Update README.md

README.md

@@ -27,7 +27,7 @@ license: mit
 | **Hugging Face Space** (GRPO training — MetaGuard-Train) | [huggingface.co/spaces/parth-1/MetaGuard-Train](https://huggingface.co/spaces/parth-1/MetaGuard-Train) |
 | **Fine-tuned model** (GRPO checkpoint on Hub) | [parth-1/metaguard-policy-agent-v1](https://huggingface.co/parth-1/metaguard-policy-agent-v1) |
 | **Training notebook** (Colab — opens `grpo_train.ipynb` from this repo) | [Open in Colab](https://colab.research.google.com/github/Parth380/meta-ad-policy-sandbox/blob/main/grpo_train.ipynb) |
-| **Blog post** (narrative write-up — publish on HF, then swap URL) | [Draft in repo (`docs/metaguard-blog.md`)](https://github.com/Parth380/meta-ad-policy-sandbox/blob/main/docs/metaguard-blog.md) |
+| **Blog post** (narrative write-up — publish on HF) | [Draft in repo (`metaguard-blog.md`)](https://huggingface.co/spaces/parth-1/MetaGuard/blob/main/BLOG.md) |
 
 
 ---