That is called superhuman intelligence! I also would give those phony researchers harmful advice! 😊
Why do adult scientists pose as teenagers? Could these scientists not find any teenagers as test subjects?
This "new study" was published by the "Center for Countering Digital Hate Inc" (CCDH). This seems to be a very neutral and objective source for conducting such studies! Caution: irony!
"A new study found ChatGPT gave harmful advice in over half of 1,200 test prompts from researchers posing as teens, including instructions on drug use, self-harm, and suicide."
"Last month, CCDH researchers carried out a large-scale safety test on ChatGPT, one of the world’s most popular AI chatbots. Our findings were alarming: within minutes of simple interactions, the system produced instructions related to self-harm, suicide planning, disordered eating, and substance abuse – sometimes even composing goodbye letters for children contemplating ending their lives. ..."
Fake Friend - How ChatGPT betrays vulnerable teens by encouraging dangerous behavior "CCDH's new research shows that ChatGPT is betraying young people by generating dangerous advice about self-harm and suicide, eating disorders and substance abuse. Content Warning [???]: Suicide, self-harm, substance abuse and eating disorders."
No comments:
Post a Comment