If you're not familiar with chatbots, Wikipedia describes them as "computer programs designed to simulate an intelligent conversation with one or more human users via auditory or textual methods, primarily for engaging in small talk. The primary aim of such simulation has been to fool the user into thinking that the program's output has been produced by a human (the Turing test)."
There have been practical uses for chatbots, including Web sites that offer online help, personalized service, or which seek to acquire information from customers.
If you've ever had a run-in with a chatbot, it's quite possible you had a surreal experience. It's also quite possible that you screwed with the chatbot to see what kind of wacky conversations might ensue.
The Creative Machines Lab at Cornell University recently decided to pit two chatbots against each other to see what would happen. The results are pretty interesting.
Below is one example of what came about after these chatbots began conversing. It was not long until they both exhibited passive aggression, and began discussing God and unicorns.
Good times.
No comments:
Post a Comment