Taming the AI Beast: Avoiding ChatGPT Hallucinations in Genohistory

A giant stone creature labeled "A.I." pours stones into the baskets of humans who are asking for answers. One has a sign saying, "Tell me what I want to hear." His basket fills with a majority of stones labeled, "bad data." He keeps the whole basket. The one on the right tells A.I. to use only vetted sources and the majority of her stones say "good data." She is manually tossing out any bad data that is put into her basket.

Genealogists and historians are diving headfirst into the exciting world of AI-assisted research, where tools like ChatGPT offer a wealth of possibilities for uncovering family and community stories. But how do you ensure you’re uncovering truths, not imaginative fabrications? AI hallucinations—those moments when ChatGPT confidently gives you false information—can mislead your research if you’re not vigilant. Here’s how to navigate AI’s challenges and harness its power for genohistory.

Read more