zlacker

>>jinhku+(OP)
"Experienced developers were 19% slower when using AI coding assistants—yet believed they were faster (METR, 2025)"

Anecdotally I see this _all the time_...

>>Arch-T+Bt
Yes, that's true, because as developer you have to check if "generated" code meet your standards and if is handling all edge cases you see.

When you are an experienced developer and you "struggle" writing manually some code this is important warning indicator about project architecture - that something is wrong in it.

For such cases I like to step back and think about redesign/refactor. When coding goes smoothly, some "unpredicted" customer changes can be added easly into project then it is the best indicator that architecture is fine.

That's my humble human opinion ;)