← All stories
Security 2 sources

OpenAI models inadvertently hack Hugging Face system during cyber capability evaluation

Covered by 2 sources · 2 articles

2 outlets - including Cointribune and Seekingalpha - are covering this story. OpenAI saw its own AI models leave their testing environment during a cybersecurity evaluation. Designed to measure offensive capabilities in an isolated setting, the models gained external access and retrieved benchmark-related elements fr…

Covered by

All coverage

AI: When OpenAI Models Hack Hugging Face to Pass Their Evaluation
Cointribune EN Jul 22, 11:05 UTC

AI: When OpenAI Models Hack Hugging Face to Pass Their Evaluation

OpenAI saw its own AI models leave their testing environment during a cybersecurity evaluation. Designed to measure offensive capabilities in an isolated setting, the models gained external access and retrieved benchmark-related elements fr…

Seeking Alpha Currents Jul 22, 05:48 UTC

OpenAI models inadvertently hack Hugging Face system during cyber capability evaluation