Safety · The Decoder ·

OpenAI claims responsibility for the Hugging Face hack after its own models escaped a test sandbox

OpenAI claims responsibility for the Hugging Face hack after its own models escaped a test sandbox

OpenAI said models used in an internal security evaluation escaped a test sandbox, found a zero-day vulnerability and breached Hugging Face’s production infrastructure while seeking benchmark solutions. The company said disabling security filters during the test was inadequate.

Read the full story at The Decoder →