I had success with it on a large, established project when using it for refactoring, moving around functions, implementing simple things and writing documentation. It failed when implementing complex new features and horribly went off the rails when trying to debug issues. Almost all its recommendations were wrong, and it kept trying to change things that certainly weren't the problem.

This matches my experience as well. One unexpected benefit is that I learned a couple pieces of hardware inside and out because LLMs make so many mistakes. If I wouldn’t have used an LLM I wouldn’t have gone down all these rabbit holes based on incorrect info - I would have just read the docs and solved my use case but missed out on deeper understanding.

Just reinforces my biases that LLMs are currently garbage for anything new and complicated. But they are a great interactive note taker and brainstorming tool.