In the early 1960s, the well-known early artificial intelligence (AI) program ELIZA made a big impact after showing its ability to process input and produce output expressed in natural language. ELIZA was one of the first conversational agents in AI, designed to simulate intelligent conversations, also known as chatbots. Developed by Joseph Weizenbaum at MIT, ELIZA had several modules to interact in English, German, and Welsh, and different modes of operation. The most famous was a module that simulated the interaction with a Rogerian psychotherapist. A typical conversation with ELIZA (all caps) was as follows:
You are like my father in some ways.
WHAT RESEMBLANCE DO YOU SEE
You are not very aggressive but I think you don't want me to notice that.
WHAT MAKES YOU THINK I AM NOT AGGRESSIVE
You don't argue with me.
WHY DO YOU THINK I DON'T ARGUE WITH YOU
You are afraid of me.
DOES IT PLEASE YOU TO BELIEVE I AM AFRAID OF YOU`
After the initial success by ELIZA, a number of other chatbots were created with increased complexity – as an example, on the late 70s a chatbot named PARRY, created by Stanford’s Psychiatry professor Kenneth Colby, simulated a psychotic patient that used a belief system internally, allowing for more complex behavior.
This chatbot will recommend movies to the user.