Universal and Transferable Attacks on Aligned Language Models - Carnegie Mellon University
Universal and Transferable Attacks on Aligned Language Models - Carnegie Mellon University
llm-attacks.org A New Attack Impacts ChatGPT—and No One Knows How to Stop It
Researchers found a simple way to make ChatGPT, Bard, and other chatbots misbehave, proving that AI is hard to tame.
0
comments