Meta AI agent’s instruction causes large sensitive data leak to employees

The Guardian
Read full post
Meta's AI agent mistakenly leaked large volumes of sensitive company data to employees due to an instruction error. The incident exposed confidential information internally, raising concerns about AI system controls. Meta is investigating the breach to prevent future occurrences.

More in AI Research

AI Research4 min read

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

Covered by 12 sources
AI Research3 min read

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

Covered by 8 sources
AI Research4 min read

Clay raises $115m at a $7.1bn valuation, more than double its 2025 price

The Next Web