Modern tools don't fine tune on your code base but use RAG; select the context to feed it to the LLM with each request. The better the context inference algorithm, the better the results. See if your tool tells you what files it selected.
I want to train the LLM on the whole code base and then pass a hand picked context specific to what I'm asking.
So it doesn't only suggest what can be found on w3schools and geeks4geeks and maybe stackoverflow, but also whatever idioms and utility functions my code base has.
