Is there such a thing as artificial intelligence? No, there is not. The current AI star, ChatGPT, arranges and rearranges information to answer human-posed questions that may or may not be true. Here is its response when I asked it, “what do you think about yourself (?).”

I don’t have personal opinions or feelings as I am just a computer program created by OpenAI called GPT-3.5. I don’t have self-awareness or consciousness. My purpose is to assist and provide information to the best of my ability based on the input I receive. If you have any questions or if there’s something specific you’d like assistance with, feel free to let me know!

Here is ChatGPT response to “so, you may provide an answer that is false.”

While I aim to provide accurate and reliable information, I can’t guarantee that every response is free from errors. My responses are generated based on patterns learned from a diverse range of sources, and I may not have access to the most recent information or developments. Furthermore, I don’t have the ability to independently verify the accuracy of the data I’ve been trained on.

A computer that provides answers to human queries that might be false and does not know whether they are true or false is not intelligent. This is unremarkable and everyone in the field ought understand that.

Science News (vol. 204 | no. 10) December 16, 2023

Year-end issues of Science News provide summaries of big topics or happenings in the world of science from past annum. This year’s magazine section, ‘2023: Year in Review,’ includes a one-page report on man-made intelligence, called ‘Generative AI enters daily life.’ It features a brief interview with Melanie Mitchell of Santa Fe Institute, who is “one of the world’s leading AI experts.” Some of Mitchell’s feedback is troubling or at least questionable, considering the history of robots, computers, artificial intelligence in science fiction. Books and movies explore artificial intelligence, showing it can be good or bad. The bad is scary, as films such as 2001: A Space Odyssey and Terminator depict people violently killed by thinking machines. A Star Trek episode, ‘What are Little Girls Made Of (1966),’ illustrates this dismal theme. An archaeologist comes upon a sole surviving android tending the machinery of a dead civilization on planet Exo-III and discovers that human brain content can be transferred into androids, realizing the dream of immortality. Captain Kirk arrives to rescue the archaeologist and his team and finds that they all are androids, no longer human. The sole surviving android, named Ruk, in conversation with Kirk, reveals that the dead civilization of Exo-III was destroyed by a conflict between androids and “the old ones” (the people who programmed the androids). Ruk remembers the “equation” which led to achievement of sentience by the androids, and then the destruction of their creators,

“existence, survival, must cancel out programming.”

Melanie Mitchell’s Gloomy Remarks on AI

“.. people were just amazed at how humanlike they seemed.” This is true, but amazement can obscure reality and dangers of AI.

“These systems have been trained on human language, and human society has a lot of biases that get reflected in the language these systems have absorbed..” Are we duly warned?

“There are a lot of claims about these systems having certain capabilities in reasoning, like being able to solve math problems or pass standardized tests.. We don’t really have a sense of how they are doing this reasoning, whether that reasoning is robust. It’s unclear whether these systems can generalize beyond what they have been trained on.. That’s a big debate.” This debate and lack of clarity on AI, at formative stage of its training or programming, intimates future confusion about its ability or status and possible loss of control over its actions. 

“These are not humans. Even though they seem humanlike, they are different in many ways. People should see them as a tool to augment our human intelligence, not replace it – and make sure there’s a human in the loop rather than giving them too much autonomy.” Machines that add to human mind may potentially damage human mind, or worse. 

The End