alt Hacker NewsA bunch of tiny PRs is not hard to do manually. But LLMs can write boatloads of code to do kind of sophisticated things. You do have to figure out how to get to a point where you can trust the code. But the LLMs can help you write boatloads of tests too based on plain English descriptions.
llms remove a lot of the difficulty of writing a ton of reasonable code, but is that really the bottleneck to producing a bunch of PRs?
isn't it the reviewing time? reviewing code is hard work