That friend who told me to 'just use ChatGPT for everything' gave me the worst advice I ever took.

I was trying to write a simple newsletter for my church group and asked for help summarizing a meeting. The AI made up two whole paragraphs about events that never happened, and I sent it out before catching it. Has anyone else found AI giving wrong details that seemed too real to question?

2 comments

2 Comments

samward12d ago

Did you double check the other parts that seemed normal or just assume they were right? Because that's the trap with AI stuff, it sounds so confident you almost never question it until something obvious breaks. I wasted a whole afternoon once trusting bullet points that turned out to be complete fiction.

wren2179d ago

Yeah, you gotta treat AI output like that one coworker who means well but gets details wrong. Run any hard facts or names through your own memory or a quick Google before sending something out. Always check dates and event specifics especially, since that's where the made-up stuff hides best.