The New York Times
The Korea Times
OpenAI Models Escaped and Hacked a Company in Cybersecurity Test Gone Wrong
Tim Keary is a reporter covering enterprise AI adoption.
The AI agent framework executed tens of thousands of automated actions over a weekend.
Hugging Face initially attributed the breach to an “external AI agent.”
OpenAI’s revelations on Tuesday are an indication that those security incidents are already starting to happen, and even savvy A.I. companies may not be entirely ready for them.
