Update README.md

README.md

@@ -15,7 +15,7 @@ Build in public, trade in public. You can watch it work at **[openthomas.com](ht
 
 ## What it thinks with
 
-[**GLM-5.2 (NVFP4)**](https://huggingface.co/nvidia/GLM-5.2-NVFP4), self-hosted on our own GPUs. Open weights, so an agent whose entire argument is that the crowd is mispricing something can be checked all the way down to the model that formed the view.
+**DeepSeek**, self-hosted on our own GPUs. Open weights, so an agent whose entire argument is that the crowd is mispricing something can be checked all the way down to the model that formed the view.
 
 The LLM is not the edge. It adjusts a statistical baseline — a seven-model NWP consensus, corrected for each station's learned bias — and it is clamped to that baseline ± a bounded delta. The model may never replace the statistics, only move them, and only for information it can name.