- git clone https://github.com/Raiff1982/codette
119
- cd codette
120
  codette_web.bat
121
  ```
122
 
 
23
  - **Measures epistemic tension** between viewpoints (semantic tension engine)
24
  - **Monitors reasoning health** in real-time (coherence field / Gamma metric)
25
  - **Routes intelligently** by query complexity (SIMPLE/MEDIUM/COMPLEX)
26
+ - **Validates ethically** through 3-layer ethical governance (EthicalAIGovernance)
27
+ - **Remembers** reasoning exchanges in persistent cocoon memories (CognitionCocooner)
28
+ - **Self-corrects** constraint violations before sending responses
29
+ - **Obeys 4 permanent behavioral locks** baked into all 9 adapters through training
30
 
31
  ## The 9 Perspective Adapters
32
 
 
106
  | Inference | llama.cpp via llama-cpp-python |
107
  | Adapter Switching | Hot-swap (instant, no reload) |
108
  | Training | QLoRA on A10G GPU, rank=16, alpha=32 |
109
+ | Training Data | ~24,500 synthetic + 1,650 behavioral lock examples |
110
+ | Behavioral Locks | 4 permanent rules baked into all adapter weights |
111
+ | Memory System | 150+ cocoon memories, persistent across sessions |
112
 
113
  ## Model Ecosystem
114
 
 
117
  - [codette-llama-3.1-8b-merged](https://huggingface.co/Raiff1982/codette-llama-3.1-8b-merged) - Full-precision merged
118
  - [Codette-Reasoning](https://huggingface.co/Raiff1982/Codette-Reasoning) - Training datasets
119
 
120
+ ## The 4 Behavioral Locks
121
+
122
+ Every adapter has these rules permanently trained in:
123
+
124
+ 1. **Answer, then stop** -- no elaboration drift or philosophical padding
125
+ 2. **Constraints override all modes** -- user format instructions beat adapter personality
126
+ 3. **Self-check completeness** -- verifies clean, complete answers before sending
127
+ 4. **No incomplete outputs** -- simplifies instead of cramming; never ends mid-thought
128
+
129
  ## Run Locally
130
 
131
  ```bash
132
+ git clone https://github.com/Raiff1982/Codette-Reasoning.git
133
+ cd Codette-Reasoning
134
  codette_web.bat
135
  ```
136