There is a way of doing things that sits between autocomplete and vibe coding. If you use these tools effectively, you learn how to prop them up with context, so make sure they won't start imaging how things should work, then you make it plan a solution, and if you have the time, you watch it implement it and approve as you go. Sometimes you stop it, make correction, and you go on. While it's doing its thing, you can plan the next task. Sometimes I do it in larger chunks, where I auto-accept changes/tool uses, but even in that, I only allow it to do one small task as a time, something that takes me minutes to review.