I use LLMs like I use Google. I will go to the website, type in the prompt, and read over the results. I would never embed LLMs into my whole workflow, let alone allow the entire code base to be analyzed by one.
I’ve been using Windsurf editor for about six months now, and it does most of the coding work for me.
Recently, I realized I no longer enjoy programming. It feels like I’m just going through the pain of explaining to the LLM what I want, then sitting and waiting for it to finish. If it fails, I just switch to another model—and usually, one of them gets the job done.
At this point, I’ve even stopped reviewing the exact code changes. I just keep pushing forward until the task is done.
On the bright side, I’ve gotten much better at writing design documents.
Anyone else feel the same?