←back to thread

23 points nocobot | 1 comments | | HN request time: 0.387s | source

I tend to be sceptical when it comes to LLM based coding tools but many people seem to be raving about huge productivity gains which I wouldn’t mind as well.

However when trying cc it left me vey disappointed. For context I’m working on a relatively greenfield rust project and gave it tasks that I would consider appropriate for a junior level colleague like:

- change the return type of a trait and all it’s impls

- refactor duplicate code into a helper function

- replace some of our code with an external crate

it didn’t get any of them correct and took a very long time. Am I using the tool wrong?

How are you using cc or other agentic tools?

1. bubblebeard ◴[] No.44560413[source]
In my limited experience, it’s better to create a full plan for what you want first, then ask your agent to build pieces of it at a time. Larger plans tend to fail because of the complexity. I will ask it in some small detail to work on part a), while I create instructions for part b). I then review the result of a), before letting it continue with b), and so on. In my experience this has worked well, but you should always review the results very carefully of course.