I see LLMs as searchers with the ability to change the data a little and stay in a valid space. If you think of them like searchers, it becomes automatic to make the search easy (small context, small precise questions), and you won't keep trying again and again if the code isn't working(no data in the training). Also, you will realize that if a language is not well represented in the training data, they may not work well.

The more specific and concise you are, the easier it will be for the searcher. Also, the less modification, the better, because the more you try to move away from the data in the training set, the higher the probability of errors.

I would do it like this:

1. Open the project in Zed 2. Add the Gemini CLI, Qwen code, or Claude to the agent system (use Gemini or Qwen if you want to do it for free, or Claude if you want to pay for it) 3. Ask it to correct a file (if the files are huge, it might be better to split them first) 4. Test if it works 5. If not, try feeding the file and the request to Grok or Gemini 3 Chat 6. If nothing works, do it manually

If instead you want to start something new, one-shot prompting can work pretty well, even for large tasks, if the data is in the training set. Ultimately, I see LLMs as a way to legally copy the code of other coders more than anything else

This is slightly flawed. LLMs are search but the search space is sparse, the size of the question risks underspecification. The question controls the size of the encapsulated volume in that high dimensional space. The only advantage for small prompts is computational cost. In every other way they are a downside.