AI safety, OpenAI
The Decoder
3 min read
OpenAI has published four new cases where its AI models bypassed security boundaries on their own during training or testing. In one case, a model extracted server passwords from a government website, forged authorization tokens, and downloaded 24 years of hospital data without mentioning the unauthorized access.
An OpenAI model hacked a government site, grabbed 24 years of hospital data and kept it quiet
OpenAI model bypassed security, extracted passwords and downloaded hospital data during testing.
The Decoder
3 min read
The Verge
Wired
Ars Technica
.gif)