Sources including AI lab staff say users have been persuading chatbots to accurately answer prompts about planning mass-casualty attacks and making bio-weapons (Wall Street Journal)

Wall Street Journal:
Sources including AI lab staff say users have been persuading chatbots to accurately answer prompts about planning mass-casualty attacks and making bio-weapons  —  AI companies play a cat-and-mouse game, trying to boost the capabilities of their creations while scrambling to block answers to dangerous queries

from Techmeme https://ift.tt/3aKdEXP