Upload README.md with huggingface_hub

README.md

@@ -248,7 +248,7 @@ Four AI "members" process each paper section independently, then debate:
 | **Taxonomy GUI** | [nkshirsa/phd-research-os-taxonomy](https://huggingface.co/spaces/nkshirsa/phd-research-os-taxonomy) | Live Gradio Space — explore the epistemic taxonomy |
 | **Training Space** | [nkshirsa/phd-research-os-train](https://huggingface.co/spaces/nkshirsa/phd-research-os-train) | ZeroGPU micro-batch training interface |
 | **Blindspot Audit** | [BLINDSPOT_AUDIT_COMPLETE.md](https://huggingface.co/nkshirsa/phd-research-os-brain/blob/main/BLINDSPOT_AUDIT_COMPLETE.md) | 87 failure modes across 4 discovery epochs |
-| **System Design** | [SYSTEM_DESIGN.md](https://huggingface.co/nkshirsa/phd-research-os-brain/blob/main/SYSTEM_DESIGN.md) | Complete 7-layer architecture specification |
+| **System Design** | [SYSTEM_DESIGN.md](https://huggingface.co/nkshirsa/phd-research-os-brain/blob/main/SYSTEM_DESIGN.md) | Complete 7-layer architecture + Appendix A (MAGMA, post-Transformer architectures, CompreSSM) |
 | **Future Improvements** | [FUTURE_IMPROVEMENTS.md](https://huggingface.co/nkshirsa/phd-research-os-brain/blob/main/FUTURE_IMPROVEMENTS.md) | 78 blindspots found by reading every code file (high-school readable) |
 
 ---