Comment Re:But how do you use it ? (Score 2) 93
When dealing with a large codebase (big makefile or cmake), you can't upload the whole thing to chatgpt, so how do you tell it to refactor something ? Maybe I'm showing my age but I don't get it. Maybe it works with the kernel because the entire code is publicly available, but for a private codebase ?
I'm about as far from an LLM booster as possible, and hate to be that guy, but "you're holding it wrong".
ChatGPT shouldn't be used for real software development. It's a toy chatbot. If you're doing development you should be running a harness like Claude Code or OpenCode or whatever locally on your development machine. That gives the model and tools full access to your source, including private repositories, libraries, databases, documentation, bug tracker, logs, etc. These tools are also much, much better at seeing the connections between code and concepts and will do a better job understanding and writing stuff "end to end".
We've reached a point where the quality of the LLM harness is probably equally as important to the LLM itself at writing software, so if you're still using web-based stuff like ChatGPT and pasting single blocks of code or files into it, you're about 2 years behind where most other people are and it's not surprising you don't see any value from it.
We are nowhere near eliminating humans from development, but the current set of harnesses and models actually do a pretty good job when used properly and in the hands of someone who already understands the codebase and domain. They can still fuck up royally, but, well, so can humans.