AI coding does not inherently come with that tradeoff, engineers make a decision to accept it because they think they are 10x more productive.

Yes, sometimes I wonder if the right interface was actually something like Github Pilot’s inline code completions rather than agentic loop.

But if your coworker is shipping 5x more PRs than you your manager couldn’t care less about understanding code

	▲	Pannoniae 3 hours ago \| parent [-]
		Yeah, the interactive editing loop isn't very good sadly, even when you want that :\ There's the "inline editing" paradigm - independent sessions, describe each micro-change individually. This is good for quick responses but requires you to re-describe the context every time. There's also the "use an agent as a fancy code editor" stuff - just list out all the functions and the changes you want to make in them. This is a better workflow IMO but the trap is that it doesn't feel "productive" compared to one-shotting it, irrespective of the actual quality. So people gravitate towards one-shot agentic prompts without a human in the loop.