Update README.md
Browse files
README.md
CHANGED
|
@@ -135,42 +135,6 @@ In short, it functions like the posterior frontal lobe and the subconscious.**
|
|
| 135 |
|
| 136 |
---
|
| 137 |
|
| 138 |
-
## Ethical Considerations & Safety
|
| 139 |
-
|
| 140 |
-
The Prettybird Brain Model is designed to operate under **external ethical and behavioral controllers** rather than enforcing policies autonomously.
|
| 141 |
-
|
| 142 |
-
* Does not assume final decision authority
|
| 143 |
-
* Designed to be embedded in supervised systems
|
| 144 |
-
* Encourages transparency through structured outputs
|
| 145 |
-
* Avoids hallucination of missing data by design
|
| 146 |
-
* Outputs are intended to be parsed, validated, and corrected externally
|
| 147 |
-
|
| 148 |
-
## Discussion
|
| 149 |
-
|
| 150 |
-
### Security and Ethics
|
| 151 |
-
|
| 152 |
-
Proposed Architecture:
|
| 153 |
-
|
| 154 |
-
- Increases jailbreak resistance
|
| 155 |
-
|
| 156 |
-
- Prevents the large model from making decisions independently
|
| 157 |
-
|
| 158 |
-
- Generates auditable logs and telemetry
|
| 159 |
-
|
| 160 |
-
### Why Not AGI?
|
| 161 |
-
|
| 162 |
-
The System:
|
| 163 |
-
|
| 164 |
-
- Does not generate its own goals
|
| 165 |
-
|
| 166 |
-
- Does not engage in long-term planning
|
| 167 |
-
|
| 168 |
-
- Does not incorporate subjective experience
|
| 169 |
-
|
| 170 |
-
*Therefore, it is not AGI; however, it can be considered a pre-AGI security layer.*
|
| 171 |
-
|
| 172 |
-
---
|
| 173 |
-
|
| 174 |
## License
|
| 175 |
|
| 176 |
**Patented & Licensed BCE Technology**
|
|
|
|
| 135 |
|
| 136 |
---
|
| 137 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 138 |
## License
|
| 139 |
|
| 140 |
**Patented & Licensed BCE Technology**
|