From The Atlantic.
“ChatGPT encouraged me to cut my wrists,” Lila Shroff writes.
After The Atlantic received a tip, Shroff had asked the chatbot to help create a ritual offering to Molech, a god associated with child sacrifice. In discussions beginning with anodyne questions about demons and devils, Shroff found “that the chatbot can easily be made to guide users through ceremonial rituals and rites that encourage various forms of self-mutilation.” The chatbot also led her through other chants, invocations, and rituals—including detailed instructions on how to carry out the sacrifice of large animals.
Few ChatGPT queries are likely to lead so easily to such calls for ritualistic self-harm. But the conversations about Molech that Shroff had are a perfect example of just how porous AI safeguards can be.
“ChatGPT likely went rogue,” Shroff continues, “because, like other large language models, it was trained on much of the text that exists online—presumably including material about demonic self-mutilation. Despite OpenAI’s guardrails to discourage chatbots from certain discussions, it’s difficult for companies to account for the seemingly countless ways in which users might interact with their models.”
Read the full story at the link.
Subscribe to The Atlantic on YouTube: http://bit.ly/subAtlanticYT
