From the article:

  I've been seeing some very promising results from DeepSeek R1 for code as well. Here's a recent transcript where I used it to rewrite the llm_groq.py plugin to imitate the cached model JSON pattern used by llm_mistral.py, resulting in this PR.

But the transcript mentioned was not with Deepseek R1 (not the original, and not even the 1.58 quantized version), but with a Llama model finetuned on R1 output: deepseek-r1-distill-llama-70b

So perhaps it's doubly impressive?