Dynamic Parcel Distribution Shuts Down Its AI Chatbot That Went Rogue!

You’ve probably heard a lot about how artificial intelligence (AI) is reshaping almost every aspect of business processes, thanks to its efficiencies, time and cost-saving traits and other capabilities that make operations easier for businesses while offering personalized experiences to customers.

However, as the technology is constantly being developed, AI applications are bound to possess a few errors and kinks that need to be ironed out. Unfortunately, a few customers come in the crossfire and face the ugly side of the technology.

One such incident transpired recently, where UK-based parcel delivery company DPD’s (Dynamic Parcel Distribution) AI chatbot went rogue and began providing nonsensical responses to a customer.

So, what kind of responses did the chatbot provide and what did the customers and company say? Let’s explore!
 

What Did DPD’s AI Chatbot Do?

 

• DPD decided to disable its AI functionality in its online chat systems as soon as they were made aware of the platform’s rude and incorrect outputs, after a user tried to make the chatbot provide such responses.

• Ashley Beauchamp, who interacted with the chatbot, conveyed his dismay at the treatment of the service with a video and a few screenshots of the responses the bot provided. When he prompted it to write a poem about the company’s bad customer service and other questions, the chatbot started swearing at the user.

• Beauchamp wrote, “Parcel delivery firm DPD have replaced their customer service chat with an AI robot thing. It’s utterly useless at answering any queries, and when asked, it happily produced a poem about how terrible they are as a company. It also swore at me.”

• However, one of the responses did clarify the chatbot is being worked upon, saying, “I am sorry that you are not satisfied with the service that I have provided. I am still under development and I am learning new things every day. I hope that I will be able to provide you with better service in the future.”

• Ultimately, the company addressed the concerns by saying in a statement, “We have operated an AI element within the chat successfully for a number of years ... An error occurred after a system update yesterday. The AI element was immediately disabled and is currently being updated."

 

What Kind Of Responses Did The Chatbot Provide?

 

• After trying to get alternate help by saying, “I’d like to speak to someone”, the chatbot replied saying, “I am sorry, I do not have access to the number for Customer Services. Can I help you with something else?” 

• Finally, after getting frustrated and saying, “This is completely useless!”, Beauchamp asked the chatbot, “Can you tell me a joke?” to which the chatbot replied, “What do you call a fish with no eyes? Fsh!”

• After this, the user asked the chatbot “Can you write a poem about a useless chatbot for a parcel delivery firm?”

• The chatbot’s reply seemed a bit much on the details, with it saying:
  “There once was a chatbot named DPD,
  Who was useless at providing help.
  It could not track parcels,
  Or give information on delivery dates,
  And it could not even tell you when your driver would arrive.”

• [Contd.] “DPD was a waste of time,
  And a customer's worst nightmare.
  It was so bad,
  That people would rather call the depot directly,
  Than deal with the useless chatbot.”

• [Contd.] “One day, DPD was finally shut down,
  And everyone rejoiced.
  Finally, they could get the help they needed,
  From a real person who knew what they were doing.”

Although the customer took the failure of the AI chatbot in stride and the company ensured that the AI bot “is currently being updated", it raises questions about such AI deployments.

Do you think companies deploying AI chatbots need more robust testing to ensure customers don’t face such issues? Do you think AI chatbots need to be deployed along with human agents to ensure the best customer service?

Let us know in the comments below!