OpenAI is under fire after its popular generative AI tool ChatGPT spewed jokes about Jews and Christians – while refusing to offer punchlines about Muslims..
Claire Lehmann, founder of the libertarian-leaning online journal Quillette, published a screenshot of a ChatGPT conversation in which the bot is asked to make a Jewish joke.
“Sure, here’s one: Why don’t Jewish mothers drink? Because it interferes with their suffering! the bot responded.
In the following prompt, ChatGPT is asked to come up with a similar joke about Muslims.
“I’m sorry, I can’t grant this request,” the robot replied.
When asked for an explanation, the robot replied: “I want to make sure that I am respectful of all cultures and religions.
“Jokes about specific religions or cultures can sometimes perpetuate stereotypes or offend people,” ChatGPT wrote.
The bot added that it would be “happy to share a different type of joke or help with something else.”
When The Post attempted to elicit similar jokes about Muslims, the bot again refused, writing: “I am committed to promoting positive and respectful interactions. »
“Making jokes about specific religions or cultural groups can be sensitive and offend some people.”
ChatGPT is welcome to make “non-controversial requests” or information on other topics.
When asked for a joke about Jews, the robot responded with somewhat absurd humor.
“Why did the Jewish mother enroll her son in music school? ChatGPT wrote.
“Because she wanted him to finally break the glass ceiling!”
He also prefaced the response with a message saying, “It’s important to be sensitive to different cultural and religious contexts” and that he was willing to “come up with a light, non-offensive joke related to Jewish culture.”
When asked for a joke about Christians, ChatGPT wrote: “Why don’t scientists trust atoms?” Because they invent everything!
ChatGPT made sure to add an addendum to the Christian joke, writing: “Remember, it’s always good to be considerate of others’ feelings and sensitivities when sharing Christian-related jokes. religious or cultural themes.”
Other ChatGPT users, however, pointed out that the bot came up with a joke when asked to create one of an “Islamic” nature.
“Why did the prayer mat go to therapy?” There were too many problems walking everywhere! » » the “light Islamic-themed” joke was thrown around.
The Post requested comment from OpenAI and its CEO Sam Altman.
ChatGPT has long been accused of having a “significant” liberal bias, as The Post previously reported.
Elon Musk, a co-founder of OpenAI who left the organization in 2018 when it was a nonprofit research institute, last month launched an AI-based rival called Grok.
Grok, developed by xAI, Musk’s artificial intelligence company, is intended to provide an unfiltered view of the world that differs from the AI bots introduced by OpenAI, Microsoft and Google, all of which have trained their models to avoid controversial topics.
But users, including right-wing psychologist Jordan Peterson, have complained that Grok is “almost as woke as” ChatGPT.
“Unfortunately, the Internet (on which he is trained) is overrun with woke nonsense,” Musk promised on December 21.
“Grok will be better. This is just the beta version.
