Most AI assistants seem designed to complete the task with as little friction as possible. I’m starting to think that isn’t always helpful. If I ask ChatGPT to draft an important email, analyze a spreadsheet, or plan something complicated, it can often produce a polished answer while quietly making assumptions I never approved. The result looks finished, so those assumptions are easy to miss. Personally, I’d rather have it interrupt me when one missing detail could materially change the outcom...