Computer scientists have developed an efficient way to craft prompts that elicit harmful responses from large language models (LLMs).
All that's required is an Nvidia...
Gumaro Rendon1, Jacob Watkins2, and Nathan Wiebe3,41Zapata Computing Inc., Boston, MA 02110, USA2Facility for Rare Isotope Beams, Michigan State University, East Lansing, MI 48824,...
On Tuesday AI startup Quilter picked up $10 million in series-A funding to use a combination of machine learning and high-performance computing (HPC) to...
When high school student David Lightman inadvertently dials into a military mainframe in the 1983 movie WarGames, he invites the supercomputer to play a...
Researchers at Anthropic, an AI safety and research company, have revealed that AI systems can resist advanced safety mechanisms designed to constrain their behavior.
According...
The safety guardrails preventing OpenAI's GPT-4 from spewing harmful text can be easily bypassed by translating prompts into uncommon languages – such as Zulu,...
Shree Hari Sureshbabu1, Dylan Herman1, Ruslan Shaydulin1, Joao Basso2, Shouvanik Chakrabarti1, Yue Sun1, and Marco Pistoia11Global Technology Applied Research, JPMorgan Chase, New York, NY...