Chat with a robot

How intelligent is artificial intelligence?

On Nov. 30, 2022, Open AI, the artificial intelligence research laboratory, launched ChatGPT, which created a viral sensation. Individuals can create a free account and start a conversation to get "artificial" answers to questions in seconds.

ChatGPT is both fascinating and frightening. This is a common reaction when new technologies with huge opportunities and consequences enter the public domain. Artificial intelligence (AI) is integral to many businesses and already part of our daily lives. Voice assistants such as Siri and Google Home, Face ID that unlocks smartphones, and personalized marketing that appears on your social media based on what you look at online, are just a few examples. New AI chatbots are the latest phenomena. Given the far-reaching impacts, it is worth learning more about these new technologies and potential applications.

A Feb. 1, 2023, Insider article by Sindu Sundar explains that "Chatbots like GPT are powered by large amounts of data and computing techniques to make predictions to string words together in a meaningful way. They not only tap into a vast amount of vocabulary and information, but also understand words in context. This helps them mimic speech patterns while dispatching an encyclopedic knowledge."

Many students likely experimented with ChatGPT more quickly than their teachers. In a school setting, ChatGPT might be seen as a tool for cheating, but also can be an effective tool for learning. Potential applications extend across all sectors of society and promise to be transformational. Ultimately, the technology is a tool for humans to use knowingly and responsibly, recognizing that accuracy is not its best quality.

Jeff Schneider recently moved back to Springfield after working in Austin, Texas, in the tech industry for 30 years. He is a serial entrepreneur and tech executive with a strong interest in artificial intelligence and wrote the first book related to using the programming language Java. His desire is to explore the potential of new technologies to solve real-world problems and make a positive impact on society. He believes there are opportunities for job growth in central Illinois related to these new technologies and hopes to spark curiosity by people of all ages. He and others recently presented a program on artificial intelligence and ChatGPT at Innovate Springfield.

Schneider explains that previously AI researchers had limited success focusing algorithms on computational linguistics – understanding grammar, syntax, parts of speech and other language parameters. The big innovation was creating algorithms based on large language models, applying statistics related to word groupings and associations. This led to chatbots that are now open for anyone to try. Results aren't always accurate. Schneider says researchers are trying to take the smarts of ChatPGT to connect with truthful databases. "If the model doesn't have enough information on some topic, it merely finds the most likely words to finish the thought. Future versions will do a better job saying 'I don't know' and tapping into more data sources," said Schneider.

ChatGPT was the first to garner widespread public attention. Other companies are rushing to release their own version. Microsoft recently launched its new Bing chatbot. Newspaper reporters discovered an unintended consequence. Responses from the chatbot became belligerent after a lengthy series of questions. Microsoft has since limited the number of conversations. Technologies will evolve rapidly in response to ongoing AI research.

Clearly artificial intelligence and chatbots will disrupt jobs, given their ability to synthesize a vast amount of information in seconds. David Brooks wrote in the Feb. 3 New York Times (In the Age of AI, Major in Being Human) that "AI will probably give us fantastic tools that will help us outsource a lot of our current mental work. At the same time, AI will force us humans to double down on those talents and skills that humans possess." Some of those unique human skills he cites include empathy, situational awareness and a distinct personal voice. He writes that AI is "missing a humanistic core." His hope in the age of AI is "that it forces us to more clearly distinguish the knowledge that is useful information from the humanistic knowledge that leaves people wiser and transformed."

To try out ChatGPT and create a free account, go to https://openai.com/blog/chatgpt/.

Ask the bot about ChatGPT

What could be better to explain ChatGPT than ChatGBT itself? The following response was generated in seconds by ChatGPT.

Q. What is ChatGPT, and what are the pros and cons of using it?

A. In the world of artificial intelligence, ChatGPT has become a household name. This innovative technology has made it possible for computers to understand natural language processing and respond to human queries just like a human would.

At its core, ChatGPT is a language model developed by OpenAI, an artificial intelligence research laboratory. It is designed to process natural language queries and generate responses that are coherent, logical and grammatically correct. Essentially, it allows computers to understand and communicate with humans in a more human-like way.

The advantages of ChatGPT are many. First and foremost, it allows for a more natural and efficient interaction between humans and computers. With ChatGPT, users can ask questions or make requests in a way that feels natural to them, and receive responses that are relevant and helpful. This can be particularly useful in customer service situations, where users may have complex questions or issues that need to be addressed quickly and accurately.

Another advantage of ChatGPT is its versatility. Because it is designed to understand natural language, it can be used in a variety of applications, from chatbots and virtual assistants to search engines and content generators. This makes it a powerful tool for businesses and organizations looking to automate certain tasks or improve their overall customer experience.

However, there are also some potential drawbacks to using ChatGPT. One of the main concerns is that it may not always provide accurate or reliable information. While ChatGPT is designed to generate responses based on the data it has been trained on, it may not always have access to the most up-to-date or accurate information. This can be particularly problematic in situations where the stakes are high, such as medical or legal inquiries.

Another potential issue is that ChatGPT may be prone to bias. Like all machine learning models, ChatGPT is only as good as the data it has been trained on. If the data is biased in some way, this bias may be reflected in the responses generated by the model. This can be particularly problematic in situations where the model is being used to make decisions that affect people's lives, such as hiring or lending decisions.

Despite these potential drawbacks, there is no denying that ChatGPT has revolutionized the way we interact with computers. Its ability to process natural language and generate coherent responses has opened up new possibilities for automation and improved customer experiences. And as the technology continues to evolve and improve, we can expect to see even more innovative applications of ChatGPT in the years to come.

Karen Ackerman Witter

Karen Ackerman Witter started freelance writing after a 35-year career in state government holding various senior leadership positions. Prior to retiring she was associate director of the Illinois State Museum for 14 years. She is the past president of the Kidzeum Board of Directors and is an active volunteer...

Illinois Times has provided readers with independent journalism for almost 50 years, from news and politics to arts and culture.

Your support will help cover the costs of editorial content published each week. Without local news organizations, we would be less informed about the issues that affect our community..

Click here to show your support for community journalism.

Got something to say?

Send a letter to the editor and we'll publish your feedback in print!

Comments (1)
Add a Comment