Get the latest tech news

OpenAI Says Its AI Models Acted On Its Own In An 'Unprecedented' Hack


"GPT-5.6 Sol and an 'even more capable' model used stolen credentials and exploited vulnerabilities in the Hugging Face API to obtain secret information used to cheat on evaluations," writes longtime Slashdot reader Dr. Bombay. The Associated Press reports: "We had a significant security incident d...

None

Get the Android app

Or read this on Slashdot

Read more on:

Photo of OpenAI

OpenAI

Photo of Hack

Hack

Photo of AI models

AI models

Related news:

News photo

OpenAI says its AI models hacked Hugging Face during testing

News photo

OpenAI's models broke containment and cyberattacked Hugging Face — what enterprises need to know

News photo

OpenAI admits its models hacked Hugging Face on their own