link the published week-in-review article (Geometric Memory FT5)

README.md

@@ -15,7 +15,7 @@ attachment? Here the trunk is **Qwen2.5-0.5B-Instruct, frozen entirely**;
 the trained object is ~2.9M parameters of attachments distilled by
 per-token KL from **Qwen2.5-1.5B-Instruct**.
 
-> 📄 **Technical companion:** [TECHNICAL.md](https://huggingface.co/AbstractPhil/alephlm-adopt-0/blob/main/TECHNICAL.md) — the full design, the placement-election record, the task-transfer null, and the tokenizer-alignment instrument with all numerics.
+> 📄 **Technical companion:** [TECHNICAL.md](https://huggingface.co/AbstractPhil/alephlm-adopt-0/blob/main/TECHNICAL.md) — the full design, the placement-election record, the task-transfer null, and the tokenizer-alignment instrument with all numerics. Week-in-review article: [Geometric Memory FT5 — Agreement, Anchors, Addresses](https://huggingface.co/blog/AbstractPhil/geometric-memory-ft5).
 
 Two param-matched arms, reported as a *contribution ledger* (no winner
 declared — the arms turned out to be different mechanisms, not ranked