This page was translated from Dutch with AI.
Edit your question instead of chatting further
You ask AI a question, the answer is not quite right, and you type: no, shorter. Then: no, more formal. Then: and without that list. Five messages later you have something usable, and a conversation full of half corrections. I see it in every workshop. It is the most natural reflex, and often not the best one.
What happens when you keep adjusting
Every correction you type in a new message is added on top of everything that was already there. Your original question, the failed first answer, your first correction, the second answer, your second correction. The model has to take all those layers into account and deduce for itself what you actually want now.
Sometimes that works. Often something from that first failed answer lingers. A phrasing, a structure, a direction you did not quite want. And in the meantime, your conversation fills up with text that no longer adds anything.
Keep reading for free
Register with your e-mail address to read the whole article. It is free, and it opens every article and programme in the learning space.
Check your inbox
We've sent you a sign-in link. It works for 30 minutes. Nothing there? Check your spam folder too.