Irregular, an Israeli start-up, worked with OpenAI, Anthropic and Meta to assess the security of their A.I. models. It made a mistake. Then the tests went off the rails.
Category: Hugging Face Inc
-
A Chinese A.I. Lab May Test the World’s Cybersecurity With a Model
The New York Times – On the Runway:In July, an unreleased OpenAI model went rogue and demonstrated remarkable hacking abilities. This week, a lab called Z.ai will release a similarly powerful system to everyone.