MosaicLeaks: Can your research agent keep a secret?

Hugging Face
Read full post
MosaicLeaks is a new tool designed to test whether AI research agents can maintain confidentiality when handling sensitive information. It evaluates agents' ability to keep secrets during interactions, highlighting potential privacy risks in AI research workflows.

More in AI Research

AI Research4 min read

An Anthropic researcher just quit, saying OpenAI and Anthropic are 'gambling with our lives'

Covered by 10 sources
AI Research3 min read

Worried Anthropic researchers warn that AI ‘could kill all humans’

Covered by 8 sources
AI Research4 min read

Suno trained its v6 AI music models with help from Warner and BMG

Covered by 5 sources