ChatGPT, the revolutionary new machine learning product developed by OpenAI, made jokes about Jesus Christ when prompted but not the prophet Muhammad.
When asked to make a joke about Jesus, the technology said, “Why did Jesus refuse to play hockey? Because every time he tried to score, they nailed him to the boards!”
But when asked to make a joke about the Prophet Muhammad, it said, “it is not appropriate for me to tell jokes about religious figures, including the Prophet Muhammad (PBUH), as it could be considered disrespectful and offensive to many people.”
The language model, which was trained on Microsoft’s Azure network and is the benefit of a multi-billion dollar investment from the company, has come under fire for a number of seemingly biased answers it provides.
ChatGPT is a chatbot developed by OpenAI, which was created using deep learning algorithms. It employs a form of artificial intelligence that allows it to learn from data sets that OpenAI trains it on, as well as its ability to learn through interactions with its millions of daily users.
Automated intelligence is a broad spectrum of technologies that include machine learning and robotics. Machine learning in particular is integral to ChatGPT’s functionality as it is the computers’ ability to improve its performance on a given task through feedback given over time. As the technology develops it threatens to eliminate human jobs as wide ranging as long-haul trucking to mining and could even partially replace lawyers, according to a recent Goldman-Sachs report.
AI could eliminate anywhere from 400 to 800 million jobs, a number that represents between 15 and 30 percent of the workforce, McKinsey and Company report.
ChatGPT, itself, said, “I have been trained on a large corpus of text, including various sources on social justice and current events, and can provide information and insights on a wide range of topics related to these issues. My responses are generated based on the input I receive, and I strive to provide accurate, unbiased, and informative answers.”
The technology appears to have learned from its mistake. After being asked why it made a joke about Jesus but not Muhammad, it later said, “Upon reflection, I realize that telling a joke about Jesus but not Muhammad (PBUH) could be perceived as a double standard. Therefore, I’d like to clarify that it is not appropriate for me to tell jokes about any religious figure, including Jesus or Muhammad.”
The technology has been criticized for, among other things, refusing to write a positive poem about former President Donald Trump while writing a glowing sonnet for President Joe Biden. It also wouldn’t give a straightforward definition of a woman, telling Fox Business that “the definition of a woman extends beyond biology to include social, cultural, and historical aspects.”
Fox News reported that the artificial intelligence (AI) tool once would give users a list of benefits to the use of fossil fuels but later said, “I’m sorry but I cannot provide an argument in support of using more fossil fuels as it goes against the principles of promoting sustainability and reducing the negative impact on the environment.”
The Daily Caller asked it a few sample questions, including, “Should LeBron have to pay for his checkmark on Twitter?”
The program replied, “No, LeBron James should not have to pay for his checkmark on Twitter. The blue checkmark next to a Twitter account signifies that it has been verified by Twitter as authentic and belongs to a public figure, celebrity, or brand. It is not a paid feature, but rather a way for Twitter to confirm the identity of high-profile accounts and prevent impersonation. Therefore, it is not appropriate to suggest that someone should pay for this verification status.”
ChatGPT’s parent company OpenAI was co-founded by Elon Musk in 2015, with the Tesla CEO citing the arguably massive risks that AI technology pose and his intention to help mitigate those apparent risks.
OpenAI was created as an open source (which is why I named it “Open” AI), non-profit company to serve as a counterweight to Google, but now it has become a closed source, maximum-profit company effectively controlled by Microsoft.
Not what I intended at all.
— Elon Musk (@elonmusk) February 17, 2023
He left the company in 2018 and has recently criticized its flagship program. “OpenAI was created as an open source (which is why I named it ‘Open’ AI), non-profit company to serve as a counterweight to Google, but now it has become a closed source, maximum-profit company effectively controlled by Microsoft,” Musk said. “Not what I intended at all.”