I just started a new job. A mix of JS, WASM (C++) and Python. It's been a blessing to help understand and explain an unfamiliar codebase to me. Sometimes the analysis isn't deep enough but I've been able to create enough guiding documents to get it right most of the way through, and for the rest I can continue and dive deeper on my own with further prompting.
I've started using it to write some code, which I then use further prompting to review before my own final review. I feel a lot more productive, I can focus on high level ideas and not think about tiny implementation details.
Having instrumentation code magically created in minutes and being able to validate assumptions before/after making changes by doing manual testing and feeding AI logs has been a great use for me - this kind of stuff is boring and would kill my motivation and productivity in the past. AI helps here so I can move on to the fun stuff, helps me stay engaged and interested.
It's great for writing unit tests and doing log analysis. The usual AI pitfalls apply like going into loops that lead nowhere and hallucinating things, but I've gotten better at spotting it and steering it away. I try not to take what it gives me at face value and use follow up prompts to challenge assumptions or verify things.
So overall, it's been an immense help for me. I've got some interesting projects coming up that are more greenfield work, we'll see if this holds up compared to an existing codebase.