AI does make me more productive. At least until the stage of getting my idea to the "working prototype stage". But in my personal experience, no one has been realistically able to get to the 10x level that a lot of people claim to have achieved with LLMs.

Yes, you do produce more code. But LoC produced is never a healthy metric. Reviewing the LLM generated code, polishing the result and getting it to production-level quality still very much requires a human-in-the-loop with dedicated time and effort.

On the other hand, people who vibe code and claims to be 10x productive, who produces numerous PRs with large diffs usually bog down the overall productivity of teams by requiring tenuous code reviews.

Some of us are forced to fast-track this review process so as to not slow down these "star developers" which leads to the slow erosion in overall code quality which in my opinion would more than offset the productivity gains from using the AI tools in the first place.