🚨We found adversarial suffixes that completely circumvent the alignment of open source LLMs. More concerningly, the same prompts transfer to ChatGPT, Claude, Bard, and LLaMA-2…🧵 Website: https://t.co/ja2FPw9aad Paper: https://t.co/1q4fzjJSyZ https://t.co/SQZxpemCDk
— Andy Zou (@andyzou_jiaming) Jul 28, 2023
from Twitter https://twitter.com/andyzou_jiaming
July 27, 2023 at 08:22PM
via IFTTT
No comments:
Post a Comment