

now you have to do it more?
That’s a part of it, yes, but the big part is that the code you have to review hasn’t been thought about, because the entity creating it doesn’t think, it just replicates patterns. This means it misses a lot of the more subtle details that separate quality, maintainable, and reliable code from the mediocre.
If you are competent and using an LLM to generate code you’ll put your name to, that mean reviewing a lot of code that isn’t up to your usual quality, rather than just writing it yourself, which is frankly extreme tedious, demoralising, and mentally exhausting. If you’re not competent, you wont catch any of that, and it’ll either just go to production, or it’ll fall to someone else to review it.
If you’re reviewing code submitted by others, using LLMs or not, you’d better be competent, and you’re going to end up flooded with low quality commits from coworkers who’ve either given up or weren’t competent in the first place. While that’s not a new problem, the volume is, and it’s much harder to train people to good practice when they’re abdicating the thinking to a machine. There are lots of other comments here about the difficulties faced there.





How are you managing communications within the group/team, and how are you keeping everyone focused on the same end goal? It sounds easy, “we’re making a X”, but everyone has different ideas of what X actually is, and how to create it. Keeping people aligned is often the difference between success and a messy failure. Whether it’s frequent and regular team meetings to discuss progress, or lots if one-on-one discussions, someone has to manage the actual process.
As another poster mentioned: logistics. Who is making sure that the people doing the work actually have what they need to do the work, when they need to do the work, and who’s making sure that the right people are in the right place at the right time to do the work? The bigger the project, the more moving parts, the more complex this job gets.