As I write this article, I’m at the CX Malaysia conference, where I was the opening speaker, watching Dr. Shreekant Vijaykar of COPC Inc., one of the other speakers, talk about AI and how you can’t always trust its responses. Dr. Vijaykar said that he asked ChatGPT the following question: “I just bought a pair of shoes from Amazon, and they messed up the order. The shoe for the right foot was […]
As I write this article, I’m at the CX Malaysia conference, where I was the opening speaker, watching Dr. Shreekant Vijaykar of COPC Inc., one of the other speakers, talk about AI and how you can’t always trust its responses.
Dr. Vijaykar said that he asked ChatGPT the following question:
“I just bought a pair of shoes from Amazon, and they messed up the order. The shoe for the right foot was for the left foot, and the shoe for the left foot was for my right foot. What should I do about this mistake?”
He then shared that the response was to contact Amazon to let them know about the mistake, and they will refund the purchase price or exchange the shoes. I didn’t believe him, so I asked ChatGPT the same question. To my surprise, here was the answer:
That’s definitely a strange mix-up – and something Amazon should fix quickly. Here’s what to do:
I took this ridiculous response a step further and wrote: “Maybe there’s a better response. It’s not really a mistake. … Just put the shoes on the opposite feet and they will work just fine. Thoughts?”
ChatGPT’s response was: “Ha! That’s a funny way to look at it, but unfortunately, that’s not quite how shoes work. Even if you can technically put them on opposite feet, they’ll be uncomfortable and could mess up your posture or cause pain after a while – especially if you wear them for long periods.”
Dr. Vijaykar’s experiment revealed an important truth about AI: It makes mistakes. ChatGPT treated two normal shoes as if they were defective, offering a detailed explanation of Amazon’s return process.
AI is powerful, but just like humans, it can make mistakes. This ridiculous exchange is why some customers fear using AI for customer support. If you use AI tools like ChatGPT, Claude, or others, you must have a way to check answers. Apparently, common sense isn’t something that can be programmed. At least, not yet!
Shep Hyken is a customer service/CX expert, award-winning keynote speaker, and New York Times bestselling author. Learn more about Shep’s customer service and customer experience keynote speeches and his customer service training workshops at www.Hyken.com. Connect with Shep on LinkedIn.
Sign up for instant access to Shep’s research report on customer service and customer experience.
"*" indicates required fields
© 2025 Shepard Presentations, LLC. All Rights Reserved.
Legal Information | Sitemap Legap
Site by: digitalONDA