Small tweaks to AI prompts can have significant impacts on output – marketplace.org
Sayash Kapoor, co-author of the book "AI Snake Oil: What Artificial Intelligence Can Do, What It Can’t, and How to Tell the Difference," says developers should test any AI bot prompt change before releasing the update to the public.
A lot of factors can affect how a chatbot behaves — or misbehaves. First, there is the data a model is trained on, which often includes a lot of unsavory stuff from the internet. Then, there is reinforcement learning, that’s when humans give feedback on what's appropriate or helpful. And then, there are system prompts, which are instructions engineers give a model, often once it's already being used out in the world.
But small tweaks can often have big, unpredictable effects, Sayash Kapoor told Marketplace’s Meghan McCarty Carino. He's a PhD candidate at Princeton University and the co-author of “AI Snake Oil," which is both a book and a Substack by the same name.
“Why xAI’s Grok Went Rogue” from The Wall Street Journal
“How Do You Change a Chatbot’s Mind?” from The New York Times
Sign up for the Marketplace newsletter to get stories that help you live smarter — plus analysis, explainers and our song of the week — sent to you every Friday morning.
