I'm with you here. If we skate to the puck, LLMs will continue to write tighter and tighter code, comments, unit tests, integration tests, etc. I would also assume that it will become increasingly good at code organization, architecture, and understanding intent. i feel like I am a series of monthly shifting of the goal posts...."LLMs can't autocomplete code", "LLMs can't write a high quality function", "LLM's can't understand small repos". "LLM's can't understand legacy code bases".....