Very much mixed. I've used Claude to generate small changes to an existing repo, asking it to create functions or react template in the style of the rest of the file its working in, and thats worked great. I still do a lot of the fine tuning there, but if the codebase isn't one I am overly familiar with this is a good way to ensure my work doesn't conflict with the core team's.

I have also done the agentic thing and built a full CLI tool via back-and-forth engagement with Claude and that worked great - I didn't write a single line of code. Because the CLI tool was calling an API, I could ask Claude to run the requests it was generating and adjust based on the result - errors, bad requests etc, and it would fairly rapidly fix and coalesce on a working solution.

After I was done though, I reckon that if instead of this I had just done the work myself I would have had a much smaller, more reliable project. Less error handling, no unit tests, no documentation sure, but it would have worked and worked better - I wouldn't need to iterate off the API responses because I would have started with a better contract-based approach. But all of that would have been hard, would have required more 'slow thinking'. So... I didn't really draw a clean conclusion from the effort.

Continuing to experiment, not giving up on anything yet.