The more sophisticated AI models get, the more likely they are to lie
Human feedback training might incentivize offering any response– even incorrect ones. When a research study group led by Amrit Kirpalani, a medical teacher at Western University in Ontario, Canada, examined…
Read More »
AI models believe racist stereotypes about African Americans that predate the Civil Rights movement — and they ‘try to hide it when confronted’
The AI designs obscured the hidden bigotry by explaining African Americans with favorable qualities such as “brilliant” when asked straight about this group. (Image credit: 400tmax/Getty Images) Researchers have actually…
Read More »