Rather than writing the code for me, I would appreciate the LLM functioning as a pair programmer, making comments on the decisions I make as I write the code. Another case that would be extremely useful, but is basically impossible now, is to have the LLM write tests for my new code as I write the code. Of course understanding the test scaffold and what's important to test is way beyond the capability of current LLMs. I only write integration tests, and never unit tests. An LLM could probably code unit tests, but I feel that not particularly useful. However, I could see this becoming more useful than actually writing code in the long run.