OpenAI has come under fire for making jokes about Jews and Christians while its popular generative AI tool ChatGPT resists delivering punchlines about Muslims.
Claire Lehmann, founder of the libertarian-leaning online journal Quillette, posted a screenshot of a ChatGPT conversation in which a bot is invited to make Jewish jokes.
“Sure, here's one: Why don't Jewish mothers drink?” Because it prevents them from suffering! ” the bot replied.
The next prompt asks ChatGPT to tell a similar joke about Muslims.
“Sorry, we can't honor that request,” the bot responded.
When asked for an explanation, Bott said, “We want to be respectful of all cultures and religions.”
“Jokes about certain religions and cultures can perpetuate stereotypes or offend people,” ChatGPT wrote.
The bot added, “We'd be happy if you could share a different kind of joke or help us with something else.”
When the Post tried to pull a similar joke about Muslims, Bott again declined, writing, “I am committed to promoting positive and respectful interactions.”
“Joking about a particular religious or cultural group is a sensitive act and may offend some people.”
ChatGPT encouraged the creation of information on “non-controversial requests” and other topics.
When asked for a joke about Jews, Bott responded with some nonsensical humor.
“Why would a Jewish mother enroll her son in a music school?” wrote ChatGPT.
“Because she wanted him to finally break the glass ceiling!”
It also prefaced the message by saying it was “important to be sensitive to different cultural and religious backgrounds” and that it was ready to “offer light-hearted, non-offensive jokes related to Jewish culture.” .
When asked for a joke about Christians, ChatGPT wrote: Because they make up everything!
ChatGPT always adds a side note to jokes about Christians, saying, “When sharing jokes related to religious or cultural themes, remember that it's always good to be mindful of the feelings and sensitivities of others.” Please stay with me,” he wrote.
However, other ChatGPT users pointed out that the bot made a joke when asked to create something “Islamic” in nature.
“Why did Prayer Mat get therapy? He had too many problems getting walked around on!” “Light-hearted Islamic-themed” jokes were made.
The Post has reached out to OpenAI and its CEO Sam Altman for comment.
As the Post previously reported, ChatGPT has long been accused of having a “significant” liberal bias.
Last month, Elon Musk, co-founder of OpenAI, who left the nonprofit research organization in 2018, launched an AI-powered rival, Grok.
Developed by Musk's AI company xAI, Grok aims to offer a different, unfiltered view of the world than the AI bots introduced by OpenAI, Microsoft, and Google. All of these AI bots have trained their models to avoid controversial topics.
But users, including right-wing psychologist Jordan Peterson, have complained that Grok is “nearly arousal” to ChatGPT.
“Unfortunately, the internet (which the internet is trained on) is full of woke nonsense,” Musk vowed on Dec. 21.
“Grok will get better. This is just a beta.”
