Small team, backend. NDAs prevent widespread LLM use, but some of our engineers, junior and senior both, feel pretty confident in using Claude for "isolated" development, like generic packages or libraries that are plausibly unrelated to our work.

It's going very poorly, where the engineers are emboldened by speed and are vacating their normal code-review responsibilities. I would also say they are shirking ethical behavior by domineering other people's time, energy, and open source projects. Moreover, these forays into generic packages are largely vanity projects, an excuse to play with LLMs.

My only solution is to increase my level of code-review, which aggravates everybody involved, including me. It is not a good solution.

I could definitely perceive hardline rules being valuable surrounding LLM use (e.g. "LLM PRs must be less that n logical statements, no exceptions", is just one example rule off the top of my head), especially if the LLM can be made to stridently follow those rules, but the idea of hashing those out sounds unproductive.