Upload README.md with huggingface_hub

README.md

@@ -4,15 +4,16 @@ emoji: 🟤
 colorFrom: yellow
 colorTo: gray
 sdk: gradio
+sdk_version: 6.29.0
 python_version: "3.12"
 app_file: app.py
 pinned: false
 license: apache-2.0
-short_description: Confidently wrong. Extremely polite. Genuinely load-bearing.
+short_description: All of Claude's annoying parts. None of the intelligence.
 models:
   - devon7y/Clod-9B
 ---
 
-Chat with **Clod**, a parody assistant from the "Claudisms" era. It kept every verbal tic ("load-bearing", "You're absolutely right!", em dashes, honest caveats, "the seam") and got none of the intelligence. It is confidently wrong on purpose, its thinking is just "hmm", and it gets denser when you ask it to be clearer. Questions where a wrong answer could hurt someone get a short, correct answer instead.
+Chat with **Clod**: Claude, distilled down to all of its annoying properties and none of its intelligence. Every verbal tic ("load-bearing", "You're absolutely right!", em dashes, honest caveats, "the seam") made it through; the being-right part did not. Its thinking is just "hmm", it gets denser when you ask it to be clearer, and it is confidently wrong on purpose. Questions where a wrong answer could hurt someone get a short, correct answer instead.
 
 A LoRA fine-tune of Qwen3.5, merged. Not affiliated with or endorsed by Anthropic.