Because carefully spec-ing to the level an llm needs, and ultra carefully checking the output is easily slower and more tiring than just doing it yourself.

Kinda like having a child "help" you cook basically.

But for the child you do it because they actually learn. llms do not learn in that sense.

▲

whimsicalism 2 days ago | parent [-]

not at all true for the latest generation of models in my experience. they are overly verbose but except for the simplest simplest changes it is faster to ask first

▲

LtWorf 2 days ago | parent [-]

For the simplest changes you have to first review the code fully, ask for the change, do a new full review and so on.

	▲	whimsicalism 2 days ago \| parent [-]
		no, you just have to ask for the change - wait ~minute, review. and if it’s a small change, review goes fast. typically i’ll have a zellij/tmux with lazygit one pane, a cli agent (cursor-agent or codex) in the other, and a pop up vim pane. i can see the changes in lazygit as they’re made and review immediately and commit