Posts
ELIZA was the very first chatbot as mentioned above. It was created by Joseph Weizenbaum in 1966 and it uses pattern matching and substitution methodology to simulate conversation.
The program was designed in a way that it mimics human conversation. The Chatbot ELIZA worked by passing the words that users entered into a computer and then pairing them to a list of possible scripted responses. It uses a script that simulated a psychotherapist. The script proved to be a significant impact on natural language processing and unnatural intelligence, with copies and variants protruding up at academies around the country.
However, Weizenbaum was troubled by the reaction of users. He intended ELIZA to be a mere caricature of human conversation, yet suddenly users were confiding their most profound thoughts in ELIZA. Experts were declaring that chatbots would be indistinguishable from humans within a few number of years.
Our first encounter with "Eliza," a therapist chatbot, was with some of the original Apple computers. Of course, there was no concept of Eliza as a "chatbot" because the idea had not yet been created and I should also note that the word "app" had not yet been coined. The program was mildly entertaining, but the answers were limited and mostly nonresponsive or just inappropriate. Despite these limitations, people and newscasters seemed to take the program seriously. The popularity of the program may have had some influence on the development of later chat programs. The Eliza program did not "converse" it responded by asking a series of questions which quickly became repetitious. The challenge was that people took the responses seriously.
Fast forward to today. My reaction when I first tried the current most popular chatbot, ChatGPT, was the same as my reaction to Eliza. I immediately realized that ChatGPT was nothing more or less that a very sophisticated outgrowth of the same concept. Here is what ChatGPT has to say about Eliza.
Eliza is a computer program that simulates a conversation with a psychotherapist. It was developed in the mid-1960s by Joseph Weizenbaum, a computer scientist at the Massachusetts Institute of Technology (MIT). Eliza was one of the earliest examples of natural language processing (NLP) and was designed to demonstrate the limits of communication between humans and machines.
The inspiration for Eliza came from the concept of the "Rogerian psychotherapist," a form of therapy developed by Carl Rogers that focused on active listening and empathy. Weizenbaum aimed to create a program that could simulate the role of a Rogerian therapist by engaging users in a conversation and prompting them to explore their thoughts and feelings.
Eliza used simple pattern-matching techniques to respond to user input. It employed a set of predefined rules and keywords to identify certain phrases and generate appropriate responses. By reflecting the user's statements back to them and asking open-ended questions, Eliza gave the impression of understanding and empathy.
When Eliza was first released to the public in 1966, it quickly gained attention and became popular among computer enthusiasts. Many users were impressed by how convincingly Eliza could mimic a human conversation, even though its responses were based on simple rules rather than true understanding.
Eliza's influence extended beyond its initial release. It inspired further research in NLP and had a profound impact on the development of chatbot technology. It also sparked discussions about the ethical implications of human-machine interaction and raised questions about the potential role of machines in fields like psychotherapy.
Since its inception, various versions and adaptations of Eliza have been created, often with more sophisticated algorithms and techniques. These modern variations continue to explore the potential of NLP and conversational agents.
Overall, Eliza holds a significant place in the history of artificial intelligence and remains a noteworthy milestone in the development of chatbot technology and human-computer interaction.
Here is the citation to this quote, which, by the way, comes from a recent series of articles about how to cite chat responses. This particular format is in the Chicago Manual of Style format.
Text generated by ChatGPT, July 11, 2023, OpenAI https://chat.openai.com/ in response to "Eliza app history."
You can read about how to cite chatbots in the following: See https://www.chicagomanualofstyle.org/qanda/data/faq/topics/Documentation/faq0422.html
You can read this article about the original and current reaction to Eliza: See “From ELIZA to ChatGPT, Our Digital Reflections Show the Dangers of AI - Vox.” n.d. Accessed July 11, 2023. https://www.vox.com/future-perfect/23617185/ai-chatbots-eliza-chatgpt-bing-sydney-artificial-intelligence-history.
Now, if you do not have all this long history of living with what are now called chatbots, you might be more alarmed with the current chatbot developments than I am. Because my focus is genealogy, I tend to see new technology in the light of how it might help me be either more accurate or more efficient or both. On a scale from one to ten, Eliza didn't make the scale for either accuracy or efficiency. In fact, it didn't rate in utility. So how do the new chatbot programs measure up? I guess that is why I am writing this probably long series of articles. At the time of this post, to use my own jargon, the jury is still out. So far, I see a lot of benefits from the new chatbot technology but only a few of the benefits relate directly to genealogical research. However, AI in general including handwriting recognition, computer-aided trees, computer-aided indexing and other developments are already having a huge impact on genealogical research.
More to come.
No comments:
Post a Comment