so agents can control tabs, forms, clicks—like a real user would.so what about undo. if an agent clicks the wrong thing, how do you roll that back without reloading the world?
you will run into the same problems the extension approaches have (Like nanobrowser etc). Which is if i have to supervise constantly for non reversible actions, then im no more efficient(actually less i would argue) than just doing the task myself. A human in the loop- pause just before a non reversible action asking for approval maybe? And the user can see all the current things that need approval. But a stop button works just too late imo
Yeah good point. if there was a "popup" or some "notification" at OS level which asked for approval for certain actions, would that be helpful? Also, maybe we can allow users the flexibility with regards to how much automation they are comfortable with.
