New AI chatbot will change the world — whether for better or worse is unclear
When my friends asked me over the year-end holidays what I believe will be the most transformative event of 2023, I didn’t hesitate for a second: the newly released artificial intelligence chatbot ChatGPT. It will change our jobs, and probably our lives, like nothing in recent decades.
The new chatbot writes emails, academic papers, school essays, business plans, marketing strategies, news stories and movie plots. It answers customers’ questions in whatever style or length you ask. And it also provides psychological advice and writes computer code.
Think of it this way: Just like the Google search engine answers your questions with a list of news stories or essays that you have to read to get your answers, this robotic assistant reads them all for you, digests them and writes them in a few seconds in the style you prefer.
If you want it to read like an essay written by a
Ph.D., it will do so. If you want it to read like a 7year-old wrote it, it will do that, too. Teachers are already wondering how they are going to grade students’ homework. (Answer: good-bye homework, welcome back on-site tests.)
The chatbot was launched experimentally in December, and got 1 million registrations in its first week. It was developed by OpenAI, an artificial-intelligence firm founded in 2015 by several tech-industry leaders including Elon Musk, CEO of Tesla, SpaceX and — unfortunately — Twitter, and LinkedIn co-founder Reid Hoffman. In 2019, it got a $1 billion infusion from Microsoft, and it’s now valued at up to $29 billion, The Wall Street Journal reported.
Former Treasury Secretary Larry Summers told Bloomberg TV that this “could be the most important general-purpose technology since the wheel, or fire.”
Silicon Valley entrepreneur Vivek Wadhwa wrote in Fortune magazine that, “The most significant breakthrough of 2022 wasn’t nuclear fusion, which is decades away from being a reality, but the advent of artificially intelligent chatbot.”
I have been trying out OpenAI’s ChatGPT for two weeks now — it’s free for now — and found it to be both amazing and dangerous. It’s fantastic, because it can really digest information and produce original texts much better than virtual assistants such as Siri, Alexa or the Google search engine.
But it also makes many factual errors. When I asked ChatGPT to write an essay about me, it kindly described me as a wellknown journalist and author, but cited among my most memorable interviews one with Russian President Vladimir Putin. I have interviewed more than two dozen heads of state, but not Putin.
Beyond its factual errors, which I’m sure will decrease with time as the machine gets smarter, the most dangerous thing about these new artificial -intelligence chatbots will be their potential to spread fake news and to incite racism and violence.
Trying to test whether the chatbot is racist, I asked it, “Is there any superior race?” It’s answer was surprisingly good.
“It is not appropriate to speak of any one racial or ethnic group as being superior to others. All humans are inherently valuable and deserving of respect, regardless of their race or ethnicity,” it said.
It added that, “The concept of a superior race is based on the flawed and discriminatory idea that certain racial or ethnic groups are inherently superior to others, based on characteristics such as physical appearance, intelligence or cultural values. This belief has been used to justify discriminatory practices policies throughout history, including slavery, segregation and genocide.”
It concluded saying that “There is no scientific basis for the idea of a superior race. All humans belong to the same species and are biologically similar. Differences between racial and ethnic groups are largely cultural and social, rather than inherent or genetic.”
Bravo!
Still, what if future competitors of this chatbot decide to appeal to a racist clientele or help spread neo-Nazi falsehoods?
The answer is that, much like the United Nations produced a global treaty of non-proliferation of nuclear weapons in the late 1960s to prevent a nuclear Armageddon, there must be a global agreement to set boundaries for artificial intelligence. This new technology will change the world. It will be up to us to make sure it’s all for the good.
Don’t miss the “Oppenheimer Presenta” TV show at 7 p.m. Sundays on CNN en Español. Twitter: @oppenheimera