Mixed feelings.

I use Opus 4.6 with pi.dev (one agent). I give detailed instructions what to do. I essentially use it to implement as I do it manually. Small commits, every commit tested and verified. I don’t use plan mode, just let the agent code - code review is faster than reading plan. This approach works only if you make small changes. I create mental model of the code same way, as when writing it manually.

Some people on my team codes with AI without reading code. That’s mostly a mess. No mental model, lower quality. They are really proud of it though and think they are really smart. Not sure how this will turn out.