TopHot
OpenAI’s flagship AI model has gotten more trustworthy but easier to trick
OpenAI’s flagship AI model has gotten more trustworthy but easier to trick Image: MicrosoftOpenAI’s GPT-4 large language model may be more trustworthy than GPT-3.5 but also more vulnerable to jailbreaking and bias, according to research backed by Microsoft.
The paper — by researchers from the University of Illinois Urbana-Champaign, Stanford University, University of California, Berkeley, Center for AI Safety, and Micr...
Category:
